diff options
author | Jeff Crouse <jefftimesten@gmail.com> | 2013-01-05 15:03:54 -0500 |
---|---|---|
committer | Jeff Crouse <jefftimesten@gmail.com> | 2013-01-05 15:03:54 -0500 |
commit | 258d5850c91e0d37a36c6bae0a25314f8149b05a (patch) | |
tree | 7d87df8436a588a4338a460499d8614006b6254a /youtube_dl | |
parent | 187da2c093ad1013ea714a464e615de9aa773482 (diff) | |
parent | 8e5f7618704805caf9fac093e604834237a7965c (diff) | |
download | youtube-dl-258d5850c91e0d37a36c6bae0a25314f8149b05a.tar.xz |
Merge branch 'master' of https://github.com/rg3/youtube-dl
Conflicts:
.gitignore
LATEST_VERSION
Makefile
youtube-dl
youtube-dl.exe
youtube_dl/InfoExtractors.py
youtube_dl/__init__.py
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/FileDownloader.py | 1399 | ||||
-rwxr-xr-x[-rw-r--r--] | youtube_dl/InfoExtractors.py | 7158 | ||||
-rw-r--r-- | youtube_dl/PostProcessor.py | 352 | ||||
-rw-r--r-- | youtube_dl/__init__.py | 1008 | ||||
-rwxr-xr-x | youtube_dl/__main__.py | 16 | ||||
-rw-r--r-- | youtube_dl/update.py | 160 | ||||
-rw-r--r-- | youtube_dl/utils.py | 785 | ||||
-rw-r--r-- | youtube_dl/version.py | 2 |
8 files changed, 5647 insertions, 5233 deletions
diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 4449fe711..be9e4918e 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -1,693 +1,738 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- -import httplib +from __future__ import absolute_import + import math +import io import os import re import socket import subprocess import sys import time -import urllib2 +import traceback if os.name == 'nt': - import ctypes + import ctypes -from utils import * +from .utils import * class FileDownloader(object): - """File Downloader class. - - File downloader objects are the ones responsible of downloading the - actual video file and writing it to disk if the user has requested - it, among some other tasks. In most cases there should be one per - program. As, given a video URL, the downloader doesn't know how to - extract all the needed information, task that InfoExtractors do, it - has to pass the URL to one of them. - - For this, file downloader objects have a method that allows - InfoExtractors to be registered in a given order. When it is passed - a URL, the file downloader handles it to the first InfoExtractor it - finds that reports being able to handle it. The InfoExtractor extracts - all the information about the video or videos the URL refers to, and - asks the FileDownloader to process the video information, possibly - downloading the video. - - File downloaders accept a lot of parameters. In order not to saturate - the object constructor with arguments, it receives a dictionary of - options instead. These options are available through the params - attribute for the InfoExtractors to use. The FileDownloader also - registers itself as the downloader in charge for the InfoExtractors - that are added to it, so this is a "mutual registration". - - Available options: - - username: Username for authentication purposes. - password: Password for authentication purposes. - usenetrc: Use netrc for authentication instead. - quiet: Do not print messages to stdout. - forceurl: Force printing final URL. - forcetitle: Force printing title. - forcethumbnail: Force printing thumbnail URL. - forcedescription: Force printing description. - forcefilename: Force printing final filename. - simulate: Do not download the video files. - format: Video format code. - format_limit: Highest quality format to try. - outtmpl: Template for output names. - ignoreerrors: Do not stop on download errors. - ratelimit: Download speed limit, in bytes/sec. - nooverwrites: Prevent overwriting files. - retries: Number of times to retry for HTTP error 5xx - continuedl: Try to continue downloads if possible. - noprogress: Do not print the progress bar. - playliststart: Playlist item to start at. - playlistend: Playlist item to end at. - matchtitle: Download only matching titles. - rejecttitle: Reject downloads for matching titles. - logtostderr: Log messages to stderr instead of stdout. - consoletitle: Display progress in console window's titlebar. - nopart: Do not use temporary .part files. - updatetime: Use the Last-modified header to set output file timestamps. - writedescription: Write the video description to a .description file - writeinfojson: Write the video description to a .info.json file - writesubtitles: Write the video subtitles to a .srt file - subtitleslang: Language of the subtitles to download - """ - - params = None - _ies = [] - _pps = [] - _download_retcode = None - _num_downloads = None - _screen_file = None - - def __init__(self, params): - """Create a FileDownloader object with the given options.""" - self._ies = [] - self._pps = [] - self._download_retcode = 0 - self._num_downloads = 0 - self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] - self.params = params - - @staticmethod - def format_bytes(bytes): - if bytes is None: - return 'N/A' - if type(bytes) is str: - bytes = float(bytes) - if bytes == 0.0: - exponent = 0 - else: - exponent = long(math.log(bytes, 1024.0)) - suffix = 'bkMGTPEZY'[exponent] - converted = float(bytes) / float(1024 ** exponent) - return '%.2f%s' % (converted, suffix) - - @staticmethod - def calc_percent(byte_counter, data_len): - if data_len is None: - return '---.-%' - return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0)) - - @staticmethod - def calc_eta(start, now, total, current): - if total is None: - return '--:--' - dif = now - start - if current == 0 or dif < 0.001: # One millisecond - return '--:--' - rate = float(current) / dif - eta = long((float(total) - float(current)) / rate) - (eta_mins, eta_secs) = divmod(eta, 60) - if eta_mins > 99: - return '--:--' - return '%02d:%02d' % (eta_mins, eta_secs) - - @staticmethod - def calc_speed(start, now, bytes): - dif = now - start - if bytes == 0 or dif < 0.001: # One millisecond - return '%10s' % '---b/s' - return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif)) - - @staticmethod - def best_block_size(elapsed_time, bytes): - new_min = max(bytes / 2.0, 1.0) - new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB - if elapsed_time < 0.001: - return long(new_max) - rate = bytes / elapsed_time - if rate > new_max: - return long(new_max) - if rate < new_min: - return long(new_min) - return long(rate) - - @staticmethod - def parse_bytes(bytestr): - """Parse a string indicating a byte quantity into a long integer.""" - matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) - if matchobj is None: - return None - number = float(matchobj.group(1)) - multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) - return long(round(number * multiplier)) - - def add_info_extractor(self, ie): - """Add an InfoExtractor object to the end of the list.""" - self._ies.append(ie) - ie.set_downloader(self) - - def add_post_processor(self, pp): - """Add a PostProcessor object to the end of the chain.""" - self._pps.append(pp) - pp.set_downloader(self) - - def to_screen(self, message, skip_eol=False): - """Print message to stdout if not in quiet mode.""" - assert type(message) == type(u'') - if not self.params.get('quiet', False): - terminator = [u'\n', u''][skip_eol] - output = message + terminator - if 'b' not in self._screen_file.mode or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr - output = output.encode(preferredencoding(), 'ignore') - self._screen_file.write(output) - self._screen_file.flush() - - def to_stderr(self, message): - """Print message to stderr.""" - print >>sys.stderr, message.encode(preferredencoding()) - - def to_cons_title(self, message): - """Set console/terminal window title to message.""" - if not self.params.get('consoletitle', False): - return - if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): - # c_wchar_p() might not be necessary if `message` is - # already of type unicode() - ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) - elif 'TERM' in os.environ: - sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding())) - - def fixed_template(self): - """Checks if the output template is fixed.""" - return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None) - - def trouble(self, message=None): - """Determine action to take when a download problem appears. - - Depending on if the downloader has been configured to ignore - download errors or not, this method may throw an exception or - not when errors are found, after printing the message. - """ - if message is not None: - self.to_stderr(message) - if not self.params.get('ignoreerrors', False): - raise DownloadError(message) - self._download_retcode = 1 - - def slow_down(self, start_time, byte_counter): - """Sleep if the download speed is over the rate limit.""" - rate_limit = self.params.get('ratelimit', None) - if rate_limit is None or byte_counter == 0: - return - now = time.time() - elapsed = now - start_time - if elapsed <= 0.0: - return - speed = float(byte_counter) / elapsed - if speed > rate_limit: - time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) - - def temp_name(self, filename): - """Returns a temporary filename for the given filename.""" - if self.params.get('nopart', False) or filename == u'-' or \ - (os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))): - return filename - return filename + u'.part' - - def undo_temp_name(self, filename): - if filename.endswith(u'.part'): - return filename[:-len(u'.part')] - return filename - - def try_rename(self, old_filename, new_filename): - try: - if old_filename == new_filename: - return - os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) - except (IOError, OSError), err: - self.trouble(u'ERROR: unable to rename file') - - def try_utime(self, filename, last_modified_hdr): - """Try to set the last-modified time of the given file.""" - if last_modified_hdr is None: - return - if not os.path.isfile(encodeFilename(filename)): - return - timestr = last_modified_hdr - if timestr is None: - return - filetime = timeconvert(timestr) - if filetime is None: - return filetime - try: - os.utime(filename, (time.time(), filetime)) - except: - pass - return filetime - - def report_writedescription(self, descfn): - """ Report that the description file is being written """ - self.to_screen(u'[info] Writing video description to: ' + descfn) - - def report_writesubtitles(self, srtfn): - """ Report that the subtitles file is being written """ - self.to_screen(u'[info] Writing video subtitles to: ' + srtfn) - - def report_writeinfojson(self, infofn): - """ Report that the metadata file has been written """ - self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn) - - def report_destination(self, filename): - """Report destination filename.""" - self.to_screen(u'[download] Destination: ' + filename) - - def report_progress(self, percent_str, data_len_str, speed_str, eta_str): - """Report download progress.""" - if self.params.get('noprogress', False): - return - self.to_screen(u'\r[download] %s of %s at %s ETA %s' % - (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) - self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' % - (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip())) - - def report_resuming_byte(self, resume_len): - """Report attempt to resume at given byte.""" - self.to_screen(u'[download] Resuming download at byte %s' % resume_len) - - def report_retry(self, count, retries): - """Report retry in case of HTTP error 5xx""" - self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) - - def report_file_already_downloaded(self, file_name): - """Report file has already been fully downloaded.""" - try: - self.to_screen(u'[download] %s has already been downloaded' % file_name) - except (UnicodeEncodeError), err: - self.to_screen(u'[download] The file has already been downloaded') - - def report_unable_to_resume(self): - """Report it was impossible to resume download.""" - self.to_screen(u'[download] Unable to resume') - - def report_finish(self): - """Report download finished.""" - if self.params.get('noprogress', False): - self.to_screen(u'[download] Download completed') - else: - self.to_screen(u'') - - def increment_downloads(self): - """Increment the ordinal that assigns a number to each file.""" - self._num_downloads += 1 - - def prepare_filename(self, info_dict): - """Generate the output filename.""" - try: - template_dict = dict(info_dict) - template_dict['epoch'] = unicode(long(time.time())) - template_dict['autonumber'] = unicode('%05d' % self._num_downloads) - filename = self.params['outtmpl'] % template_dict - return filename - except (ValueError, KeyError), err: - self.trouble(u'ERROR: invalid system charset or erroneous output template') - return None - - def _match_entry(self, info_dict): - """ Returns None iff the file should be downloaded """ - - title = info_dict['title'] - matchtitle = self.params.get('matchtitle', False) - if matchtitle: - matchtitle = matchtitle.decode('utf8') - if not re.search(matchtitle, title, re.IGNORECASE): - return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"' - rejecttitle = self.params.get('rejecttitle', False) - if rejecttitle: - rejecttitle = rejecttitle.decode('utf8') - if re.search(rejecttitle, title, re.IGNORECASE): - return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"' - return None - - def process_info(self, info_dict): - """Process a single dictionary returned by an InfoExtractor.""" - - info_dict['stitle'] = sanitize_filename(info_dict['title']) - - reason = self._match_entry(info_dict) - if reason is not None: - self.to_screen(u'[download] ' + reason) - return - - max_downloads = self.params.get('max_downloads') - if max_downloads is not None: - if self._num_downloads > int(max_downloads): - raise MaxDownloadsReached() - - filename = self.prepare_filename(info_dict) - - # Forced printings - if self.params.get('forcetitle', False): - print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace') - if self.params.get('forceurl', False): - print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace') - if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: - print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace') - if self.params.get('forcedescription', False) and 'description' in info_dict: - print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace') - if self.params.get('forcefilename', False) and filename is not None: - print filename.encode(preferredencoding(), 'xmlcharrefreplace') - if self.params.get('forceformat', False): - print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace') - - # Do nothing else if in simulate mode - if self.params.get('simulate', False): - return - - if filename is None: - return - - try: - dn = os.path.dirname(encodeFilename(filename)) - if dn != '' and not os.path.exists(dn): # dn is already encoded - os.makedirs(dn) - except (OSError, IOError), err: - self.trouble(u'ERROR: unable to create directory ' + unicode(err)) - return - - if self.params.get('writedescription', False): - try: - descfn = filename + u'.description' - self.report_writedescription(descfn) - descfile = open(encodeFilename(descfn), 'wb') - try: - descfile.write(info_dict['description'].encode('utf-8')) - finally: - descfile.close() - except (OSError, IOError): - self.trouble(u'ERROR: Cannot write description file ' + descfn) - return - - if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']: - # subtitles download errors are already managed as troubles in relevant IE - # that way it will silently go on when used with unsupporting IE - try: - srtfn = filename.rsplit('.', 1)[0] + u'.srt' - self.report_writesubtitles(srtfn) - srtfile = open(encodeFilename(srtfn), 'wb') - try: - srtfile.write(info_dict['subtitles'].encode('utf-8')) - finally: - srtfile.close() - except (OSError, IOError): - self.trouble(u'ERROR: Cannot write subtitles file ' + descfn) - return - - if self.params.get('writeinfojson', False): - infofn = filename + u'.info.json' - self.report_writeinfojson(infofn) - try: - json.dump - except (NameError,AttributeError): - self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.') - return - try: - infof = open(encodeFilename(infofn), 'wb') - try: - json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',)) - json.dump(json_info_dict, infof) - finally: - infof.close() - except (OSError, IOError): - self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn) - return - - if not self.params.get('skip_download', False): - if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)): - success = True - else: - try: - success = self._do_download(filename, info_dict) - except (OSError, IOError), err: - raise UnavailableVideoError - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self.trouble(u'ERROR: unable to download video data: %s' % str(err)) - return - except (ContentTooShortError, ), err: - self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) - return - - if success: - try: - self.post_process(filename, info_dict) - except (PostProcessingError), err: - self.trouble(u'ERROR: postprocessing: %s' % str(err)) - return - - def download(self, url_list): - """Download a given list of URLs.""" - if len(url_list) > 1 and self.fixed_template(): - raise SameFileError(self.params['outtmpl']) - - for url in url_list: - suitable_found = False - for ie in self._ies: - # Go to next InfoExtractor if not suitable - if not ie.suitable(url): - continue - - # Suitable InfoExtractor found - suitable_found = True - - # Extract information from URL and process it - videos = ie.extract(url) - for video in videos or []: - video['extractor'] = ie.IE_NAME - try: - self.increment_downloads() - self.process_info(video) - except UnavailableVideoError: - self.trouble(u'\nERROR: unable to download video') - - # Suitable InfoExtractor had been found; go to next URL - break - - if not suitable_found: - self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url) - - return self._download_retcode - - def post_process(self, filename, ie_info): - """Run the postprocessing chain on the given file.""" - info = dict(ie_info) - info['filepath'] = filename - for pp in self._pps: - info = pp.run(info) - if info is None: - break - - def _download_with_rtmpdump(self, filename, url, player_url): - self.report_destination(filename) - tmpfilename = self.temp_name(filename) - - # Check for rtmpdump first - try: - subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT) - except (OSError, IOError): - self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run') - return False - - # Download using rtmpdump. rtmpdump returns exit code 2 when - # the connection was interrumpted and resuming appears to be - # possible. This is part of rtmpdump's normal usage, AFAIK. - basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename] - args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)] - if self.params.get('verbose', False): - try: - import pipes - shell_quote = lambda args: ' '.join(map(pipes.quote, args)) - except ImportError: - shell_quote = repr - self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(args)) - retval = subprocess.call(args) - while retval == 2 or retval == 1: - prevsize = os.path.getsize(encodeFilename(tmpfilename)) - self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True) - time.sleep(5.0) # This seems to be needed - retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1]) - cursize = os.path.getsize(encodeFilename(tmpfilename)) - if prevsize == cursize and retval == 1: - break - # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those - if prevsize == cursize and retval == 2 and cursize > 1024: - self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.') - retval = 0 - break - if retval == 0: - self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(encodeFilename(tmpfilename))) - self.try_rename(tmpfilename, filename) - return True - else: - self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) - return False - - def _do_download(self, filename, info_dict): - url = info_dict['url'] - player_url = info_dict.get('player_url', None) - - # Check file already present - if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False): - self.report_file_already_downloaded(filename) - return True - - # Attempt to download using rtmpdump - if url.startswith('rtmp'): - return self._download_with_rtmpdump(filename, url, player_url) - - tmpfilename = self.temp_name(filename) - stream = None - - # Do not include the Accept-Encoding header - headers = {'Youtubedl-no-compression': 'True'} - basic_request = urllib2.Request(url, None, headers) - request = urllib2.Request(url, None, headers) - - # Establish possible resume length - if os.path.isfile(encodeFilename(tmpfilename)): - resume_len = os.path.getsize(encodeFilename(tmpfilename)) - else: - resume_len = 0 - - open_mode = 'wb' - if resume_len != 0: - if self.params.get('continuedl', False): - self.report_resuming_byte(resume_len) - request.add_header('Range','bytes=%d-' % resume_len) - open_mode = 'ab' - else: - resume_len = 0 - - count = 0 - retries = self.params.get('retries', 0) - while count <= retries: - # Establish connection - try: - if count == 0 and 'urlhandle' in info_dict: - data = info_dict['urlhandle'] - data = urllib2.urlopen(request) - break - except (urllib2.HTTPError, ), err: - if (err.code < 500 or err.code >= 600) and err.code != 416: - # Unexpected HTTP error - raise - elif err.code == 416: - # Unable to resume (requested range not satisfiable) - try: - # Open the connection again without the range header - data = urllib2.urlopen(basic_request) - content_length = data.info()['Content-Length'] - except (urllib2.HTTPError, ), err: - if err.code < 500 or err.code >= 600: - raise - else: - # Examine the reported length - if (content_length is not None and - (resume_len - 100 < long(content_length) < resume_len + 100)): - # The file had already been fully downloaded. - # Explanation to the above condition: in issue #175 it was revealed that - # YouTube sometimes adds or removes a few bytes from the end of the file, - # changing the file size slightly and causing problems for some users. So - # I decided to implement a suggested change and consider the file - # completely downloaded if the file size differs less than 100 bytes from - # the one in the hard drive. - self.report_file_already_downloaded(filename) - self.try_rename(tmpfilename, filename) - return True - else: - # The length does not match, we start the download over - self.report_unable_to_resume() - open_mode = 'wb' - break - # Retry - count += 1 - if count <= retries: - self.report_retry(count, retries) - - if count > retries: - self.trouble(u'ERROR: giving up after %s retries' % retries) - return False - - data_len = data.info().get('Content-length', None) - if data_len is not None: - data_len = long(data_len) + resume_len - data_len_str = self.format_bytes(data_len) - byte_counter = 0 + resume_len - block_size = 1024 - start = time.time() - while True: - # Download and write - before = time.time() - data_block = data.read(block_size) - after = time.time() - if len(data_block) == 0: - break - byte_counter += len(data_block) - - # Open file just in time - if stream is None: - try: - (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) - assert stream is not None - filename = self.undo_temp_name(tmpfilename) - self.report_destination(filename) - except (OSError, IOError), err: - self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) - return False - try: - stream.write(data_block) - except (IOError, OSError), err: - self.trouble(u'\nERROR: unable to write data: %s' % str(err)) - return False - block_size = self.best_block_size(after - before, len(data_block)) - - # Progress message - speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len) - if data_len is None: - self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA') - else: - percent_str = self.calc_percent(byte_counter, data_len) - eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len) - self.report_progress(percent_str, data_len_str, speed_str, eta_str) - - # Apply rate limit - self.slow_down(start, byte_counter - resume_len) - - if stream is None: - self.trouble(u'\nERROR: Did not get any data blocks') - return False - stream.close() - self.report_finish() - if data_len is not None and byte_counter != data_len: - raise ContentTooShortError(byte_counter, long(data_len)) - self.try_rename(tmpfilename, filename) - - # Update file modification time - if self.params.get('updatetime', True): - info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None)) - - return True + """File Downloader class. + + File downloader objects are the ones responsible of downloading the + actual video file and writing it to disk if the user has requested + it, among some other tasks. In most cases there should be one per + program. As, given a video URL, the downloader doesn't know how to + extract all the needed information, task that InfoExtractors do, it + has to pass the URL to one of them. + + For this, file downloader objects have a method that allows + InfoExtractors to be registered in a given order. When it is passed + a URL, the file downloader handles it to the first InfoExtractor it + finds that reports being able to handle it. The InfoExtractor extracts + all the information about the video or videos the URL refers to, and + asks the FileDownloader to process the video information, possibly + downloading the video. + + File downloaders accept a lot of parameters. In order not to saturate + the object constructor with arguments, it receives a dictionary of + options instead. These options are available through the params + attribute for the InfoExtractors to use. The FileDownloader also + registers itself as the downloader in charge for the InfoExtractors + that are added to it, so this is a "mutual registration". + + Available options: + + username: Username for authentication purposes. + password: Password for authentication purposes. + usenetrc: Use netrc for authentication instead. + quiet: Do not print messages to stdout. + forceurl: Force printing final URL. + forcetitle: Force printing title. + forcethumbnail: Force printing thumbnail URL. + forcedescription: Force printing description. + forcefilename: Force printing final filename. + simulate: Do not download the video files. + format: Video format code. + format_limit: Highest quality format to try. + outtmpl: Template for output names. + restrictfilenames: Do not allow "&" and spaces in file names + ignoreerrors: Do not stop on download errors. + ratelimit: Download speed limit, in bytes/sec. + nooverwrites: Prevent overwriting files. + retries: Number of times to retry for HTTP error 5xx + buffersize: Size of download buffer in bytes. + noresizebuffer: Do not automatically resize the download buffer. + continuedl: Try to continue downloads if possible. + noprogress: Do not print the progress bar. + playliststart: Playlist item to start at. + playlistend: Playlist item to end at. + matchtitle: Download only matching titles. + rejecttitle: Reject downloads for matching titles. + logtostderr: Log messages to stderr instead of stdout. + consoletitle: Display progress in console window's titlebar. + nopart: Do not use temporary .part files. + updatetime: Use the Last-modified header to set output file timestamps. + writedescription: Write the video description to a .description file + writeinfojson: Write the video description to a .info.json file + writesubtitles: Write the video subtitles to a .srt file + subtitleslang: Language of the subtitles to download + test: Download only first bytes to test the downloader. + """ + + params = None + _ies = [] + _pps = [] + _download_retcode = None + _num_downloads = None + _screen_file = None + + def __init__(self, params): + """Create a FileDownloader object with the given options.""" + self._ies = [] + self._pps = [] + self._download_retcode = 0 + self._num_downloads = 0 + self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] + self.params = params + + if '%(stitle)s' in self.params['outtmpl']: + self.to_stderr(u'WARNING: %(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.') + + @staticmethod + def format_bytes(bytes): + if bytes is None: + return 'N/A' + if type(bytes) is str: + bytes = float(bytes) + if bytes == 0.0: + exponent = 0 + else: + exponent = int(math.log(bytes, 1024.0)) + suffix = 'bkMGTPEZY'[exponent] + converted = float(bytes) / float(1024 ** exponent) + return '%.2f%s' % (converted, suffix) + + @staticmethod + def calc_percent(byte_counter, data_len): + if data_len is None: + return '---.-%' + return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0)) + + @staticmethod + def calc_eta(start, now, total, current): + if total is None: + return '--:--' + dif = now - start + if current == 0 or dif < 0.001: # One millisecond + return '--:--' + rate = float(current) / dif + eta = int((float(total) - float(current)) / rate) + (eta_mins, eta_secs) = divmod(eta, 60) + if eta_mins > 99: + return '--:--' + return '%02d:%02d' % (eta_mins, eta_secs) + + @staticmethod + def calc_speed(start, now, bytes): + dif = now - start + if bytes == 0 or dif < 0.001: # One millisecond + return '%10s' % '---b/s' + return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif)) + + @staticmethod + def best_block_size(elapsed_time, bytes): + new_min = max(bytes / 2.0, 1.0) + new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB + if elapsed_time < 0.001: + return int(new_max) + rate = bytes / elapsed_time + if rate > new_max: + return int(new_max) + if rate < new_min: + return int(new_min) + return int(rate) + + @staticmethod + def parse_bytes(bytestr): + """Parse a string indicating a byte quantity into an integer.""" + matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) + if matchobj is None: + return None + number = float(matchobj.group(1)) + multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) + return int(round(number * multiplier)) + + def add_info_extractor(self, ie): + """Add an InfoExtractor object to the end of the list.""" + self._ies.append(ie) + ie.set_downloader(self) + + def add_post_processor(self, pp): + """Add a PostProcessor object to the end of the chain.""" + self._pps.append(pp) + pp.set_downloader(self) + + def to_screen(self, message, skip_eol=False): + """Print message to stdout if not in quiet mode.""" + assert type(message) == type(u'') + if not self.params.get('quiet', False): + terminator = [u'\n', u''][skip_eol] + output = message + terminator + if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr + output = output.encode(preferredencoding(), 'ignore') + self._screen_file.write(output) + self._screen_file.flush() + + def to_stderr(self, message): + """Print message to stderr.""" + assert type(message) == type(u'') + output = message + u'\n' + if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr + output = output.encode(preferredencoding()) + sys.stderr.write(output) + + def to_cons_title(self, message): + """Set console/terminal window title to message.""" + if not self.params.get('consoletitle', False): + return + if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): + # c_wchar_p() might not be necessary if `message` is + # already of type unicode() + ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) + elif 'TERM' in os.environ: + sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding())) + + def fixed_template(self): + """Checks if the output template is fixed.""" + return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None) + + def trouble(self, message=None, tb=None): + """Determine action to take when a download problem appears. + + Depending on if the downloader has been configured to ignore + download errors or not, this method may throw an exception or + not when errors are found, after printing the message. + + tb, if given, is additional traceback information. + """ + if message is not None: + self.to_stderr(message) + if self.params.get('verbose'): + if tb is None: + tb_data = traceback.format_list(traceback.extract_stack()) + tb = u''.join(tb_data) + self.to_stderr(tb) + if not self.params.get('ignoreerrors', False): + raise DownloadError(message) + self._download_retcode = 1 + + def slow_down(self, start_time, byte_counter): + """Sleep if the download speed is over the rate limit.""" + rate_limit = self.params.get('ratelimit', None) + if rate_limit is None or byte_counter == 0: + return + now = time.time() + elapsed = now - start_time + if elapsed <= 0.0: + return + speed = float(byte_counter) / elapsed + if speed > rate_limit: + time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) + + def temp_name(self, filename): + """Returns a temporary filename for the given filename.""" + if self.params.get('nopart', False) or filename == u'-' or \ + (os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))): + return filename + return filename + u'.part' + + def undo_temp_name(self, filename): + if filename.endswith(u'.part'): + return filename[:-len(u'.part')] + return filename + + def try_rename(self, old_filename, new_filename): + try: + if old_filename == new_filename: + return + os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) + except (IOError, OSError) as err: + self.trouble(u'ERROR: unable to rename file') + + def try_utime(self, filename, last_modified_hdr): + """Try to set the last-modified time of the given file.""" + if last_modified_hdr is None: + return + if not os.path.isfile(encodeFilename(filename)): + return + timestr = last_modified_hdr + if timestr is None: + return + filetime = timeconvert(timestr) + if filetime is None: + return filetime + try: + os.utime(filename, (time.time(), filetime)) + except: + pass + return filetime + + def report_writedescription(self, descfn): + """ Report that the description file is being written """ + self.to_screen(u'[info] Writing video description to: ' + descfn) + + def report_writesubtitles(self, srtfn): + """ Report that the subtitles file is being written """ + self.to_screen(u'[info] Writing video subtitles to: ' + srtfn) + + def report_writeinfojson(self, infofn): + """ Report that the metadata file has been written """ + self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn) + + def report_destination(self, filename): + """Report destination filename.""" + self.to_screen(u'[download] Destination: ' + filename) + + def report_progress(self, percent_str, data_len_str, speed_str, eta_str): + """Report download progress.""" + if self.params.get('noprogress', False): + return + self.to_screen(u'\r[download] %s of %s at %s ETA %s' % + (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) + self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' % + (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip())) + + def report_resuming_byte(self, resume_len): + """Report attempt to resume at given byte.""" + self.to_screen(u'[download] Resuming download at byte %s' % resume_len) + + def report_retry(self, count, retries): + """Report retry in case of HTTP error 5xx""" + self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) + + def report_file_already_downloaded(self, file_name): + """Report file has already been fully downloaded.""" + try: + self.to_screen(u'[download] %s has already been downloaded' % file_name) + except (UnicodeEncodeError) as err: + self.to_screen(u'[download] The file has already been downloaded') + + def report_unable_to_resume(self): + """Report it was impossible to resume download.""" + self.to_screen(u'[download] Unable to resume') + + def report_finish(self): + """Report download finished.""" + if self.params.get('noprogress', False): + self.to_screen(u'[download] Download completed') + else: + self.to_screen(u'') + + def increment_downloads(self): + """Increment the ordinal that assigns a number to each file.""" + self._num_downloads += 1 + + def prepare_filename(self, info_dict): + """Generate the output filename.""" + try: + template_dict = dict(info_dict) + + template_dict['epoch'] = int(time.time()) + template_dict['autonumber'] = u'%05d' % self._num_downloads + + sanitize = lambda k,v: sanitize_filename( + u'NA' if v is None else compat_str(v), + restricted=self.params.get('restrictfilenames'), + is_id=(k==u'id')) + template_dict = dict((k, sanitize(k, v)) for k,v in template_dict.items()) + + filename = self.params['outtmpl'] % template_dict + return filename + except (ValueError, KeyError) as err: + self.trouble(u'ERROR: invalid system charset or erroneous output template') + return None + + def _match_entry(self, info_dict): + """ Returns None iff the file should be downloaded """ + + title = info_dict['title'] + matchtitle = self.params.get('matchtitle', False) + if matchtitle: + matchtitle = matchtitle.decode('utf8') + if not re.search(matchtitle, title, re.IGNORECASE): + return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"' + rejecttitle = self.params.get('rejecttitle', False) + if rejecttitle: + rejecttitle = rejecttitle.decode('utf8') + if re.search(rejecttitle, title, re.IGNORECASE): + return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"' + return None + + def process_info(self, info_dict): + """Process a single dictionary returned by an InfoExtractor.""" + + # Keep for backwards compatibility + info_dict['stitle'] = info_dict['title'] + + if not 'format' in info_dict: + info_dict['format'] = info_dict['ext'] + + reason = self._match_entry(info_dict) + if reason is not None: + self.to_screen(u'[download] ' + reason) + return + + max_downloads = self.params.get('max_downloads') + if max_downloads is not None: + if self._num_downloads > int(max_downloads): + raise MaxDownloadsReached() + + filename = self.prepare_filename(info_dict) + + # Forced printings + if self.params.get('forcetitle', False): + compat_print(info_dict['title']) + if self.params.get('forceurl', False): + compat_print(info_dict['url']) + if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: + compat_print(info_dict['thumbnail']) + if self.params.get('forcedescription', False) and 'description' in info_dict: + compat_print(info_dict['description']) + if self.params.get('forcefilename', False) and filename is not None: + compat_print(filename) + if self.params.get('forceformat', False): + compat_print(info_dict['format']) + + # Do nothing else if in simulate mode + if self.params.get('simulate', False): + return + + if filename is None: + return + + try: + dn = os.path.dirname(encodeFilename(filename)) + if dn != '' and not os.path.exists(dn): # dn is already encoded + os.makedirs(dn) + except (OSError, IOError) as err: + self.trouble(u'ERROR: unable to create directory ' + compat_str(err)) + return + + if self.params.get('writedescription', False): + try: + descfn = filename + u'.description' + self.report_writedescription(descfn) + with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile: + descfile.write(info_dict['description']) + except (OSError, IOError): + self.trouble(u'ERROR: Cannot write description file ' + descfn) + return + + if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']: + # subtitles download errors are already managed as troubles in relevant IE + # that way it will silently go on when used with unsupporting IE + try: + srtfn = filename.rsplit('.', 1)[0] + u'.srt' + self.report_writesubtitles(srtfn) + with io.open(encodeFilename(srtfn), 'w', encoding='utf-8') as srtfile: + srtfile.write(info_dict['subtitles']) + except (OSError, IOError): + self.trouble(u'ERROR: Cannot write subtitles file ' + descfn) + return + + if self.params.get('writeinfojson', False): + infofn = filename + u'.info.json' + self.report_writeinfojson(infofn) + try: + json_info_dict = dict((k, v) for k,v in info_dict.items() if not k in ['urlhandle']) + write_json_file(json_info_dict, encodeFilename(infofn)) + except (OSError, IOError): + self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn) + return + + if not self.params.get('skip_download', False): + if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)): + success = True + else: + try: + success = self._do_download(filename, info_dict) + except (OSError, IOError) as err: + raise UnavailableVideoError() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self.trouble(u'ERROR: unable to download video data: %s' % str(err)) + return + except (ContentTooShortError, ) as err: + self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) + return + + if success: + try: + self.post_process(filename, info_dict) + except (PostProcessingError) as err: + self.trouble(u'ERROR: postprocessing: %s' % str(err)) + return + + def download(self, url_list): + """Download a given list of URLs.""" + if len(url_list) > 1 and self.fixed_template(): + raise SameFileError(self.params['outtmpl']) + + for url in url_list: + suitable_found = False + for ie in self._ies: + # Go to next InfoExtractor if not suitable + if not ie.suitable(url): + continue + + # Warn if the _WORKING attribute is False + if not ie.working(): + self.to_stderr(u'WARNING: the program functionality for this site has been marked as broken, ' + u'and will probably not work. If you want to go on, use the -i option.') + + # Suitable InfoExtractor found + suitable_found = True + + # Extract information from URL and process it + try: + videos = ie.extract(url) + except ExtractorError as de: # An error we somewhat expected + self.trouble(u'ERROR: ' + compat_str(de), de.format_traceback()) + break + except Exception as e: + if self.params.get('ignoreerrors', False): + self.trouble(u'ERROR: ' + compat_str(e), tb=compat_str(traceback.format_exc())) + break + else: + raise + + if len(videos or []) > 1 and self.fixed_template(): + raise SameFileError(self.params['outtmpl']) + + for video in videos or []: + video['extractor'] = ie.IE_NAME + try: + self.increment_downloads() + self.process_info(video) + except UnavailableVideoError: + self.trouble(u'\nERROR: unable to download video') + + # Suitable InfoExtractor had been found; go to next URL + break + + if not suitable_found: + self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url) + + return self._download_retcode + + def post_process(self, filename, ie_info): + """Run the postprocessing chain on the given file.""" + info = dict(ie_info) + info['filepath'] = filename + for pp in self._pps: + info = pp.run(info) + if info is None: + break + + def _download_with_rtmpdump(self, filename, url, player_url, page_url): + self.report_destination(filename) + tmpfilename = self.temp_name(filename) + + # Check for rtmpdump first + try: + subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT) + except (OSError, IOError): + self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run') + return False + + # Download using rtmpdump. rtmpdump returns exit code 2 when + # the connection was interrumpted and resuming appears to be + # possible. This is part of rtmpdump's normal usage, AFAIK. + basic_args = ['rtmpdump', '-q', '-r', url, '-o', tmpfilename] + if player_url is not None: + basic_args += ['-W', player_url] + if page_url is not None: + basic_args += ['--pageUrl', page_url] + args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)] + if self.params.get('verbose', False): + try: + import pipes + shell_quote = lambda args: ' '.join(map(pipes.quote, args)) + except ImportError: + shell_quote = repr + self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(args)) + retval = subprocess.call(args) + while retval == 2 or retval == 1: + prevsize = os.path.getsize(encodeFilename(tmpfilename)) + self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True) + time.sleep(5.0) # This seems to be needed + retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1]) + cursize = os.path.getsize(encodeFilename(tmpfilename)) + if prevsize == cursize and retval == 1: + break + # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those + if prevsize == cursize and retval == 2 and cursize > 1024: + self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.') + retval = 0 + break + if retval == 0: + self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(encodeFilename(tmpfilename))) + self.try_rename(tmpfilename, filename) + return True + else: + self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) + return False + + def _do_download(self, filename, info_dict): + url = info_dict['url'] + + # Check file already present + if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False): + self.report_file_already_downloaded(filename) + return True + + # Attempt to download using rtmpdump + if url.startswith('rtmp'): + return self._download_with_rtmpdump(filename, url, + info_dict.get('player_url', None), + info_dict.get('page_url', None)) + + tmpfilename = self.temp_name(filename) + stream = None + + # Do not include the Accept-Encoding header + headers = {'Youtubedl-no-compression': 'True'} + basic_request = compat_urllib_request.Request(url, None, headers) + request = compat_urllib_request.Request(url, None, headers) + + if self.params.get('test', False): + request.add_header('Range','bytes=0-10240') + + # Establish possible resume length + if os.path.isfile(encodeFilename(tmpfilename)): + resume_len = os.path.getsize(encodeFilename(tmpfilename)) + else: + resume_len = 0 + + open_mode = 'wb' + if resume_len != 0: + if self.params.get('continuedl', False): + self.report_resuming_byte(resume_len) + request.add_header('Range','bytes=%d-' % resume_len) + open_mode = 'ab' + else: + resume_len = 0 + + count = 0 + retries = self.params.get('retries', 0) + while count <= retries: + # Establish connection + try: + if count == 0 and 'urlhandle' in info_dict: + data = info_dict['urlhandle'] + data = compat_urllib_request.urlopen(request) + break + except (compat_urllib_error.HTTPError, ) as err: + if (err.code < 500 or err.code >= 600) and err.code != 416: + # Unexpected HTTP error + raise + elif err.code == 416: + # Unable to resume (requested range not satisfiable) + try: + # Open the connection again without the range header + data = compat_urllib_request.urlopen(basic_request) + content_length = data.info()['Content-Length'] + except (compat_urllib_error.HTTPError, ) as err: + if err.code < 500 or err.code >= 600: + raise + else: + # Examine the reported length + if (content_length is not None and + (resume_len - 100 < int(content_length) < resume_len + 100)): + # The file had already been fully downloaded. + # Explanation to the above condition: in issue #175 it was revealed that + # YouTube sometimes adds or removes a few bytes from the end of the file, + # changing the file size slightly and causing problems for some users. So + # I decided to implement a suggested change and consider the file + # completely downloaded if the file size differs less than 100 bytes from + # the one in the hard drive. + self.report_file_already_downloaded(filename) + self.try_rename(tmpfilename, filename) + return True + else: + # The length does not match, we start the download over + self.report_unable_to_resume() + open_mode = 'wb' + break + # Retry + count += 1 + if count <= retries: + self.report_retry(count, retries) + + if count > retries: + self.trouble(u'ERROR: giving up after %s retries' % retries) + return False + + data_len = data.info().get('Content-length', None) + if data_len is not None: + data_len = int(data_len) + resume_len + data_len_str = self.format_bytes(data_len) + byte_counter = 0 + resume_len + block_size = self.params.get('buffersize', 1024) + start = time.time() + while True: + # Download and write + before = time.time() + data_block = data.read(block_size) + after = time.time() + if len(data_block) == 0: + break + byte_counter += len(data_block) + + # Open file just in time + if stream is None: + try: + (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) + assert stream is not None + filename = self.undo_temp_name(tmpfilename) + self.report_destination(filename) + except (OSError, IOError) as err: + self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) + return False + try: + stream.write(data_block) + except (IOError, OSError) as err: + self.trouble(u'\nERROR: unable to write data: %s' % str(err)) + return False + if not self.params.get('noresizebuffer', False): + block_size = self.best_block_size(after - before, len(data_block)) + + # Progress message + speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len) + if data_len is None: + self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA') + else: + percent_str = self.calc_percent(byte_counter, data_len) + eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len) + self.report_progress(percent_str, data_len_str, speed_str, eta_str) + + # Apply rate limit + self.slow_down(start, byte_counter - resume_len) + + if stream is None: + self.trouble(u'\nERROR: Did not get any data blocks') + return False + stream.close() + self.report_finish() + if data_len is not None and byte_counter != data_len: + raise ContentTooShortError(byte_counter, int(data_len)) + self.try_rename(tmpfilename, filename) + + # Update file modification time + if self.params.get('updatetime', True): + info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None)) + + return True diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index d30de6943..e380f62a1 100644..100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -1,3696 +1,3782 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- +from __future__ import absolute_import + +import base64 import datetime -import HTMLParser -import httplib import netrc import os import re import socket import time -import urllib -import urllib2 import email.utils import xml.etree.ElementTree import random import math -from urlparse import parse_qs, urlparse - -try: - import cStringIO as StringIO -except ImportError: - import StringIO -from utils import * +from .utils import * class InfoExtractor(object): - """Information Extractor class. - - Information extractors are the classes that, given a URL, extract - information from the video (or videos) the URL refers to. This - information includes the real video URL, the video title and simplified - title, author and others. The information is stored in a dictionary - which is then passed to the FileDownloader. The FileDownloader - processes this information possibly downloading the video to the file - system, among other possible outcomes. The dictionaries must include - the following fields: - - id: Video identifier. - url: Final video URL. - uploader: Nickname of the video uploader. - title: Literal title. - ext: Video filename extension. - format: Video format. - player_url: SWF Player URL (may be None). - - The following fields are optional. Their primary purpose is to allow - youtube-dl to serve as the backend for a video search function, such - as the one in youtube2mp3. They are only used when their respective - forced printing functions are called: - - thumbnail: Full URL to a video thumbnail image. - description: One-line video description. - - Subclasses of this one should re-define the _real_initialize() and - _real_extract() methods and define a _VALID_URL regexp. - Probably, they should also be added to the list of extractors. - """ - - _ready = False - _downloader = None - - def __init__(self, downloader=None): - """Constructor. Receives an optional downloader.""" - self._ready = False - self.set_downloader(downloader) - - def suitable(self, url): - """Receives a URL and returns True if suitable for this IE.""" - return re.match(self._VALID_URL, url) is not None - - def initialize(self): - """Initializes an instance (authentication, etc).""" - if not self._ready: - self._real_initialize() - self._ready = True - - def extract(self, url): - """Extracts URL information and returns it in list of dicts.""" - self.initialize() - return self._real_extract(url) - - def set_downloader(self, downloader): - """Sets the downloader for this IE.""" - self._downloader = downloader - - def _real_initialize(self): - """Real initialization process. Redefine in subclasses.""" - pass - - def _real_extract(self, url): - """Real extraction process. Redefine in subclasses.""" - pass - - + """Information Extractor class. + + Information extractors are the classes that, given a URL, extract + information about the video (or videos) the URL refers to. This + information includes the real video URL, the video title, author and + others. The information is stored in a dictionary which is then + passed to the FileDownloader. The FileDownloader processes this + information possibly downloading the video to the file system, among + other possible outcomes. + + The dictionaries must include the following fields: + + id: Video identifier. + url: Final video URL. + title: Video title, unescaped. + ext: Video filename extension. + uploader: Full name of the video uploader. + upload_date: Video upload date (YYYYMMDD). + + The following fields are optional: + + format: The video format, defaults to ext (used for --get-format) + thumbnail: Full URL to a video thumbnail image. + description: One-line video description. + uploader_id: Nickname or id of the video uploader. + player_url: SWF Player URL (used for rtmpdump). + subtitles: The .srt file contents. + urlhandle: [internal] The urlHandle to be used to download the file, + like returned by urllib.request.urlopen + + The fields should all be Unicode strings. + + Subclasses of this one should re-define the _real_initialize() and + _real_extract() methods and define a _VALID_URL regexp. + Probably, they should also be added to the list of extractors. + + _real_extract() must return a *list* of information dictionaries as + described above. + + Finally, the _WORKING attribute should be set to False for broken IEs + in order to warn the users and skip the tests. + """ + + _ready = False + _downloader = None + _WORKING = True + + def __init__(self, downloader=None): + """Constructor. Receives an optional downloader.""" + self._ready = False + self.set_downloader(downloader) + + def suitable(self, url): + """Receives a URL and returns True if suitable for this IE.""" + return re.match(self._VALID_URL, url) is not None + + def working(self): + """Getter method for _WORKING.""" + return self._WORKING + + def initialize(self): + """Initializes an instance (authentication, etc).""" + if not self._ready: + self._real_initialize() + self._ready = True + + def extract(self, url): + """Extracts URL information and returns it in list of dicts.""" + self.initialize() + return self._real_extract(url) + + def set_downloader(self, downloader): + """Sets the downloader for this IE.""" + self._downloader = downloader + + def _real_initialize(self): + """Real initialization process. Redefine in subclasses.""" + pass + + def _real_extract(self, url): + """Real extraction process. Redefine in subclasses.""" + pass + + @property + def IE_NAME(self): + return type(self).__name__[:-2] + + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None): + if note is None: + note = u'Downloading video webpage' + self._downloader.to_screen(u'[%s] %s: %s' % (self.IE_NAME, video_id, note)) + try: + urlh = compat_urllib_request.urlopen(url_or_request) + webpage_bytes = urlh.read() + return webpage_bytes.decode('utf-8', 'replace') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + if errnote is None: + errnote = u'Unable to download webpage' + raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2]) class YoutubeIE(InfoExtractor): - """Information extractor for youtube.com.""" - - _VALID_URL = r"""^ - ( - (?:https?://)? # http(s):// (optional) - (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/| - tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains - (?:.*?\#/)? # handle anchor (#/) redirect urls - (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs - (?: # the various things that can precede the ID: - (?:(?:v|embed|e)/) # v/ or embed/ or e/ - |(?: # or the v= param in all its forms - (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) - (?:\?|\#!?) # the params delimiter ? or # or #! - (?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx) - v= - ) - )? # optional -> youtube.com/xxxx is OK - )? # all until now is optional -> you can pass the naked ID - ([0-9A-Za-z_-]+) # here is it! the YouTube video ID - (?(1).+)? # if we found the ID, everything can follow - $""" - _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' - _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' - _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' - _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' - _NETRC_MACHINE = 'youtube' - # Listed in order of quality - _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13'] - _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13'] - _video_extensions = { - '13': '3gp', - '17': 'mp4', - '18': 'mp4', - '22': 'mp4', - '37': 'mp4', - '38': 'video', # You actually don't know if this will be MOV, AVI or whatever - '43': 'webm', - '44': 'webm', - '45': 'webm', - '46': 'webm', - } - _video_dimensions = { - '5': '240x400', - '6': '???', - '13': '???', - '17': '144x176', - '18': '360x640', - '22': '720x1280', - '34': '360x640', - '35': '480x854', - '37': '1080x1920', - '38': '3072x4096', - '43': '360x640', - '44': '480x854', - '45': '720x1280', - '46': '1080x1920', - } - IE_NAME = u'youtube' - - def suitable(self, url): - """Receives a URL and returns True if suitable for this IE.""" - return re.match(self._VALID_URL, url, re.VERBOSE) is not None - - def report_lang(self): - """Report attempt to set language.""" - self._downloader.to_screen(u'[youtube] Setting language') - - def report_login(self): - """Report attempt to log in.""" - self._downloader.to_screen(u'[youtube] Logging in') - - def report_age_confirmation(self): - """Report attempt to confirm age.""" - self._downloader.to_screen(u'[youtube] Confirming age') - - def report_video_webpage_download(self, video_id): - """Report attempt to download video webpage.""" - self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id) - - def report_video_info_webpage_download(self, video_id): - """Report attempt to download video info webpage.""" - self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) - - def report_video_subtitles_download(self, video_id): - """Report attempt to download video info webpage.""" - self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id) - - def report_information_extraction(self, video_id): - """Report attempt to extract video information.""" - self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) - - def report_unavailable_format(self, video_id, format): - """Report extracted video URL.""" - self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) - - def report_rtmp_download(self): - """Indicate the download will use the RTMP protocol.""" - self._downloader.to_screen(u'[youtube] RTMP download detected') - - def _closed_captions_xml_to_srt(self, xml_string): - srt = '' - texts = re.findall(r'<text start="([\d\.]+)"( dur="([\d\.]+)")?>([^<]+)</text>', xml_string, re.MULTILINE) - # TODO parse xml instead of regex - for n, (start, dur_tag, dur, caption) in enumerate(texts): - if not dur: dur = '4' - start = float(start) - end = start + float(dur) - start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000) - end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000) - caption = unescapeHTML(caption) - caption = unescapeHTML(caption) # double cycle, intentional - srt += str(n+1) + '\n' - srt += start + ' --> ' + end + '\n' - srt += caption + '\n\n' - return srt - - def _print_formats(self, formats): - print 'Available formats:' - for x in formats: - print '%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???')) - - def _real_initialize(self): - if self._downloader is None: - return - - username = None - password = None - downloader_params = self._downloader.params - - # Attempt to use provided username and password or .netrc data - if downloader_params.get('username', None) is not None: - username = downloader_params['username'] - password = downloader_params['password'] - elif downloader_params.get('usenetrc', False): - try: - info = netrc.netrc().authenticators(self._NETRC_MACHINE) - if info is not None: - username = info[0] - password = info[2] - else: - raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) - except (IOError, netrc.NetrcParseError), err: - self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) - return - - # Set language - request = urllib2.Request(self._LANG_URL) - try: - self.report_lang() - urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err)) - return - - # No authentication to be performed - if username is None: - return - - # Log in - login_form = { - 'current_form': 'loginForm', - 'next': '/', - 'action_login': 'Log In', - 'username': username, - 'password': password, - } - request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form)) - try: - self.report_login() - login_results = urllib2.urlopen(request).read() - if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None: - self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password') - return - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) - return - - # Confirm age - age_form = { - 'next_url': '/', - 'action_confirm': 'Confirm', - } - request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form)) - try: - self.report_age_confirmation() - age_results = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) - return - - def _real_extract(self, url): - # Extract original video URL from URL with redirection, like age verification, using next_url parameter - mobj = re.search(self._NEXT_URL_RE, url) - if mobj: - url = 'http://www.youtube.com/' + urllib.unquote(mobj.group(1)).lstrip('/') - - # Extract video id from URL - mobj = re.match(self._VALID_URL, url, re.VERBOSE) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - video_id = mobj.group(2) - - # Get video webpage - self.report_video_webpage_download(video_id) - request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id) - try: - video_webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) - return - - # Attempt to extract SWF player URL - mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) - if mobj is not None: - player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) - else: - player_url = None - - # Get video info - self.report_video_info_webpage_download(video_id) - for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: - video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' - % (video_id, el_type)) - request = urllib2.Request(video_info_url) - try: - video_info_webpage = urllib2.urlopen(request).read() - video_info = parse_qs(video_info_webpage) - if 'token' in video_info: - break - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) - return - if 'token' not in video_info: - if 'reason' in video_info: - self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8')) - else: - self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason') - return - - # Check for "rental" videos - if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: - self._downloader.trouble(u'ERROR: "rental" videos not supported') - return - - # Start extracting information - self.report_information_extraction(video_id) - - # uploader - if 'author' not in video_info: - self._downloader.trouble(u'ERROR: unable to extract uploader nickname') - return - video_uploader = urllib.unquote_plus(video_info['author'][0]) - - # title - if 'title' not in video_info: - self._downloader.trouble(u'ERROR: unable to extract video title') - return - video_title = urllib.unquote_plus(video_info['title'][0]) - video_title = video_title.decode('utf-8') - - # thumbnail image - if 'thumbnail_url' not in video_info: - self._downloader.trouble(u'WARNING: unable to extract video thumbnail') - video_thumbnail = '' - else: # don't panic if we can't find it - video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0]) - - # upload date - upload_date = u'NA' - mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL) - if mobj is not None: - upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) - format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y'] - for expression in format_expressions: - try: - upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d') - except: - pass - - # description - video_description = get_element_by_id("eow-description", video_webpage.decode('utf8')) - if video_description: video_description = clean_html(video_description) - else: video_description = '' - - # closed captions - video_subtitles = None - if self._downloader.params.get('writesubtitles', False): - try: - self.report_video_subtitles_download(video_id) - request = urllib2.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) - try: - srt_list = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err)) - srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list) - srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list) - if not srt_lang_list: - raise Trouble(u'WARNING: video has no closed captions') - if self._downloader.params.get('subtitleslang', False): - srt_lang = self._downloader.params.get('subtitleslang') - elif 'en' in srt_lang_list: - srt_lang = 'en' - else: - srt_lang = srt_lang_list.keys()[0] - if not srt_lang in srt_lang_list: - raise Trouble(u'WARNING: no closed captions found in the specified language') - request = urllib2.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id)) - try: - srt_xml = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err)) - if not srt_xml: - raise Trouble(u'WARNING: unable to download video subtitles') - video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8')) - except Trouble as trouble: - self._downloader.trouble(trouble[0]) - - if 'length_seconds' not in video_info: - self._downloader.trouble(u'WARNING: unable to extract video duration') - video_duration = '' - else: - video_duration = urllib.unquote_plus(video_info['length_seconds'][0]) - - # token - video_token = urllib.unquote_plus(video_info['token'][0]) - - # Decide which formats to download - req_format = self._downloader.params.get('format', None) - - if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): - self.report_rtmp_download() - video_url_list = [(None, video_info['conn'][0])] - elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1: - url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',') - url_data = [parse_qs(uds) for uds in url_data_strs] - url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data) - url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data) - - format_limit = self._downloader.params.get('format_limit', None) - available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats - if format_limit is not None and format_limit in available_formats: - format_list = available_formats[available_formats.index(format_limit):] - else: - format_list = available_formats - existing_formats = [x for x in format_list if x in url_map] - if len(existing_formats) == 0: - self._downloader.trouble(u'ERROR: no known formats available for video') - return - if self._downloader.params.get('listformats', None): - self._print_formats(existing_formats) - return - if req_format is None or req_format == 'best': - video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality - elif req_format == 'worst': - video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality - elif req_format in ('-1', 'all'): - video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats - else: - # Specific formats. We pick the first in a slash-delimeted sequence. - # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'. - req_formats = req_format.split('/') - video_url_list = None - for rf in req_formats: - if rf in url_map: - video_url_list = [(rf, url_map[rf])] - break - if video_url_list is None: - self._downloader.trouble(u'ERROR: requested format not available') - return - else: - self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info') - return - - results = [] - for format_param, video_real_url in video_url_list: - # Extension - video_extension = self._video_extensions.get(format_param, 'flv') - - results.append({ - 'id': video_id.decode('utf-8'), - 'url': video_real_url.decode('utf-8'), - 'uploader': video_uploader.decode('utf-8'), - 'upload_date': upload_date, - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), - 'thumbnail': video_thumbnail.decode('utf-8'), - 'description': video_description, - 'player_url': player_url, - 'subtitles': video_subtitles, - 'duration': video_duration - }) - return results + """Information extractor for youtube.com.""" + + _VALID_URL = r"""^ + ( + (?:https?://)? # http(s):// (optional) + (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/| + tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains + (?:.*?\#/)? # handle anchor (#/) redirect urls + (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs + (?: # the various things that can precede the ID: + (?:(?:v|embed|e)/) # v/ or embed/ or e/ + |(?: # or the v= param in all its forms + (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) + (?:\?|\#!?) # the params delimiter ? or # or #! + (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx) + v= + ) + )? # optional -> youtube.com/xxxx is OK + )? # all until now is optional -> you can pass the naked ID + ([0-9A-Za-z_-]+) # here is it! the YouTube video ID + (?(1).+)? # if we found the ID, everything can follow + $""" + _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' + _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' + _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' + _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' + _NETRC_MACHINE = 'youtube' + # Listed in order of quality + _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13'] + _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13'] + _video_extensions = { + '13': '3gp', + '17': 'mp4', + '18': 'mp4', + '22': 'mp4', + '37': 'mp4', + '38': 'video', # You actually don't know if this will be MOV, AVI or whatever + '43': 'webm', + '44': 'webm', + '45': 'webm', + '46': 'webm', + } + _video_dimensions = { + '5': '240x400', + '6': '???', + '13': '???', + '17': '144x176', + '18': '360x640', + '22': '720x1280', + '34': '360x640', + '35': '480x854', + '37': '1080x1920', + '38': '3072x4096', + '43': '360x640', + '44': '480x854', + '45': '720x1280', + '46': '1080x1920', + } + IE_NAME = u'youtube' + + def suitable(self, url): + """Receives a URL and returns True if suitable for this IE.""" + return re.match(self._VALID_URL, url, re.VERBOSE) is not None + + def report_lang(self): + """Report attempt to set language.""" + self._downloader.to_screen(u'[youtube] Setting language') + + def report_login(self): + """Report attempt to log in.""" + self._downloader.to_screen(u'[youtube] Logging in') + + def report_age_confirmation(self): + """Report attempt to confirm age.""" + self._downloader.to_screen(u'[youtube] Confirming age') + + def report_video_webpage_download(self, video_id): + """Report attempt to download video webpage.""" + self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id) + + def report_video_info_webpage_download(self, video_id): + """Report attempt to download video info webpage.""" + self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) + + def report_video_subtitles_download(self, video_id): + """Report attempt to download video info webpage.""" + self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id) + + def report_information_extraction(self, video_id): + """Report attempt to extract video information.""" + self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) + + def report_unavailable_format(self, video_id, format): + """Report extracted video URL.""" + self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) + + def report_rtmp_download(self): + """Indicate the download will use the RTMP protocol.""" + self._downloader.to_screen(u'[youtube] RTMP download detected') + + def _closed_captions_xml_to_srt(self, xml_string): + srt = '' + texts = re.findall(r'<text start="([\d\.]+)"( dur="([\d\.]+)")?>([^<]+)</text>', xml_string, re.MULTILINE) + # TODO parse xml instead of regex + for n, (start, dur_tag, dur, caption) in enumerate(texts): + if not dur: dur = '4' + start = float(start) + end = start + float(dur) + start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000) + end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000) + caption = unescapeHTML(caption) + caption = unescapeHTML(caption) # double cycle, intentional + srt += str(n+1) + '\n' + srt += start + ' --> ' + end + '\n' + srt += caption + '\n\n' + return srt + + def _extract_subtitles(self, video_id): + self.report_video_subtitles_download(video_id) + request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) + try: + srt_list = compat_urllib_request.urlopen(request).read().decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None) + srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list) + srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list) + if not srt_lang_list: + return (u'WARNING: video has no closed captions', None) + if self._downloader.params.get('subtitleslang', False): + srt_lang = self._downloader.params.get('subtitleslang') + elif 'en' in srt_lang_list: + srt_lang = 'en' + else: + srt_lang = list(srt_lang_list.keys())[0] + if not srt_lang in srt_lang_list: + return (u'WARNING: no closed captions found in the specified language', None) + request = compat_urllib_request.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id)) + try: + srt_xml = compat_urllib_request.urlopen(request).read().decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None) + if not srt_xml: + return (u'WARNING: unable to download video subtitles', None) + return (None, self._closed_captions_xml_to_srt(srt_xml)) + + def _print_formats(self, formats): + print('Available formats:') + for x in formats: + print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'))) + + def _real_initialize(self): + if self._downloader is None: + return + + username = None + password = None + downloader_params = self._downloader.params + + # Attempt to use provided username and password or .netrc data + if downloader_params.get('username', None) is not None: + username = downloader_params['username'] + password = downloader_params['password'] + elif downloader_params.get('usenetrc', False): + try: + info = netrc.netrc().authenticators(self._NETRC_MACHINE) + if info is not None: + username = info[0] + password = info[2] + else: + raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) + except (IOError, netrc.NetrcParseError) as err: + self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err)) + return + + # Set language + request = compat_urllib_request.Request(self._LANG_URL) + try: + self.report_lang() + compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_str(err)) + return + + # No authentication to be performed + if username is None: + return + + # Log in + login_form = { + 'current_form': 'loginForm', + 'next': '/', + 'action_login': 'Log In', + 'username': username, + 'password': password, + } + request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) + try: + self.report_login() + login_results = compat_urllib_request.urlopen(request).read().decode('utf-8') + if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None: + self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password') + return + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err)) + return + + # Confirm age + age_form = { + 'next_url': '/', + 'action_confirm': 'Confirm', + } + request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form)) + try: + self.report_age_confirmation() + age_results = compat_urllib_request.urlopen(request).read().decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err)) + return + + def _extract_id(self, url): + mobj = re.match(self._VALID_URL, url, re.VERBOSE) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group(2) + return video_id + + def _real_extract(self, url): + # Extract original video URL from URL with redirection, like age verification, using next_url parameter + mobj = re.search(self._NEXT_URL_RE, url) + if mobj: + url = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/') + video_id = self._extract_id(url) + + # Get video webpage + self.report_video_webpage_download(video_id) + url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id + request = compat_urllib_request.Request(url) + try: + video_webpage_bytes = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) + return + + video_webpage = video_webpage_bytes.decode('utf-8', 'ignore') + + # Attempt to extract SWF player URL + mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) + if mobj is not None: + player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) + else: + player_url = None + + # Get video info + self.report_video_info_webpage_download(video_id) + for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: + video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' + % (video_id, el_type)) + request = compat_urllib_request.Request(video_info_url) + try: + video_info_webpage_bytes = compat_urllib_request.urlopen(request).read() + video_info_webpage = video_info_webpage_bytes.decode('utf-8', 'ignore') + video_info = compat_parse_qs(video_info_webpage) + if 'token' in video_info: + break + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) + return + if 'token' not in video_info: + if 'reason' in video_info: + self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0]) + else: + self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason') + return + + # Check for "rental" videos + if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: + self._downloader.trouble(u'ERROR: "rental" videos not supported') + return + + # Start extracting information + self.report_information_extraction(video_id) + + # uploader + if 'author' not in video_info: + self._downloader.trouble(u'ERROR: unable to extract uploader name') + return + video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0]) + + # uploader_id + video_uploader_id = None + mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage) + if mobj is not None: + video_uploader_id = mobj.group(1) + else: + self._downloader.trouble(u'WARNING: unable to extract uploader nickname') + + # title + if 'title' not in video_info: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = compat_urllib_parse.unquote_plus(video_info['title'][0]) + + # thumbnail image + if 'thumbnail_url' not in video_info: + self._downloader.trouble(u'WARNING: unable to extract video thumbnail') + video_thumbnail = '' + else: # don't panic if we can't find it + video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0]) + + # upload date + upload_date = None + mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL) + if mobj is not None: + upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) + format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y'] + for expression in format_expressions: + try: + upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d') + except: + pass + + # description + video_description = get_element_by_id("eow-description", video_webpage) + if video_description: + video_description = clean_html(video_description) + else: + video_description = '' + + # closed captions + video_subtitles = None + if self._downloader.params.get('writesubtitles', False): + (srt_error, video_subtitles) = self._extract_subtitles(video_id) + if srt_error: + self._downloader.trouble(srt_error) + + if 'length_seconds' not in video_info: + self._downloader.trouble(u'WARNING: unable to extract video duration') + video_duration = '' + else: + video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0]) + + # token + video_token = compat_urllib_parse.unquote_plus(video_info['token'][0]) + + # Decide which formats to download + req_format = self._downloader.params.get('format', None) + + if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): + self.report_rtmp_download() + video_url_list = [(None, video_info['conn'][0])] + elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1: + url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',') + url_data = [compat_parse_qs(uds) for uds in url_data_strs] + url_data = [ud for ud in url_data if 'itag' in ud and 'url' in ud] + url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data) + + format_limit = self._downloader.params.get('format_limit', None) + available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats + if format_limit is not None and format_limit in available_formats: + format_list = available_formats[available_formats.index(format_limit):] + else: + format_list = available_formats + existing_formats = [x for x in format_list if x in url_map] + if len(existing_formats) == 0: + self._downloader.trouble(u'ERROR: no known formats available for video') + return + if self._downloader.params.get('listformats', None): + self._print_formats(existing_formats) + return + if req_format is None or req_format == 'best': + video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality + elif req_format == 'worst': + video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality + elif req_format in ('-1', 'all'): + video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats + else: + # Specific formats. We pick the first in a slash-delimeted sequence. + # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'. + req_formats = req_format.split('/') + video_url_list = None + for rf in req_formats: + if rf in url_map: + video_url_list = [(rf, url_map[rf])] + break + if video_url_list is None: + self._downloader.trouble(u'ERROR: requested format not available') + return + else: + self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info') + return + + results = [] + for format_param, video_real_url in video_url_list: + # Extension + video_extension = self._video_extensions.get(format_param, 'flv') + + video_format = '{0} - {1}'.format(format_param if format_param else video_extension, + self._video_dimensions.get(format_param, '???')) + + results.append({ + 'id': video_id, + 'url': video_real_url, + 'uploader': video_uploader, + 'uploader_id': video_uploader_id, + 'upload_date': upload_date, + 'title': video_title, + 'ext': video_extension, + 'format': video_format, + 'thumbnail': video_thumbnail, + 'description': video_description, + 'player_url': player_url, + 'subtitles': video_subtitles, + 'duration': video_duration + }) + return results class MetacafeIE(InfoExtractor): - """Information Extractor for metacafe.com.""" - - _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' - _DISCLAIMER = 'http://www.metacafe.com/family_filter/' - _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' - IE_NAME = u'metacafe' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_disclaimer(self): - """Report disclaimer retrieval.""" - self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') - - def report_age_confirmation(self): - """Report attempt to confirm age.""" - self._downloader.to_screen(u'[metacafe] Confirming age') - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) - - def _real_initialize(self): - # Retrieve disclaimer - request = urllib2.Request(self._DISCLAIMER) - try: - self.report_disclaimer() - disclaimer = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err)) - return - - # Confirm age - disclaimer_form = { - 'filters': '0', - 'submit': "Continue - I'm over 18", - } - request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form)) - try: - self.report_age_confirmation() - disclaimer = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) - return - - def _real_extract(self, url): - # Extract id and simplified title from URL - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - - video_id = mobj.group(1) - - # Check if video comes from YouTube - mobj2 = re.match(r'^yt-(.*)$', video_id) - if mobj2 is not None: - self._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)]) - return - - # Retrieve video webpage to extract further information - request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id) - try: - self.report_download_webpage(video_id) - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err)) - return - - # Extract URL, uploader and title from webpage - self.report_extraction(video_id) - mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) - if mobj is not None: - mediaURL = urllib.unquote(mobj.group(1)) - video_extension = mediaURL[-3:] - - # Extract gdaKey if available - mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) - if mobj is None: - video_url = mediaURL - else: - gdaKey = mobj.group(1) - video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) - else: - mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - vardict = parse_qs(mobj.group(1)) - if 'mediaData' not in vardict: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0]) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - mediaURL = mobj.group(1).replace('\\/', '/') - video_extension = mediaURL[-3:] - video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2)) - - mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') - return - video_title = mobj.group(1).decode('utf-8') - - mobj = re.search(r'submitter=(.*?);', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract uploader nickname') - return - video_uploader = mobj.group(1) - - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_url.decode('utf-8'), - 'uploader': video_uploader.decode('utf-8'), - 'upload_date': u'NA', - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - 'format': u'NA', - 'player_url': None, - }] + """Information Extractor for metacafe.com.""" + + _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' + _DISCLAIMER = 'http://www.metacafe.com/family_filter/' + _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' + IE_NAME = u'metacafe' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_disclaimer(self): + """Report disclaimer retrieval.""" + self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') + + def report_age_confirmation(self): + """Report attempt to confirm age.""" + self._downloader.to_screen(u'[metacafe] Confirming age') + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) + + def _real_initialize(self): + # Retrieve disclaimer + request = compat_urllib_request.Request(self._DISCLAIMER) + try: + self.report_disclaimer() + disclaimer = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % compat_str(err)) + return + + # Confirm age + disclaimer_form = { + 'filters': '0', + 'submit': "Continue - I'm over 18", + } + request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form)) + try: + self.report_age_confirmation() + disclaimer = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err)) + return + + def _real_extract(self, url): + # Extract id and simplified title from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + video_id = mobj.group(1) + + # Check if video comes from YouTube + mobj2 = re.match(r'^yt-(.*)$', video_id) + if mobj2 is not None: + self._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)]) + return + + # Retrieve video webpage to extract further information + request = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id) + try: + self.report_download_webpage(video_id) + webpage = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err)) + return + + # Extract URL, uploader and title from webpage + self.report_extraction(video_id) + mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) + if mobj is not None: + mediaURL = compat_urllib_parse.unquote(mobj.group(1)) + video_extension = mediaURL[-3:] + + # Extract gdaKey if available + mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) + if mobj is None: + video_url = mediaURL + else: + gdaKey = mobj.group(1) + video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) + else: + mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + vardict = compat_parse_qs(mobj.group(1)) + if 'mediaData' not in vardict: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0]) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mediaURL = mobj.group(1).replace('\\/', '/') + video_extension = mediaURL[-3:] + video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2)) + + mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_title = mobj.group(1).decode('utf-8') + + mobj = re.search(r'submitter=(.*?);', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + return + video_uploader = mobj.group(1) + + return [{ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': video_uploader.decode('utf-8'), + 'upload_date': None, + 'title': video_title, + 'ext': video_extension.decode('utf-8'), + }] class DailymotionIE(InfoExtractor): - """Information Extractor for Dailymotion""" - - _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)' - IE_NAME = u'dailymotion' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) - - def _real_extract(self, url): - # Extract id and simplified title from URL - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - - video_id = mobj.group(1).split('_')[0].split('?')[0] - - video_extension = 'mp4' - - # Retrieve video webpage to extract further information - request = urllib2.Request(url) - request.add_header('Cookie', 'family_filter=off') - try: - self.report_download_webpage(video_id) - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err)) - return - - # Extract URL, uploader and title from webpage - self.report_extraction(video_id) - mobj = re.search(r'\s*var flashvars = (.*)', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - flashvars = urllib.unquote(mobj.group(1)) - - for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']: - if key in flashvars: - max_quality = key - self._downloader.to_screen(u'[dailymotion] Using %s' % key) - break - else: - self._downloader.trouble(u'ERROR: unable to extract video URL') - return - - mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video URL') - return - - video_url = urllib.unquote(mobj.group(1)).replace('\\/', '/') - - # TODO: support choosing qualities - - mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') - return - video_title = unescapeHTML(mobj.group('title').decode('utf-8')) - - video_uploader = u'NA' - mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage) - if mobj is None: - # lookin for official user - mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage) - if mobj_official is None: - self._downloader.trouble(u'WARNING: unable to extract uploader nickname') - else: - video_uploader = mobj_official.group(1) - else: - video_uploader = mobj.group(1) - - video_upload_date = u'NA' - mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage) - if mobj is not None: - video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1) - - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_url.decode('utf-8'), - 'uploader': video_uploader.decode('utf-8'), - 'upload_date': video_upload_date, - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - 'format': u'NA', - 'player_url': None, - }] - - -class GoogleIE(InfoExtractor): - """Information extractor for video.google.com.""" - - _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*' - IE_NAME = u'video.google' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id) - - def _real_extract(self, url): - # Extract id from URL - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - - video_id = mobj.group(1) - - video_extension = 'mp4' - - # Retrieve video webpage to extract further information - request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id) - try: - self.report_download_webpage(video_id) - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) - return - - # Extract URL, uploader, and title from webpage - self.report_extraction(video_id) - mobj = re.search(r"download_url:'([^']+)'", webpage) - if mobj is None: - video_extension = 'flv' - mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - mediaURL = urllib.unquote(mobj.group(1)) - mediaURL = mediaURL.replace('\\x3d', '\x3d') - mediaURL = mediaURL.replace('\\x26', '\x26') - - video_url = mediaURL - - mobj = re.search(r'<title>(.*)</title>', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') - return - video_title = mobj.group(1).decode('utf-8') - - # Extract video description - mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video description') - return - video_description = mobj.group(1).decode('utf-8') - if not video_description: - video_description = 'No description available.' - - # Extract video thumbnail - if self._downloader.params.get('forcethumbnail', False): - request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id))) - try: - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) - return - mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video thumbnail') - return - video_thumbnail = mobj.group(1) - else: # we need something to pass to process_info - video_thumbnail = '' - - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_url.decode('utf-8'), - 'uploader': u'NA', - 'upload_date': u'NA', - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - 'format': u'NA', - 'player_url': None, - }] + """Information Extractor for Dailymotion""" + + _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)' + IE_NAME = u'dailymotion' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) + + def _real_extract(self, url): + # Extract id and simplified title from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + video_id = mobj.group(1).split('_')[0].split('?')[0] + + video_extension = 'mp4' + + # Retrieve video webpage to extract further information + request = compat_urllib_request.Request(url) + request.add_header('Cookie', 'family_filter=off') + webpage = self._download_webpage(request, video_id) + + # Extract URL, uploader and title from webpage + self.report_extraction(video_id) + mobj = re.search(r'\s*var flashvars = (.*)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + flashvars = compat_urllib_parse.unquote(mobj.group(1)) + + for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']: + if key in flashvars: + max_quality = key + self._downloader.to_screen(u'[dailymotion] Using %s' % key) + break + else: + self._downloader.trouble(u'ERROR: unable to extract video URL') + return + + mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video URL') + return + + video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/') + + # TODO: support choosing qualities + + mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_title = unescapeHTML(mobj.group('title')) + + video_uploader = None + mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage) + if mobj is None: + # lookin for official user + mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage) + if mobj_official is None: + self._downloader.trouble(u'WARNING: unable to extract uploader nickname') + else: + video_uploader = mobj_official.group(1) + else: + video_uploader = mobj.group(1) + + video_upload_date = None + mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage) + if mobj is not None: + video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1) + + return [{ + 'id': video_id, + 'url': video_url, + 'uploader': video_uploader, + 'upload_date': video_upload_date, + 'title': video_title, + 'ext': video_extension, + }] class PhotobucketIE(InfoExtractor): - """Information extractor for photobucket.com.""" - - _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' - IE_NAME = u'photobucket' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id) - - def _real_extract(self, url): - # Extract id from URL - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - - video_id = mobj.group(1) - - video_extension = 'flv' - - # Retrieve video webpage to extract further information - request = urllib2.Request(url) - try: - self.report_download_webpage(video_id) - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) - return - - # Extract URL, uploader, and title from webpage - self.report_extraction(video_id) - mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - mediaURL = urllib.unquote(mobj.group(1)) - - video_url = mediaURL - - mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') - return - video_title = mobj.group(1).decode('utf-8') - - video_uploader = mobj.group(2).decode('utf-8') - - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_url.decode('utf-8'), - 'uploader': video_uploader, - 'upload_date': u'NA', - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - 'format': u'NA', - 'player_url': None, - }] + """Information extractor for photobucket.com.""" + + _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' + IE_NAME = u'photobucket' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id) + + def _real_extract(self, url): + # Extract id from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + video_id = mobj.group(1) + + video_extension = 'flv' + + # Retrieve video webpage to extract further information + request = compat_urllib_request.Request(url) + try: + self.report_download_webpage(video_id) + webpage = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) + return + + # Extract URL, uploader, and title from webpage + self.report_extraction(video_id) + mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mediaURL = compat_urllib_parse.unquote(mobj.group(1)) + + video_url = mediaURL + + mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_title = mobj.group(1).decode('utf-8') + + video_uploader = mobj.group(2).decode('utf-8') + + return [{ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': video_uploader, + 'upload_date': None, + 'title': video_title, + 'ext': video_extension.decode('utf-8'), + }] class YahooIE(InfoExtractor): - """Information extractor for video.yahoo.com.""" - - # _VALID_URL matches all Yahoo! Video URLs - # _VPAGE_URL matches only the extractable '/watch/' URLs - _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' - _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' - IE_NAME = u'video.yahoo' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id) - - def _real_extract(self, url, new_video=True): - # Extract ID from URL - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - - video_id = mobj.group(2) - video_extension = 'flv' - - # Rewrite valid but non-extractable URLs as - # extractable English language /watch/ URLs - if re.match(self._VPAGE_URL, url) is None: - request = urllib2.Request(url) - try: - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) - return - - mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: Unable to extract id field') - return - yahoo_id = mobj.group(1) - - mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: Unable to extract vid field') - return - yahoo_vid = mobj.group(1) - - url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id) - return self._real_extract(url, new_video=False) - - # Retrieve video webpage to extract further information - request = urllib2.Request(url) - try: - self.report_download_webpage(video_id) - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) - return - - # Extract uploader and title from webpage - self.report_extraction(video_id) - mobj = re.search(r'<meta name="title" content="(.*)" />', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video title') - return - video_title = mobj.group(1).decode('utf-8') - - mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video uploader') - return - video_uploader = mobj.group(1).decode('utf-8') - - # Extract video thumbnail - mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video thumbnail') - return - video_thumbnail = mobj.group(1).decode('utf-8') - - # Extract video description - mobj = re.search(r'<meta name="description" content="(.*)" />', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video description') - return - video_description = mobj.group(1).decode('utf-8') - if not video_description: - video_description = 'No description available.' - - # Extract video height and width - mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video height') - return - yv_video_height = mobj.group(1) - - mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video width') - return - yv_video_width = mobj.group(1) - - # Retrieve video playlist to extract media URL - # I'm not completely sure what all these options are, but we - # seem to need most of them, otherwise the server sends a 401. - yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents - yv_bitrate = '700' # according to Wikipedia this is hard-coded - request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + - '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + - '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') - try: - self.report_download_webpage(video_id) - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) - return - - # Extract media URL from playlist XML - mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: Unable to extract media URL') - return - video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8') - video_url = unescapeHTML(video_url) - - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_url, - 'uploader': video_uploader, - 'upload_date': u'NA', - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - 'thumbnail': video_thumbnail.decode('utf-8'), - 'description': video_description, - 'thumbnail': video_thumbnail, - 'player_url': None, - }] + """Information extractor for video.yahoo.com.""" + + _WORKING = False + # _VALID_URL matches all Yahoo! Video URLs + # _VPAGE_URL matches only the extractable '/watch/' URLs + _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' + _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' + IE_NAME = u'video.yahoo' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id) + + def _real_extract(self, url, new_video=True): + # Extract ID from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + video_id = mobj.group(2) + video_extension = 'flv' + + # Rewrite valid but non-extractable URLs as + # extractable English language /watch/ URLs + if re.match(self._VPAGE_URL, url) is None: + request = compat_urllib_request.Request(url) + try: + webpage = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) + return + + mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: Unable to extract id field') + return + yahoo_id = mobj.group(1) + + mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: Unable to extract vid field') + return + yahoo_vid = mobj.group(1) + + url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id) + return self._real_extract(url, new_video=False) + + # Retrieve video webpage to extract further information + request = compat_urllib_request.Request(url) + try: + self.report_download_webpage(video_id) + webpage = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) + return + + # Extract uploader and title from webpage + self.report_extraction(video_id) + mobj = re.search(r'<meta name="title" content="(.*)" />', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = mobj.group(1).decode('utf-8') + + mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video uploader') + return + video_uploader = mobj.group(1).decode('utf-8') + + # Extract video thumbnail + mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = mobj.group(1).decode('utf-8') + + # Extract video description + mobj = re.search(r'<meta name="description" content="(.*)" />', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video description') + return + video_description = mobj.group(1).decode('utf-8') + if not video_description: + video_description = 'No description available.' + + # Extract video height and width + mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video height') + return + yv_video_height = mobj.group(1) + + mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video width') + return + yv_video_width = mobj.group(1) + + # Retrieve video playlist to extract media URL + # I'm not completely sure what all these options are, but we + # seem to need most of them, otherwise the server sends a 401. + yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents + yv_bitrate = '700' # according to Wikipedia this is hard-coded + request = compat_urllib_request.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + + '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + + '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') + try: + self.report_download_webpage(video_id) + webpage = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) + return + + # Extract media URL from playlist XML + mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: Unable to extract media URL') + return + video_url = compat_urllib_parse.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8') + video_url = unescapeHTML(video_url) + + return [{ + 'id': video_id.decode('utf-8'), + 'url': video_url, + 'uploader': video_uploader, + 'upload_date': None, + 'title': video_title, + 'ext': video_extension.decode('utf-8'), + 'thumbnail': video_thumbnail.decode('utf-8'), + 'description': video_description, + }] class VimeoIE(InfoExtractor): - """Information extractor for vimeo.com.""" - - # _VALID_URL matches Vimeo URLs - _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)' - IE_NAME = u'vimeo' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id) - - def _real_extract(self, url, new_video=True): - # Extract ID from URL - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - - video_id = mobj.group(1) - - # Retrieve video webpage to extract further information - request = urllib2.Request(url, None, std_headers) - try: - self.report_download_webpage(video_id) - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) - return - - # Now we begin extracting as much information as we can from what we - # retrieved. First we extract the information common to all extractors, - # and latter we extract those that are Vimeo specific. - self.report_extraction(video_id) - - # Extract the config JSON - config = webpage.split(' = {config:')[1].split(',assets:')[0] - try: - config = json.loads(config) - except: - self._downloader.trouble(u'ERROR: unable to extract info section') - return - - # Extract title - video_title = config["video"]["title"] - - # Extract uploader - video_uploader = config["video"]["owner"]["name"] - - # Extract video thumbnail - video_thumbnail = config["video"]["thumbnail"] - - # Extract video description - video_description = get_element_by_id("description", webpage.decode('utf8')) - if video_description: video_description = clean_html(video_description) - else: video_description = '' - - # Extract upload date - video_upload_date = u'NA' - mobj = re.search(r'<span id="clip-date" style="display:none">[^:]*: (.*?)( \([^\(]*\))?</span>', webpage) - if mobj is not None: - video_upload_date = mobj.group(1) - - # Vimeo specific: extract request signature and timestamp - sig = config['request']['signature'] - timestamp = config['request']['timestamp'] - - # Vimeo specific: extract video codec and quality information - # TODO bind to format param - codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')] - for codec in codecs: - if codec[0] in config["video"]["files"]: - video_codec = codec[0] - video_extension = codec[1] - if 'hd' in config["video"]["files"][codec[0]]: quality = 'hd' - else: quality = 'sd' - break - else: - self._downloader.trouble(u'ERROR: no known codec found') - return - - video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \ - %(video_id, sig, timestamp, quality, video_codec.upper()) - - return [{ - 'id': video_id, - 'url': video_url, - 'uploader': video_uploader, - 'upload_date': video_upload_date, - 'title': video_title, - 'ext': video_extension, - 'thumbnail': video_thumbnail, - 'description': video_description, - 'player_url': None, - }] + """Information extractor for vimeo.com.""" + + # _VALID_URL matches Vimeo URLs + _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?:videos?/)?([0-9]+)' + IE_NAME = u'vimeo' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id) + + def _real_extract(self, url, new_video=True): + # Extract ID from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + video_id = mobj.group(1) + + # Retrieve video webpage to extract further information + request = compat_urllib_request.Request(url, None, std_headers) + try: + self.report_download_webpage(video_id) + webpage_bytes = compat_urllib_request.urlopen(request).read() + webpage = webpage_bytes.decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) + return + + # Now we begin extracting as much information as we can from what we + # retrieved. First we extract the information common to all extractors, + # and latter we extract those that are Vimeo specific. + self.report_extraction(video_id) + + # Extract the config JSON + try: + config = webpage.split(' = {config:')[1].split(',assets:')[0] + config = json.loads(config) + except: + self._downloader.trouble(u'ERROR: unable to extract info section') + return + + # Extract title + video_title = config["video"]["title"] + + # Extract uploader and uploader_id + video_uploader = config["video"]["owner"]["name"] + video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] + + # Extract video thumbnail + video_thumbnail = config["video"]["thumbnail"] + + # Extract video description + video_description = get_element_by_attribute("itemprop", "description", webpage) + if video_description: video_description = clean_html(video_description) + else: video_description = '' + + # Extract upload date + video_upload_date = None + mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage) + if mobj is not None: + video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3) + + # Vimeo specific: extract request signature and timestamp + sig = config['request']['signature'] + timestamp = config['request']['timestamp'] + + # Vimeo specific: extract video codec and quality information + # First consider quality, then codecs, then take everything + # TODO bind to format param + codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')] + files = { 'hd': [], 'sd': [], 'other': []} + for codec_name, codec_extension in codecs: + if codec_name in config["video"]["files"]: + if 'hd' in config["video"]["files"][codec_name]: + files['hd'].append((codec_name, codec_extension, 'hd')) + elif 'sd' in config["video"]["files"][codec_name]: + files['sd'].append((codec_name, codec_extension, 'sd')) + else: + files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0])) + + for quality in ('hd', 'sd', 'other'): + if len(files[quality]) > 0: + video_quality = files[quality][0][2] + video_codec = files[quality][0][0] + video_extension = files[quality][0][1] + self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality)) + break + else: + self._downloader.trouble(u'ERROR: no known codec found') + return + + video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \ + %(video_id, sig, timestamp, video_quality, video_codec.upper()) + + return [{ + 'id': video_id, + 'url': video_url, + 'uploader': video_uploader, + 'uploader_id': video_uploader_id, + 'upload_date': video_upload_date, + 'title': video_title, + 'ext': video_extension, + 'thumbnail': video_thumbnail, + 'description': video_description, + }] + + +class ArteTvIE(InfoExtractor): + """arte.tv information extractor.""" + + _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*' + _LIVE_URL = r'index-[0-9]+\.html$' + + IE_NAME = u'arte.tv' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id) + + def fetch_webpage(self, url): + request = compat_urllib_request.Request(url) + try: + self.report_download_webpage(url) + webpage = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) + return + except ValueError as err: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + return webpage + + def grep_webpage(self, url, regex, regexFlags, matchTuples): + page = self.fetch_webpage(url) + mobj = re.search(regex, page, regexFlags) + info = {} + + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + for (i, key, err) in matchTuples: + if mobj.group(i) is None: + self._downloader.trouble(err) + return + else: + info[key] = mobj.group(i) + + return info + + def extractLiveStream(self, url): + video_lang = url.split('/')[-4] + info = self.grep_webpage( + url, + r'src="(.*?/videothek_js.*?\.js)', + 0, + [ + (1, 'url', u'ERROR: Invalid URL: %s' % url) + ] + ) + http_host = url.split('/')[2] + next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url'))) + info = self.grep_webpage( + next_url, + r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' + + '(http://.*?\.swf).*?' + + '(rtmp://.*?)\'', + re.DOTALL, + [ + (1, 'path', u'ERROR: could not extract video path: %s' % url), + (2, 'player', u'ERROR: could not extract video player: %s' % url), + (3, 'url', u'ERROR: could not extract video url: %s' % url) + ] + ) + video_url = u'%s/%s' % (info.get('url'), info.get('path')) + + def extractPlus7Stream(self, url): + video_lang = url.split('/')[-3] + info = self.grep_webpage( + url, + r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)', + 0, + [ + (1, 'url', u'ERROR: Invalid URL: %s' % url) + ] + ) + next_url = compat_urllib_parse.unquote(info.get('url')) + info = self.grep_webpage( + next_url, + r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang, + 0, + [ + (1, 'url', u'ERROR: Could not find <video> tag: %s' % url) + ] + ) + next_url = compat_urllib_parse.unquote(info.get('url')) + + info = self.grep_webpage( + next_url, + r'<video id="(.*?)".*?>.*?' + + '<name>(.*?)</name>.*?' + + '<dateVideo>(.*?)</dateVideo>.*?' + + '<url quality="hd">(.*?)</url>', + re.DOTALL, + [ + (1, 'id', u'ERROR: could not extract video id: %s' % url), + (2, 'title', u'ERROR: could not extract video title: %s' % url), + (3, 'date', u'ERROR: could not extract video date: %s' % url), + (4, 'url', u'ERROR: could not extract video url: %s' % url) + ] + ) + + return { + 'id': info.get('id'), + 'url': compat_urllib_parse.unquote(info.get('url')), + 'uploader': u'arte.tv', + 'upload_date': info.get('date'), + 'title': info.get('title').decode('utf-8'), + 'ext': u'mp4', + 'format': u'NA', + 'player_url': None, + } + + def _real_extract(self, url): + video_id = url.split('/')[-1] + self.report_extraction(video_id) + + if re.search(self._LIVE_URL, video_id) is not None: + self.extractLiveStream(url) + return + else: + info = self.extractPlus7Stream(url) + + return [info] class GenericIE(InfoExtractor): - """Generic last-resort information extractor.""" - - _VALID_URL = r'.*' - IE_NAME = u'generic' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') - self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id) - - def report_following_redirect(self, new_url): - """Report information extraction.""" - self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url) - - def _test_redirect(self, url): - """Check if it is a redirect, like url shorteners, in case restart chain.""" - class HeadRequest(urllib2.Request): - def get_method(self): - return "HEAD" - - class HEADRedirectHandler(urllib2.HTTPRedirectHandler): - """ - Subclass the HTTPRedirectHandler to make it use our - HeadRequest also on the redirected URL - """ - def redirect_request(self, req, fp, code, msg, headers, newurl): - if code in (301, 302, 303, 307): - newurl = newurl.replace(' ', '%20') - newheaders = dict((k,v) for k,v in req.headers.items() - if k.lower() not in ("content-length", "content-type")) - return HeadRequest(newurl, - headers=newheaders, - origin_req_host=req.get_origin_req_host(), - unverifiable=True) - else: - raise urllib2.HTTPError(req.get_full_url(), code, msg, headers, fp) - - class HTTPMethodFallback(urllib2.BaseHandler): - """ - Fallback to GET if HEAD is not allowed (405 HTTP error) - """ - def http_error_405(self, req, fp, code, msg, headers): - fp.read() - fp.close() - - newheaders = dict((k,v) for k,v in req.headers.items() - if k.lower() not in ("content-length", "content-type")) - return self.parent.open(urllib2.Request(req.get_full_url(), - headers=newheaders, - origin_req_host=req.get_origin_req_host(), - unverifiable=True)) - - # Build our opener - opener = urllib2.OpenerDirector() - for handler in [urllib2.HTTPHandler, urllib2.HTTPDefaultErrorHandler, - HTTPMethodFallback, HEADRedirectHandler, - urllib2.HTTPErrorProcessor, urllib2.HTTPSHandler]: - opener.add_handler(handler()) - - response = opener.open(HeadRequest(url)) - new_url = response.geturl() - - if url == new_url: return False - - self.report_following_redirect(new_url) - self._downloader.download([new_url]) - return True - - def _real_extract(self, url): - if self._test_redirect(url): return - - video_id = url.split('/')[-1] - request = urllib2.Request(url) - try: - self.report_download_webpage(video_id) - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) - return - except ValueError, err: - # since this is the last-resort InfoExtractor, if - # this error is thrown, it'll be thrown here - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - - self.report_extraction(video_id) - # Start with something easy: JW Player in SWFObject - mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) - if mobj is None: - # Broaden the search a little bit - mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - - # It's possible that one of the regexes - # matched, but returned an empty group: - if mobj.group(1) is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - - video_url = urllib.unquote(mobj.group(1)) - video_id = os.path.basename(video_url) - - # here's a fun little line of code for you: - video_extension = os.path.splitext(video_id)[1][1:] - video_id = os.path.splitext(video_id)[0] - - # it's tempting to parse this further, but you would - # have to take into account all the variations like - # Video Title - Site Name - # Site Name | Video Title - # Video Title - Tagline | Site Name - # and so on and so forth; it's just not practical - mobj = re.search(r'<title>(.*)</title>', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') - return - video_title = mobj.group(1).decode('utf-8') - - # video uploader is domain name - mobj = re.match(r'(?:https?://)?([^/]*)/.*', url) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') - return - video_uploader = mobj.group(1).decode('utf-8') - - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_url.decode('utf-8'), - 'uploader': video_uploader, - 'upload_date': u'NA', - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - 'format': u'NA', - 'player_url': None, - }] + """Generic last-resort information extractor.""" + + _VALID_URL = r'.*' + IE_NAME = u'generic' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') + self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id) + + def report_following_redirect(self, new_url): + """Report information extraction.""" + self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url) + + def _test_redirect(self, url): + """Check if it is a redirect, like url shorteners, in case restart chain.""" + class HeadRequest(compat_urllib_request.Request): + def get_method(self): + return "HEAD" + + class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler): + """ + Subclass the HTTPRedirectHandler to make it use our + HeadRequest also on the redirected URL + """ + def redirect_request(self, req, fp, code, msg, headers, newurl): + if code in (301, 302, 303, 307): + newurl = newurl.replace(' ', '%20') + newheaders = dict((k,v) for k,v in req.headers.items() + if k.lower() not in ("content-length", "content-type")) + return HeadRequest(newurl, + headers=newheaders, + origin_req_host=req.get_origin_req_host(), + unverifiable=True) + else: + raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp) + + class HTTPMethodFallback(compat_urllib_request.BaseHandler): + """ + Fallback to GET if HEAD is not allowed (405 HTTP error) + """ + def http_error_405(self, req, fp, code, msg, headers): + fp.read() + fp.close() + + newheaders = dict((k,v) for k,v in req.headers.items() + if k.lower() not in ("content-length", "content-type")) + return self.parent.open(compat_urllib_request.Request(req.get_full_url(), + headers=newheaders, + origin_req_host=req.get_origin_req_host(), + unverifiable=True)) + + # Build our opener + opener = compat_urllib_request.OpenerDirector() + for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler, + HTTPMethodFallback, HEADRedirectHandler, + compat_urllib_error.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]: + opener.add_handler(handler()) + + response = opener.open(HeadRequest(url)) + new_url = response.geturl() + + if url == new_url: + return False + + self.report_following_redirect(new_url) + self._downloader.download([new_url]) + return True + + def _real_extract(self, url): + if self._test_redirect(url): return + + video_id = url.split('/')[-1] + request = compat_urllib_request.Request(url) + try: + self.report_download_webpage(video_id) + webpage = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) + return + except ValueError as err: + # since this is the last-resort InfoExtractor, if + # this error is thrown, it'll be thrown here + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + self.report_extraction(video_id) + # Start with something easy: JW Player in SWFObject + mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) + if mobj is None: + # Broaden the search a little bit + mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + # It's possible that one of the regexes + # matched, but returned an empty group: + if mobj.group(1) is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + video_url = compat_urllib_parse.unquote(mobj.group(1)) + video_id = os.path.basename(video_url) + + # here's a fun little line of code for you: + video_extension = os.path.splitext(video_id)[1][1:] + video_id = os.path.splitext(video_id)[0] + + # it's tempting to parse this further, but you would + # have to take into account all the variations like + # Video Title - Site Name + # Site Name | Video Title + # Video Title - Tagline | Site Name + # and so on and so forth; it's just not practical + mobj = re.search(r'<title>(.*)</title>', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_title = mobj.group(1) + + # video uploader is domain name + mobj = re.match(r'(?:https?://)?([^/]*)/.*', url) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_uploader = mobj.group(1) + + return [{ + 'id': video_id, + 'url': video_url, + 'uploader': video_uploader, + 'upload_date': None, + 'title': video_title, + 'ext': video_extension, + }] class YoutubeSearchIE(InfoExtractor): - """Information Extractor for YouTube search queries.""" - _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+' - _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc' - _max_youtube_results = 1000 - IE_NAME = u'youtube:search' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_page(self, query, pagenum): - """Report attempt to download search page with given number.""" - query = query.decode(preferredencoding()) - self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) - - def _real_extract(self, query): - mobj = re.match(self._VALID_URL, query) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) - return - - prefix, query = query.split(':') - prefix = prefix[8:] - query = query.encode('utf-8') - if prefix == '': - self._download_n_results(query, 1) - return - elif prefix == 'all': - self._download_n_results(query, self._max_youtube_results) - return - else: - try: - n = long(prefix) - if n <= 0: - self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) - return - elif n > self._max_youtube_results: - self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) - n = self._max_youtube_results - self._download_n_results(query, n) - return - except ValueError: # parsing prefix as integer fails - self._download_n_results(query, 1) - return - - def _download_n_results(self, query, n): - """Downloads a specified number of results for a query""" - - video_ids = [] - pagenum = 0 - limit = n - - while (50 * pagenum) < limit: - self.report_download_page(query, pagenum+1) - result_url = self._API_URL % (urllib.quote_plus(query), (50*pagenum)+1) - request = urllib2.Request(result_url) - try: - data = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download API page: %s' % str(err)) - return - api_response = json.loads(data)['data'] - - new_ids = list(video['id'] for video in api_response['items']) - video_ids += new_ids - - limit = min(n, api_response['totalItems']) - pagenum += 1 - - if len(video_ids) > n: - video_ids = video_ids[:n] - for id in video_ids: - self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) - return + """Information Extractor for YouTube search queries.""" + _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+' + _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc' + _max_youtube_results = 1000 + IE_NAME = u'youtube:search' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_page(self, query, pagenum): + """Report attempt to download search page with given number.""" + query = query.decode(preferredencoding()) + self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) + + def _real_extract(self, query): + mobj = re.match(self._VALID_URL, query) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) + return + + prefix, query = query.split(':') + prefix = prefix[8:] + query = query.encode('utf-8') + if prefix == '': + self._download_n_results(query, 1) + return + elif prefix == 'all': + self._download_n_results(query, self._max_youtube_results) + return + else: + try: + n = int(prefix) + if n <= 0: + self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) + return + elif n > self._max_youtube_results: + self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) + n = self._max_youtube_results + self._download_n_results(query, n) + return + except ValueError: # parsing prefix as integer fails + self._download_n_results(query, 1) + return + + def _download_n_results(self, query, n): + """Downloads a specified number of results for a query""" + + video_ids = [] + pagenum = 0 + limit = n + + while (50 * pagenum) < limit: + self.report_download_page(query, pagenum+1) + result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1) + request = compat_urllib_request.Request(result_url) + try: + data = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download API page: %s' % compat_str(err)) + return + api_response = json.loads(data)['data'] + + new_ids = list(video['id'] for video in api_response['items']) + video_ids += new_ids + + limit = min(n, api_response['totalItems']) + pagenum += 1 + + if len(video_ids) > n: + video_ids = video_ids[:n] + for id in video_ids: + self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) + return class GoogleSearchIE(InfoExtractor): - """Information Extractor for Google Video search queries.""" - _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+' - _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en' - _VIDEO_INDICATOR = r'<a href="http://video\.google\.com/videoplay\?docid=([^"\&]+)' - _MORE_PAGES_INDICATOR = r'class="pn" id="pnnext"' - _max_google_results = 1000 - IE_NAME = u'video.google:search' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_page(self, query, pagenum): - """Report attempt to download playlist page with given number.""" - query = query.decode(preferredencoding()) - self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum)) - - def _real_extract(self, query): - mobj = re.match(self._VALID_URL, query) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) - return - - prefix, query = query.split(':') - prefix = prefix[8:] - query = query.encode('utf-8') - if prefix == '': - self._download_n_results(query, 1) - return - elif prefix == 'all': - self._download_n_results(query, self._max_google_results) - return - else: - try: - n = long(prefix) - if n <= 0: - self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) - return - elif n > self._max_google_results: - self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n)) - n = self._max_google_results - self._download_n_results(query, n) - return - except ValueError: # parsing prefix as integer fails - self._download_n_results(query, 1) - return - - def _download_n_results(self, query, n): - """Downloads a specified number of results for a query""" - - video_ids = [] - pagenum = 0 - - while True: - self.report_download_page(query, pagenum) - result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum*10) - request = urllib2.Request(result_url) - try: - page = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) - return - - # Extract video identifiers - for mobj in re.finditer(self._VIDEO_INDICATOR, page): - video_id = mobj.group(1) - if video_id not in video_ids: - video_ids.append(video_id) - if len(video_ids) == n: - # Specified n videos reached - for id in video_ids: - self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id]) - return - - if re.search(self._MORE_PAGES_INDICATOR, page) is None: - for id in video_ids: - self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id]) - return - - pagenum = pagenum + 1 + """Information Extractor for Google Video search queries.""" + _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+' + _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en' + _VIDEO_INDICATOR = r'<a href="http://video\.google\.com/videoplay\?docid=([^"\&]+)' + _MORE_PAGES_INDICATOR = r'class="pn" id="pnnext"' + _max_google_results = 1000 + IE_NAME = u'video.google:search' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_page(self, query, pagenum): + """Report attempt to download playlist page with given number.""" + query = query.decode(preferredencoding()) + self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum)) + + def _real_extract(self, query): + mobj = re.match(self._VALID_URL, query) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) + return + + prefix, query = query.split(':') + prefix = prefix[8:] + query = query.encode('utf-8') + if prefix == '': + self._download_n_results(query, 1) + return + elif prefix == 'all': + self._download_n_results(query, self._max_google_results) + return + else: + try: + n = int(prefix) + if n <= 0: + self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) + return + elif n > self._max_google_results: + self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n)) + n = self._max_google_results + self._download_n_results(query, n) + return + except ValueError: # parsing prefix as integer fails + self._download_n_results(query, 1) + return + + def _download_n_results(self, query, n): + """Downloads a specified number of results for a query""" + + video_ids = [] + pagenum = 0 + + while True: + self.report_download_page(query, pagenum) + result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum*10) + request = compat_urllib_request.Request(result_url) + try: + page = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) + return + + # Extract video identifiers + for mobj in re.finditer(self._VIDEO_INDICATOR, page): + video_id = mobj.group(1) + if video_id not in video_ids: + video_ids.append(video_id) + if len(video_ids) == n: + # Specified n videos reached + for id in video_ids: + self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id]) + return + + if re.search(self._MORE_PAGES_INDICATOR, page) is None: + for id in video_ids: + self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id]) + return + + pagenum = pagenum + 1 class YahooSearchIE(InfoExtractor): - """Information Extractor for Yahoo! Video search queries.""" - _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+' - _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s' - _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"' - _MORE_PAGES_INDICATOR = r'\s*Next' - _max_yahoo_results = 1000 - IE_NAME = u'video.yahoo:search' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_page(self, query, pagenum): - """Report attempt to download playlist page with given number.""" - query = query.decode(preferredencoding()) - self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum)) - - def _real_extract(self, query): - mobj = re.match(self._VALID_URL, query) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) - return - - prefix, query = query.split(':') - prefix = prefix[8:] - query = query.encode('utf-8') - if prefix == '': - self._download_n_results(query, 1) - return - elif prefix == 'all': - self._download_n_results(query, self._max_yahoo_results) - return - else: - try: - n = long(prefix) - if n <= 0: - self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) - return - elif n > self._max_yahoo_results: - self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n)) - n = self._max_yahoo_results - self._download_n_results(query, n) - return - except ValueError: # parsing prefix as integer fails - self._download_n_results(query, 1) - return - - def _download_n_results(self, query, n): - """Downloads a specified number of results for a query""" - - video_ids = [] - already_seen = set() - pagenum = 1 - - while True: - self.report_download_page(query, pagenum) - result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) - request = urllib2.Request(result_url) - try: - page = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) - return - - # Extract video identifiers - for mobj in re.finditer(self._VIDEO_INDICATOR, page): - video_id = mobj.group(1) - if video_id not in already_seen: - video_ids.append(video_id) - already_seen.add(video_id) - if len(video_ids) == n: - # Specified n videos reached - for id in video_ids: - self._downloader.download(['http://video.yahoo.com/watch/%s' % id]) - return - - if re.search(self._MORE_PAGES_INDICATOR, page) is None: - for id in video_ids: - self._downloader.download(['http://video.yahoo.com/watch/%s' % id]) - return - - pagenum = pagenum + 1 + """Information Extractor for Yahoo! Video search queries.""" + + _WORKING = False + _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+' + _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s' + _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"' + _MORE_PAGES_INDICATOR = r'\s*Next' + _max_yahoo_results = 1000 + IE_NAME = u'video.yahoo:search' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_page(self, query, pagenum): + """Report attempt to download playlist page with given number.""" + query = query.decode(preferredencoding()) + self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum)) + + def _real_extract(self, query): + mobj = re.match(self._VALID_URL, query) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) + return + + prefix, query = query.split(':') + prefix = prefix[8:] + query = query.encode('utf-8') + if prefix == '': + self._download_n_results(query, 1) + return + elif prefix == 'all': + self._download_n_results(query, self._max_yahoo_results) + return + else: + try: + n = int(prefix) + if n <= 0: + self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) + return + elif n > self._max_yahoo_results: + self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n)) + n = self._max_yahoo_results + self._download_n_results(query, n) + return + except ValueError: # parsing prefix as integer fails + self._download_n_results(query, 1) + return + + def _download_n_results(self, query, n): + """Downloads a specified number of results for a query""" + + video_ids = [] + already_seen = set() + pagenum = 1 + + while True: + self.report_download_page(query, pagenum) + result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum) + request = compat_urllib_request.Request(result_url) + try: + page = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) + return + + # Extract video identifiers + for mobj in re.finditer(self._VIDEO_INDICATOR, page): + video_id = mobj.group(1) + if video_id not in already_seen: + video_ids.append(video_id) + already_seen.add(video_id) + if len(video_ids) == n: + # Specified n videos reached + for id in video_ids: + self._downloader.download(['http://video.yahoo.com/watch/%s' % id]) + return + + if re.search(self._MORE_PAGES_INDICATOR, page) is None: + for id in video_ids: + self._downloader.download(['http://video.yahoo.com/watch/%s' % id]) + return + + pagenum = pagenum + 1 class YoutubePlaylistIE(InfoExtractor): - """Information Extractor for YouTube playlists.""" - - _VALID_URL = r'(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?|PL|EC)([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*' - _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en' - _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&([^&"]+&)*list=.*?%s' - _MORE_PAGES_INDICATOR = r'yt-uix-pager-next' - IE_NAME = u'youtube:playlist' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_page(self, playlist_id, pagenum): - """Report attempt to download playlist page with given number.""" - self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum)) - - def _real_extract(self, url): - # Extract playlist id - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid url: %s' % url) - return - - # Single video case - if mobj.group(3) is not None: - self._downloader.download([mobj.group(3)]) - return - - # Download playlist pages - # prefix is 'p' as default for playlists but there are other types that need extra care - playlist_prefix = mobj.group(1) - if playlist_prefix == 'a': - playlist_access = 'artist' - else: - playlist_prefix = 'p' - playlist_access = 'view_play_list' - playlist_id = mobj.group(2) - video_ids = [] - pagenum = 1 - - while True: - self.report_download_page(playlist_id, pagenum) - url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum) - request = urllib2.Request(url) - try: - page = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) - return - - # Extract video identifiers - ids_in_page = [] - for mobj in re.finditer(self._VIDEO_INDICATOR_TEMPLATE % playlist_id, page): - if mobj.group(1) not in ids_in_page: - ids_in_page.append(mobj.group(1)) - video_ids.extend(ids_in_page) - - if re.search(self._MORE_PAGES_INDICATOR, page) is None: - break - pagenum = pagenum + 1 - - playliststart = self._downloader.params.get('playliststart', 1) - 1 - playlistend = self._downloader.params.get('playlistend', -1) - if playlistend == -1: - video_ids = video_ids[playliststart:] - else: - video_ids = video_ids[playliststart:playlistend] - - for id in video_ids: - self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) - return + """Information Extractor for YouTube playlists.""" + + _VALID_URL = r'(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?|PL|EC)([0-9A-Za-z-_]{10,})(?:/.*?/([0-9A-Za-z_-]+))?.*' + _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en' + _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&([^&"]+&)*list=.*?%s' + _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}" + IE_NAME = u'youtube:playlist' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_page(self, playlist_id, pagenum): + """Report attempt to download playlist page with given number.""" + self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum)) + + def _real_extract(self, url): + # Extract playlist id + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid url: %s' % url) + return + + # Single video case + if mobj.group(3) is not None: + self._downloader.download([mobj.group(3)]) + return + + # Download playlist pages + # prefix is 'p' as default for playlists but there are other types that need extra care + playlist_prefix = mobj.group(1) + if playlist_prefix == 'a': + playlist_access = 'artist' + else: + playlist_prefix = 'p' + playlist_access = 'view_play_list' + playlist_id = mobj.group(2) + video_ids = [] + pagenum = 1 + + while True: + self.report_download_page(playlist_id, pagenum) + url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum) + request = compat_urllib_request.Request(url) + try: + page = compat_urllib_request.urlopen(request).read().decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) + return + + # Extract video identifiers + ids_in_page = [] + for mobj in re.finditer(self._VIDEO_INDICATOR_TEMPLATE % playlist_id, page): + if mobj.group(1) not in ids_in_page: + ids_in_page.append(mobj.group(1)) + video_ids.extend(ids_in_page) + + if self._MORE_PAGES_INDICATOR not in page: + break + pagenum = pagenum + 1 + + total = len(video_ids) + + playliststart = self._downloader.params.get('playliststart', 1) - 1 + playlistend = self._downloader.params.get('playlistend', -1) + if playlistend == -1: + video_ids = video_ids[playliststart:] + else: + video_ids = video_ids[playliststart:playlistend] + + if len(video_ids) == total: + self._downloader.to_screen(u'[youtube] PL %s: Found %i videos' % (playlist_id, total)) + else: + self._downloader.to_screen(u'[youtube] PL %s: Found %i videos, downloading %i' % (playlist_id, total, len(video_ids))) + + for id in video_ids: + self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) + return class YoutubeChannelIE(InfoExtractor): - """Information Extractor for YouTube channels.""" - - _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$" - _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en' - _MORE_PAGES_INDICATOR = r'yt-uix-button-content">Next' # TODO - IE_NAME = u'youtube:channel' - - def report_download_page(self, channel_id, pagenum): - """Report attempt to download channel page with given number.""" - self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum)) - - def _real_extract(self, url): - # Extract channel id - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid url: %s' % url) - return - - # Download channel pages - channel_id = mobj.group(1) - video_ids = [] - pagenum = 1 - - while True: - self.report_download_page(channel_id, pagenum) - url = self._TEMPLATE_URL % (channel_id, pagenum) - request = urllib2.Request(url) - try: - page = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) - return - - # Extract video identifiers - ids_in_page = [] - for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page): - if mobj.group(1) not in ids_in_page: - ids_in_page.append(mobj.group(1)) - video_ids.extend(ids_in_page) - - if re.search(self._MORE_PAGES_INDICATOR, page) is None: - break - pagenum = pagenum + 1 - - for id in video_ids: - self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) - return + """Information Extractor for YouTube channels.""" + + _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$" + _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en' + _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}" + IE_NAME = u'youtube:channel' + + def report_download_page(self, channel_id, pagenum): + """Report attempt to download channel page with given number.""" + self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum)) + + def _real_extract(self, url): + # Extract channel id + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid url: %s' % url) + return + + # Download channel pages + channel_id = mobj.group(1) + video_ids = [] + pagenum = 1 + + while True: + self.report_download_page(channel_id, pagenum) + url = self._TEMPLATE_URL % (channel_id, pagenum) + request = compat_urllib_request.Request(url) + try: + page = compat_urllib_request.urlopen(request).read().decode('utf8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) + return + + # Extract video identifiers + ids_in_page = [] + for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page): + if mobj.group(1) not in ids_in_page: + ids_in_page.append(mobj.group(1)) + video_ids.extend(ids_in_page) + + if self._MORE_PAGES_INDICATOR not in page: + break + pagenum = pagenum + 1 + + self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids))) + + for id in video_ids: + self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) + return class YoutubeUserIE(InfoExtractor): - """Information Extractor for YouTube users.""" + """Information Extractor for YouTube users.""" - _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)' - _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s' - _GDATA_PAGE_SIZE = 50 - _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d' - _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]' - IE_NAME = u'youtube:user' + _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)' + _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s' + _GDATA_PAGE_SIZE = 50 + _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d' + _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]' + IE_NAME = u'youtube:user' - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) - def report_download_page(self, username, start_index): - """Report attempt to download user page.""" - self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' % - (username, start_index, start_index + self._GDATA_PAGE_SIZE)) + def report_download_page(self, username, start_index): + """Report attempt to download user page.""" + self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' % + (username, start_index, start_index + self._GDATA_PAGE_SIZE)) - def _real_extract(self, url): - # Extract username - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid url: %s' % url) - return + def _real_extract(self, url): + # Extract username + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid url: %s' % url) + return - username = mobj.group(1) + username = mobj.group(1) - # Download video ids using YouTube Data API. Result size per - # query is limited (currently to 50 videos) so we need to query - # page by page until there are no video ids - it means we got - # all of them. + # Download video ids using YouTube Data API. Result size per + # query is limited (currently to 50 videos) so we need to query + # page by page until there are no video ids - it means we got + # all of them. - video_ids = [] - pagenum = 0 + video_ids = [] + pagenum = 0 - while True: - start_index = pagenum * self._GDATA_PAGE_SIZE + 1 - self.report_download_page(username, start_index) + while True: + start_index = pagenum * self._GDATA_PAGE_SIZE + 1 + self.report_download_page(username, start_index) - request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)) + request = compat_urllib_request.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)) - try: - page = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) - return + try: + page = compat_urllib_request.urlopen(request).read().decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) + return - # Extract video identifiers - ids_in_page = [] + # Extract video identifiers + ids_in_page = [] - for mobj in re.finditer(self._VIDEO_INDICATOR, page): - if mobj.group(1) not in ids_in_page: - ids_in_page.append(mobj.group(1)) + for mobj in re.finditer(self._VIDEO_INDICATOR, page): + if mobj.group(1) not in ids_in_page: + ids_in_page.append(mobj.group(1)) - video_ids.extend(ids_in_page) + video_ids.extend(ids_in_page) - # A little optimization - if current page is not - # "full", ie. does not contain PAGE_SIZE video ids then - # we can assume that this page is the last one - there - # are no more ids on further pages - no need to query - # again. + # A little optimization - if current page is not + # "full", ie. does not contain PAGE_SIZE video ids then + # we can assume that this page is the last one - there + # are no more ids on further pages - no need to query + # again. - if len(ids_in_page) < self._GDATA_PAGE_SIZE: - break + if len(ids_in_page) < self._GDATA_PAGE_SIZE: + break - pagenum += 1 + pagenum += 1 - all_ids_count = len(video_ids) - playliststart = self._downloader.params.get('playliststart', 1) - 1 - playlistend = self._downloader.params.get('playlistend', -1) + all_ids_count = len(video_ids) + playliststart = self._downloader.params.get('playliststart', 1) - 1 + playlistend = self._downloader.params.get('playlistend', -1) - if playlistend == -1: - video_ids = video_ids[playliststart:] - else: - video_ids = video_ids[playliststart:playlistend] + if playlistend == -1: + video_ids = video_ids[playliststart:] + else: + video_ids = video_ids[playliststart:playlistend] - self._downloader.to_screen(u"[youtube] user %s: Collected %d video ids (downloading %d of them)" % - (username, all_ids_count, len(video_ids))) + self._downloader.to_screen(u"[youtube] user %s: Collected %d video ids (downloading %d of them)" % + (username, all_ids_count, len(video_ids))) - for video_id in video_ids: - self._downloader.download(['http://www.youtube.com/watch?v=%s' % video_id]) + for video_id in video_ids: + self._downloader.download(['http://www.youtube.com/watch?v=%s' % video_id]) class BlipTVUserIE(InfoExtractor): - """Information Extractor for blip.tv users.""" + """Information Extractor for blip.tv users.""" - _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$' - _PAGE_SIZE = 12 - IE_NAME = u'blip.tv:user' + _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$' + _PAGE_SIZE = 12 + IE_NAME = u'blip.tv:user' - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) - def report_download_page(self, username, pagenum): - """Report attempt to download user page.""" - self._downloader.to_screen(u'[%s] user %s: Downloading video ids from page %d' % - (self.IE_NAME, username, pagenum)) + def report_download_page(self, username, pagenum): + """Report attempt to download user page.""" + self._downloader.to_screen(u'[%s] user %s: Downloading video ids from page %d' % + (self.IE_NAME, username, pagenum)) - def _real_extract(self, url): - # Extract username - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid url: %s' % url) - return + def _real_extract(self, url): + # Extract username + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid url: %s' % url) + return - username = mobj.group(1) + username = mobj.group(1) - page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1' + page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1' - request = urllib2.Request(url) + request = compat_urllib_request.Request(url) - try: - page = urllib2.urlopen(request).read().decode('utf-8') - mobj = re.search(r'data-users-id="([^"]+)"', page) - page_base = page_base % mobj.group(1) - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) - return + try: + page = compat_urllib_request.urlopen(request).read().decode('utf-8') + mobj = re.search(r'data-users-id="([^"]+)"', page) + page_base = page_base % mobj.group(1) + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) + return - # Download video ids using BlipTV Ajax calls. Result size per - # query is limited (currently to 12 videos) so we need to query - # page by page until there are no video ids - it means we got - # all of them. + # Download video ids using BlipTV Ajax calls. Result size per + # query is limited (currently to 12 videos) so we need to query + # page by page until there are no video ids - it means we got + # all of them. - video_ids = [] - pagenum = 1 + video_ids = [] + pagenum = 1 - while True: - self.report_download_page(username, pagenum) + while True: + self.report_download_page(username, pagenum) - request = urllib2.Request( page_base + "&page=" + str(pagenum) ) + request = compat_urllib_request.Request( page_base + "&page=" + str(pagenum) ) - try: - page = urllib2.urlopen(request).read().decode('utf-8') - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) - return + try: + page = compat_urllib_request.urlopen(request).read().decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + return - # Extract video identifiers - ids_in_page = [] + # Extract video identifiers + ids_in_page = [] - for mobj in re.finditer(r'href="/([^"]+)"', page): - if mobj.group(1) not in ids_in_page: - ids_in_page.append(unescapeHTML(mobj.group(1))) + for mobj in re.finditer(r'href="/([^"]+)"', page): + if mobj.group(1) not in ids_in_page: + ids_in_page.append(unescapeHTML(mobj.group(1))) - video_ids.extend(ids_in_page) + video_ids.extend(ids_in_page) - # A little optimization - if current page is not - # "full", ie. does not contain PAGE_SIZE video ids then - # we can assume that this page is the last one - there - # are no more ids on further pages - no need to query - # again. + # A little optimization - if current page is not + # "full", ie. does not contain PAGE_SIZE video ids then + # we can assume that this page is the last one - there + # are no more ids on further pages - no need to query + # again. - if len(ids_in_page) < self._PAGE_SIZE: - break + if len(ids_in_page) < self._PAGE_SIZE: + break - pagenum += 1 + pagenum += 1 - all_ids_count = len(video_ids) - playliststart = self._downloader.params.get('playliststart', 1) - 1 - playlistend = self._downloader.params.get('playlistend', -1) + all_ids_count = len(video_ids) + playliststart = self._downloader.params.get('playliststart', 1) - 1 + playlistend = self._downloader.params.get('playlistend', -1) - if playlistend == -1: - video_ids = video_ids[playliststart:] - else: - video_ids = video_ids[playliststart:playlistend] + if playlistend == -1: + video_ids = video_ids[playliststart:] + else: + video_ids = video_ids[playliststart:playlistend] - self._downloader.to_screen(u"[%s] user %s: Collected %d video ids (downloading %d of them)" % - (self.IE_NAME, username, all_ids_count, len(video_ids))) + self._downloader.to_screen(u"[%s] user %s: Collected %d video ids (downloading %d of them)" % + (self.IE_NAME, username, all_ids_count, len(video_ids))) - for video_id in video_ids: - self._downloader.download([u'http://blip.tv/'+video_id]) + for video_id in video_ids: + self._downloader.download([u'http://blip.tv/'+video_id]) class DepositFilesIE(InfoExtractor): - """Information extractor for depositfiles.com""" - - _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)' - IE_NAME = u'DepositFiles' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, file_id): - """Report webpage download.""" - self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id) - - def report_extraction(self, file_id): - """Report information extraction.""" - self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id) - - def _real_extract(self, url): - file_id = url.split('/')[-1] - # Rebuild url in english locale - url = 'http://depositfiles.com/en/files/' + file_id - - # Retrieve file webpage with 'Free download' button pressed - free_download_indication = { 'gateway_result' : '1' } - request = urllib2.Request(url, urllib.urlencode(free_download_indication)) - try: - self.report_download_webpage(file_id) - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err)) - return - - # Search for the real file URL - mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage) - if (mobj is None) or (mobj.group(1) is None): - # Try to figure out reason of the error. - mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL) - if (mobj is not None) and (mobj.group(1) is not None): - restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip() - self._downloader.trouble(u'ERROR: %s' % restriction_message) - else: - self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url) - return - - file_url = mobj.group(1) - file_extension = os.path.splitext(file_url)[1][1:] - - # Search for file title - mobj = re.search(r'<b title="(.*?)">', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') - return - file_title = mobj.group(1).decode('utf-8') - - return [{ - 'id': file_id.decode('utf-8'), - 'url': file_url.decode('utf-8'), - 'uploader': u'NA', - 'upload_date': u'NA', - 'title': file_title, - 'ext': file_extension.decode('utf-8'), - 'format': u'NA', - 'player_url': None, - }] + """Information extractor for depositfiles.com""" + + _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)' + + def report_download_webpage(self, file_id): + """Report webpage download.""" + self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id) + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id) + + def _real_extract(self, url): + file_id = url.split('/')[-1] + # Rebuild url in english locale + url = 'http://depositfiles.com/en/files/' + file_id + + # Retrieve file webpage with 'Free download' button pressed + free_download_indication = { 'gateway_result' : '1' } + request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication)) + try: + self.report_download_webpage(file_id) + webpage = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % compat_str(err)) + return + + # Search for the real file URL + mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage) + if (mobj is None) or (mobj.group(1) is None): + # Try to figure out reason of the error. + mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL) + if (mobj is not None) and (mobj.group(1) is not None): + restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip() + self._downloader.trouble(u'ERROR: %s' % restriction_message) + else: + self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url) + return + + file_url = mobj.group(1) + file_extension = os.path.splitext(file_url)[1][1:] + + # Search for file title + mobj = re.search(r'<b title="(.*?)">', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + file_title = mobj.group(1).decode('utf-8') + + return [{ + 'id': file_id.decode('utf-8'), + 'url': file_url.decode('utf-8'), + 'uploader': None, + 'upload_date': None, + 'title': file_title, + 'ext': file_extension.decode('utf-8'), + }] class FacebookIE(InfoExtractor): - """Information Extractor for Facebook""" - - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)' - _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&' - _NETRC_MACHINE = 'facebook' - _available_formats = ['video', 'highqual', 'lowqual'] - _video_extensions = { - 'video': 'mp4', - 'highqual': 'mp4', - 'lowqual': 'mp4', - } - IE_NAME = u'facebook' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def _reporter(self, message): - """Add header and report message.""" - self._downloader.to_screen(u'[facebook] %s' % message) - - def report_login(self): - """Report attempt to log in.""" - self._reporter(u'Logging in') - - def report_video_webpage_download(self, video_id): - """Report attempt to download video webpage.""" - self._reporter(u'%s: Downloading video webpage' % video_id) - - def report_information_extraction(self, video_id): - """Report attempt to extract video information.""" - self._reporter(u'%s: Extracting video information' % video_id) - - def _parse_page(self, video_webpage): - """Extract video information from page""" - # General data - data = {'title': r'\("video_title", "(.*?)"\)', - 'description': r'<div class="datawrap">(.*?)</div>', - 'owner': r'\("video_owner_name", "(.*?)"\)', - 'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)', - } - video_info = {} - for piece in data.keys(): - mobj = re.search(data[piece], video_webpage) - if mobj is not None: - video_info[piece] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape")) - - # Video urls - video_urls = {} - for fmt in self._available_formats: - mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage) - if mobj is not None: - # URL is in a Javascript segment inside an escaped Unicode format within - # the generally utf-8 page - video_urls[fmt] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape")) - video_info['video_urls'] = video_urls - - return video_info - - def _real_initialize(self): - if self._downloader is None: - return - - useremail = None - password = None - downloader_params = self._downloader.params - - # Attempt to use provided username and password or .netrc data - if downloader_params.get('username', None) is not None: - useremail = downloader_params['username'] - password = downloader_params['password'] - elif downloader_params.get('usenetrc', False): - try: - info = netrc.netrc().authenticators(self._NETRC_MACHINE) - if info is not None: - useremail = info[0] - password = info[2] - else: - raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) - except (IOError, netrc.NetrcParseError), err: - self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) - return - - if useremail is None: - return - - # Log in - login_form = { - 'email': useremail, - 'pass': password, - 'login': 'Log+In' - } - request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form)) - try: - self.report_login() - login_results = urllib2.urlopen(request).read() - if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None: - self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') - return - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) - return - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - video_id = mobj.group('ID') - - # Get video webpage - self.report_video_webpage_download(video_id) - request = urllib2.Request('https://www.facebook.com/video/video.php?v=%s' % video_id) - try: - page = urllib2.urlopen(request) - video_webpage = page.read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) - return - - # Start extracting information - self.report_information_extraction(video_id) - - # Extract information - video_info = self._parse_page(video_webpage) - - # uploader - if 'owner' not in video_info: - self._downloader.trouble(u'ERROR: unable to extract uploader nickname') - return - video_uploader = video_info['owner'] - - # title - if 'title' not in video_info: - self._downloader.trouble(u'ERROR: unable to extract video title') - return - video_title = video_info['title'] - video_title = video_title.decode('utf-8') - - # thumbnail image - if 'thumbnail' not in video_info: - self._downloader.trouble(u'WARNING: unable to extract video thumbnail') - video_thumbnail = '' - else: - video_thumbnail = video_info['thumbnail'] - - # upload date - upload_date = u'NA' - if 'upload_date' in video_info: - upload_time = video_info['upload_date'] - timetuple = email.utils.parsedate_tz(upload_time) - if timetuple is not None: - try: - upload_date = time.strftime('%Y%m%d', timetuple[0:9]) - except: - pass - - # description - video_description = video_info.get('description', 'No description available.') - - url_map = video_info['video_urls'] - if len(url_map.keys()) > 0: - # Decide which formats to download - req_format = self._downloader.params.get('format', None) - format_limit = self._downloader.params.get('format_limit', None) - - if format_limit is not None and format_limit in self._available_formats: - format_list = self._available_formats[self._available_formats.index(format_limit):] - else: - format_list = self._available_formats - existing_formats = [x for x in format_list if x in url_map] - if len(existing_formats) == 0: - self._downloader.trouble(u'ERROR: no known formats available for video') - return - if req_format is None: - video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality - elif req_format == 'worst': - video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality - elif req_format == '-1': - video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats - else: - # Specific format - if req_format not in url_map: - self._downloader.trouble(u'ERROR: requested format not available') - return - video_url_list = [(req_format, url_map[req_format])] # Specific format - - results = [] - for format_param, video_real_url in video_url_list: - # Extension - video_extension = self._video_extensions.get(format_param, 'mp4') - - results.append({ - 'id': video_id.decode('utf-8'), - 'url': video_real_url.decode('utf-8'), - 'uploader': video_uploader.decode('utf-8'), - 'upload_date': upload_date, - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), - 'thumbnail': video_thumbnail.decode('utf-8'), - 'description': video_description.decode('utf-8'), - 'player_url': None, - }) - return results + """Information Extractor for Facebook""" + + _WORKING = False + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)' + _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&' + _NETRC_MACHINE = 'facebook' + _available_formats = ['video', 'highqual', 'lowqual'] + _video_extensions = { + 'video': 'mp4', + 'highqual': 'mp4', + 'lowqual': 'mp4', + } + IE_NAME = u'facebook' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def _reporter(self, message): + """Add header and report message.""" + self._downloader.to_screen(u'[facebook] %s' % message) + + def report_login(self): + """Report attempt to log in.""" + self._reporter(u'Logging in') + + def report_video_webpage_download(self, video_id): + """Report attempt to download video webpage.""" + self._reporter(u'%s: Downloading video webpage' % video_id) + + def report_information_extraction(self, video_id): + """Report attempt to extract video information.""" + self._reporter(u'%s: Extracting video information' % video_id) + + def _parse_page(self, video_webpage): + """Extract video information from page""" + # General data + data = {'title': r'\("video_title", "(.*?)"\)', + 'description': r'<div class="datawrap">(.*?)</div>', + 'owner': r'\("video_owner_name", "(.*?)"\)', + 'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)', + } + video_info = {} + for piece in data.keys(): + mobj = re.search(data[piece], video_webpage) + if mobj is not None: + video_info[piece] = compat_urllib_parse.unquote_plus(mobj.group(1).decode("unicode_escape")) + + # Video urls + video_urls = {} + for fmt in self._available_formats: + mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage) + if mobj is not None: + # URL is in a Javascript segment inside an escaped Unicode format within + # the generally utf-8 page + video_urls[fmt] = compat_urllib_parse.unquote_plus(mobj.group(1).decode("unicode_escape")) + video_info['video_urls'] = video_urls + + return video_info + + def _real_initialize(self): + if self._downloader is None: + return + + useremail = None + password = None + downloader_params = self._downloader.params + + # Attempt to use provided username and password or .netrc data + if downloader_params.get('username', None) is not None: + useremail = downloader_params['username'] + password = downloader_params['password'] + elif downloader_params.get('usenetrc', False): + try: + info = netrc.netrc().authenticators(self._NETRC_MACHINE) + if info is not None: + useremail = info[0] + password = info[2] + else: + raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) + except (IOError, netrc.NetrcParseError) as err: + self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err)) + return + + if useremail is None: + return + + # Log in + login_form = { + 'email': useremail, + 'pass': password, + 'login': 'Log+In' + } + request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) + try: + self.report_login() + login_results = compat_urllib_request.urlopen(request).read() + if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None: + self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') + return + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err)) + return + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group('ID') + + # Get video webpage + self.report_video_webpage_download(video_id) + request = compat_urllib_request.Request('https://www.facebook.com/video/video.php?v=%s' % video_id) + try: + page = compat_urllib_request.urlopen(request) + video_webpage = page.read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) + return + + # Start extracting information + self.report_information_extraction(video_id) + + # Extract information + video_info = self._parse_page(video_webpage) + + # uploader + if 'owner' not in video_info: + self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + return + video_uploader = video_info['owner'] + + # title + if 'title' not in video_info: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = video_info['title'] + video_title = video_title.decode('utf-8') + + # thumbnail image + if 'thumbnail' not in video_info: + self._downloader.trouble(u'WARNING: unable to extract video thumbnail') + video_thumbnail = '' + else: + video_thumbnail = video_info['thumbnail'] + + # upload date + upload_date = None + if 'upload_date' in video_info: + upload_time = video_info['upload_date'] + timetuple = email.utils.parsedate_tz(upload_time) + if timetuple is not None: + try: + upload_date = time.strftime('%Y%m%d', timetuple[0:9]) + except: + pass + + # description + video_description = video_info.get('description', 'No description available.') + + url_map = video_info['video_urls'] + if url_map: + # Decide which formats to download + req_format = self._downloader.params.get('format', None) + format_limit = self._downloader.params.get('format_limit', None) + + if format_limit is not None and format_limit in self._available_formats: + format_list = self._available_formats[self._available_formats.index(format_limit):] + else: + format_list = self._available_formats + existing_formats = [x for x in format_list if x in url_map] + if len(existing_formats) == 0: + self._downloader.trouble(u'ERROR: no known formats available for video') + return + if req_format is None: + video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality + elif req_format == 'worst': + video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality + elif req_format == '-1': + video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats + else: + # Specific format + if req_format not in url_map: + self._downloader.trouble(u'ERROR: requested format not available') + return + video_url_list = [(req_format, url_map[req_format])] # Specific format + + results = [] + for format_param, video_real_url in video_url_list: + # Extension + video_extension = self._video_extensions.get(format_param, 'mp4') + + results.append({ + 'id': video_id.decode('utf-8'), + 'url': video_real_url.decode('utf-8'), + 'uploader': video_uploader.decode('utf-8'), + 'upload_date': upload_date, + 'title': video_title, + 'ext': video_extension.decode('utf-8'), + 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), + 'thumbnail': video_thumbnail.decode('utf-8'), + 'description': video_description.decode('utf-8'), + }) + return results class BlipTVIE(InfoExtractor): - """Information extractor for blip.tv""" - - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$' - _URL_EXT = r'^.*\.([a-z0-9]+)$' - IE_NAME = u'blip.tv' - - def report_extraction(self, file_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) - - def report_direct_download(self, title): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title)) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - - if '?' in url: - cchar = '&' - else: - cchar = '?' - json_url = url + cchar + 'skin=json&version=2&no_wrap=1' - request = urllib2.Request(json_url.encode('utf-8')) - self.report_extraction(mobj.group(1)) - info = None - try: - urlh = urllib2.urlopen(request) - if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download - basename = url.split('/')[-1] - title,ext = os.path.splitext(basename) - title = title.decode('UTF-8') - ext = ext.replace('.', '') - self.report_direct_download(title) - info = { - 'id': title, - 'url': url, - 'title': title, - 'ext': ext, - 'urlhandle': urlh - } - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) - return - if info is None: # Regular URL - try: - json_code = urlh.read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % str(err)) - return - - try: - json_data = json.loads(json_code) - if 'Post' in json_data: - data = json_data['Post'] - else: - data = json_data - - upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d') - video_url = data['media']['url'] - umobj = re.match(self._URL_EXT, video_url) - if umobj is None: - raise ValueError('Can not determine filename extension') - ext = umobj.group(1) - - info = { - 'id': data['item_id'], - 'url': video_url, - 'uploader': data['display_name'], - 'upload_date': upload_date, - 'title': data['title'], - 'ext': ext, - 'format': data['media']['mimeType'], - 'thumbnail': data['thumbnailUrl'], - 'description': data['description'], - 'player_url': data['embedUrl'] - } - except (ValueError,KeyError), err: - self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err)) - return - - std_headers['User-Agent'] = 'iTunes/10.6.1' - return [info] + """Information extractor for blip.tv""" + + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$' + _URL_EXT = r'^.*\.([a-z0-9]+)$' + IE_NAME = u'blip.tv' + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) + + def report_direct_download(self, title): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title)) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + if '?' in url: + cchar = '&' + else: + cchar = '?' + json_url = url + cchar + 'skin=json&version=2&no_wrap=1' + request = compat_urllib_request.Request(json_url) + self.report_extraction(mobj.group(1)) + info = None + try: + urlh = compat_urllib_request.urlopen(request) + if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download + basename = url.split('/')[-1] + title,ext = os.path.splitext(basename) + title = title.decode('UTF-8') + ext = ext.replace('.', '') + self.report_direct_download(title) + info = { + 'id': title, + 'url': url, + 'uploader': None, + 'upload_date': None, + 'title': title, + 'ext': ext, + 'urlhandle': urlh + } + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) + return + if info is None: # Regular URL + try: + json_code_bytes = urlh.read() + json_code = json_code_bytes.decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % compat_str(err)) + return + + try: + json_data = json.loads(json_code) + if 'Post' in json_data: + data = json_data['Post'] + else: + data = json_data + + upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d') + video_url = data['media']['url'] + umobj = re.match(self._URL_EXT, video_url) + if umobj is None: + raise ValueError('Can not determine filename extension') + ext = umobj.group(1) + + info = { + 'id': data['item_id'], + 'url': video_url, + 'uploader': data['display_name'], + 'upload_date': upload_date, + 'title': data['title'], + 'ext': ext, + 'format': data['media']['mimeType'], + 'thumbnail': data['thumbnailUrl'], + 'description': data['description'], + 'player_url': data['embedUrl'] + } + except (ValueError,KeyError) as err: + self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err)) + return + + std_headers['User-Agent'] = 'iTunes/10.6.1' + return [info] class MyVideoIE(InfoExtractor): - """Information Extractor for myvideo.de.""" - - _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*' - IE_NAME = u'myvideo' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id) - - def _real_extract(self,url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._download.trouble(u'ERROR: invalid URL: %s' % url) - return - - video_id = mobj.group(1) - - # Get video webpage - request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id) - try: - self.report_download_webpage(video_id) - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) - return - - self.report_extraction(video_id) - mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/[^.]+\.jpg\' />', - webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - video_url = mobj.group(1) + ('/%s.flv' % video_id) - - mobj = re.search('<title>([^<]+)</title>', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') - return - - video_title = mobj.group(1) - - return [{ - 'id': video_id, - 'url': video_url, - 'uploader': u'NA', - 'upload_date': u'NA', - 'title': video_title, - 'ext': u'flv', - 'format': u'NA', - 'player_url': None, - }] + """Information Extractor for myvideo.de.""" + + _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*' + IE_NAME = u'myvideo' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id) + + def _real_extract(self,url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._download.trouble(u'ERROR: invalid URL: %s' % url) + return + + video_id = mobj.group(1) + + # Get video webpage + webpage_url = 'http://www.myvideo.de/watch/%s' % video_id + webpage = self._download_webpage(webpage_url, video_id) + + self.report_extraction(video_id) + mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/[^.]+\.jpg\' />', + webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + video_url = mobj.group(1) + ('/%s.flv' % video_id) + + mobj = re.search('<title>([^<]+)</title>', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + + video_title = mobj.group(1) + + return [{ + 'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': None, + 'title': video_title, + 'ext': u'flv', + }] class ComedyCentralIE(InfoExtractor): - """Information extractor for The Daily Show and Colbert Report """ - - _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$' - IE_NAME = u'comedycentral' - - def report_extraction(self, episode_id): - self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) - - def report_config_download(self, episode_id): - self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id) - - def report_index_download(self, episode_id): - self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id) - - def report_player_url(self, episode_id): - self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - - if mobj.group('shortname'): - if mobj.group('shortname') in ('tds', 'thedailyshow'): - url = u'http://www.thedailyshow.com/full-episodes/' - else: - url = u'http://www.colbertnation.com/full-episodes/' - mobj = re.match(self._VALID_URL, url) - assert mobj is not None - - dlNewest = not mobj.group('episode') - if dlNewest: - epTitle = mobj.group('showname') - else: - epTitle = mobj.group('episode') - - req = urllib2.Request(url) - self.report_extraction(epTitle) - try: - htmlHandle = urllib2.urlopen(req) - html = htmlHandle.read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err)) - return - if dlNewest: - url = htmlHandle.geturl() - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url) - return - if mobj.group('episode') == '': - self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url) - return - epTitle = mobj.group('episode') - - mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"', html) - if len(mMovieParams) == 0: - self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url) - return - - playerUrl_raw = mMovieParams[0][0] - self.report_player_url(epTitle) - try: - urlHandle = urllib2.urlopen(playerUrl_raw) - playerUrl = urlHandle.geturl() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to find out player URL: ' + unicode(err)) - return - - uri = mMovieParams[0][1] - indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + urllib.urlencode({'uri': uri}) - self.report_index_download(epTitle) - try: - indexXml = urllib2.urlopen(indexUrl).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download episode index: ' + unicode(err)) - return - - results = [] - - idoc = xml.etree.ElementTree.fromstring(indexXml) - itemEls = idoc.findall('.//item') - for itemEl in itemEls: - mediaId = itemEl.findall('./guid')[0].text - shortMediaId = mediaId.split(':')[-1] - showId = mediaId.split(':')[-2].replace('.com', '') - officialTitle = itemEl.findall('./title')[0].text - officialDate = itemEl.findall('./pubDate')[0].text - - configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' + - urllib.urlencode({'uri': mediaId})) - configReq = urllib2.Request(configUrl) - self.report_config_download(epTitle) - try: - configXml = urllib2.urlopen(configReq).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err)) - return - - cdoc = xml.etree.ElementTree.fromstring(configXml) - turls = [] - for rendition in cdoc.findall('.//rendition'): - finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text) - turls.append(finfo) - - if len(turls) == 0: - self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found') - continue - - # For now, just pick the highest bitrate - format,video_url = turls[-1] - - effTitle = showId + u'-' + epTitle - info = { - 'id': shortMediaId, - 'url': video_url, - 'uploader': showId, - 'upload_date': officialDate, - 'title': effTitle, - 'ext': 'mp4', - 'format': format, - 'thumbnail': None, - 'description': officialTitle, - 'player_url': playerUrl - } - - results.append(info) - - return results + """Information extractor for The Daily Show and Colbert Report """ + + # urls can be abbreviations like :thedailyshow or :colbert + # urls for episodes like: + # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day + # or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news + # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524 + _VALID_URL = r"""^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport) + |(https?://)?(www\.)? + (?P<showname>thedailyshow|colbertnation)\.com/ + (full-episodes/(?P<episode>.*)| + (?P<clip> + (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?)) + |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))))) + $""" + IE_NAME = u'comedycentral' + + _available_formats = ['3500', '2200', '1700', '1200', '750', '400'] + + _video_extensions = { + '3500': 'mp4', + '2200': 'mp4', + '1700': 'mp4', + '1200': 'mp4', + '750': 'mp4', + '400': 'mp4', + } + _video_dimensions = { + '3500': '1280x720', + '2200': '960x540', + '1700': '768x432', + '1200': '640x360', + '750': '512x288', + '400': '384x216', + } + + def suitable(self, url): + """Receives a URL and returns True if suitable for this IE.""" + return re.match(self._VALID_URL, url, re.VERBOSE) is not None + + def report_extraction(self, episode_id): + self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) + + def report_config_download(self, episode_id): + self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id) + + def report_index_download(self, episode_id): + self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id) + + def report_player_url(self, episode_id): + self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id) + + + def _print_formats(self, formats): + print('Available formats:') + for x in formats: + print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???'))) + + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url, re.VERBOSE) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + if mobj.group('shortname'): + if mobj.group('shortname') in ('tds', 'thedailyshow'): + url = u'http://www.thedailyshow.com/full-episodes/' + else: + url = u'http://www.colbertnation.com/full-episodes/' + mobj = re.match(self._VALID_URL, url, re.VERBOSE) + assert mobj is not None + + if mobj.group('clip'): + if mobj.group('showname') == 'thedailyshow': + epTitle = mobj.group('tdstitle') + else: + epTitle = mobj.group('cntitle') + dlNewest = False + else: + dlNewest = not mobj.group('episode') + if dlNewest: + epTitle = mobj.group('showname') + else: + epTitle = mobj.group('episode') + + req = compat_urllib_request.Request(url) + self.report_extraction(epTitle) + try: + htmlHandle = compat_urllib_request.urlopen(req) + html = htmlHandle.read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) + return + if dlNewest: + url = htmlHandle.geturl() + mobj = re.match(self._VALID_URL, url, re.VERBOSE) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url) + return + if mobj.group('episode') == '': + self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url) + return + epTitle = mobj.group('episode') + + mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', html) + + if len(mMovieParams) == 0: + # The Colbert Report embeds the information in a without + # a URL prefix; so extract the alternate reference + # and then add the URL prefix manually. + + altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', html) + if len(altMovieParams) == 0: + self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url) + return + else: + mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])] + + playerUrl_raw = mMovieParams[0][0] + self.report_player_url(epTitle) + try: + urlHandle = compat_urllib_request.urlopen(playerUrl_raw) + playerUrl = urlHandle.geturl() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to find out player URL: ' + compat_str(err)) + return + + uri = mMovieParams[0][1] + indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri}) + self.report_index_download(epTitle) + try: + indexXml = compat_urllib_request.urlopen(indexUrl).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download episode index: ' + compat_str(err)) + return + + results = [] + + idoc = xml.etree.ElementTree.fromstring(indexXml) + itemEls = idoc.findall('.//item') + for itemEl in itemEls: + mediaId = itemEl.findall('./guid')[0].text + shortMediaId = mediaId.split(':')[-1] + showId = mediaId.split(':')[-2].replace('.com', '') + officialTitle = itemEl.findall('./title')[0].text + officialDate = itemEl.findall('./pubDate')[0].text + + configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' + + compat_urllib_parse.urlencode({'uri': mediaId})) + configReq = compat_urllib_request.Request(configUrl) + self.report_config_download(epTitle) + try: + configXml = compat_urllib_request.urlopen(configReq).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) + return + + cdoc = xml.etree.ElementTree.fromstring(configXml) + turls = [] + for rendition in cdoc.findall('.//rendition'): + finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text) + turls.append(finfo) + + if len(turls) == 0: + self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found') + continue + + if self._downloader.params.get('listformats', None): + self._print_formats([i[0] for i in turls]) + return + + # For now, just pick the highest bitrate + format,video_url = turls[-1] + + # Get the format arg from the arg stream + req_format = self._downloader.params.get('format', None) + + # Select format if we can find one + for f,v in turls: + if f == req_format: + format, video_url = f, v + break + + # Patch to download from alternative CDN, which does not + # break on current RTMPDump builds + broken_cdn = "rtmpe://viacomccstrmfs.fplive.net/viacomccstrm/gsp.comedystor/" + better_cdn = "rtmpe://cp10740.edgefcs.net/ondemand/mtvnorigin/gsp.comedystor/" + + if video_url.startswith(broken_cdn): + video_url = video_url.replace(broken_cdn, better_cdn) + + effTitle = showId + u'-' + epTitle + info = { + 'id': shortMediaId, + 'url': video_url, + 'uploader': showId, + 'upload_date': officialDate, + 'title': effTitle, + 'ext': 'mp4', + 'format': format, + 'thumbnail': None, + 'description': officialTitle, + 'player_url': None #playerUrl + } + + results.append(info) + + return results class EscapistIE(InfoExtractor): - """Information extractor for The Escapist """ - - _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$' - IE_NAME = u'escapist' - - def report_extraction(self, showName): - self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName) - - def report_config_download(self, showName): - self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - showName = mobj.group('showname') - videoId = mobj.group('episode') - - self.report_extraction(showName) - try: - webPage = urllib2.urlopen(url) - webPageBytes = webPage.read() - m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type']) - webPage = webPageBytes.decode(m.group(1) if m else 'utf-8') - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err)) - return - - descMatch = re.search('<meta name="description" content="([^"]*)"', webPage) - description = unescapeHTML(descMatch.group(1)) - imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage) - imgUrl = unescapeHTML(imgMatch.group(1)) - playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage) - playerUrl = unescapeHTML(playerUrlMatch.group(1)) - configUrlMatch = re.search('config=(.*)$', playerUrl) - configUrl = urllib2.unquote(configUrlMatch.group(1)) - - self.report_config_download(showName) - try: - configJSON = urllib2.urlopen(configUrl).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download configuration: ' + unicode(err)) - return - - # Technically, it's JavaScript, not JSON - configJSON = configJSON.replace("'", '"') - - try: - config = json.loads(configJSON) - except (ValueError,), err: - self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + unicode(err)) - return - - playlist = config['playlist'] - videoUrl = playlist[1]['url'] - - info = { - 'id': videoId, - 'url': videoUrl, - 'uploader': showName, - 'upload_date': None, - 'title': showName, - 'ext': 'flv', - 'format': 'flv', - 'thumbnail': imgUrl, - 'description': description, - 'player_url': playerUrl, - } - - return [info] + """Information extractor for The Escapist """ + + _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$' + IE_NAME = u'escapist' + + def report_extraction(self, showName): + self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName) + + def report_config_download(self, showName): + self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + showName = mobj.group('showname') + videoId = mobj.group('episode') + + self.report_extraction(showName) + try: + webPage = compat_urllib_request.urlopen(url) + webPageBytes = webPage.read() + m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type']) + webPage = webPageBytes.decode(m.group(1) if m else 'utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download webpage: ' + compat_str(err)) + return + + descMatch = re.search('<meta name="description" content="([^"]*)"', webPage) + description = unescapeHTML(descMatch.group(1)) + imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage) + imgUrl = unescapeHTML(imgMatch.group(1)) + playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage) + playerUrl = unescapeHTML(playerUrlMatch.group(1)) + configUrlMatch = re.search('config=(.*)$', playerUrl) + configUrl = compat_urllib_parse.unquote(configUrlMatch.group(1)) + + self.report_config_download(showName) + try: + configJSON = compat_urllib_request.urlopen(configUrl) + m = re.match(r'text/html; charset="?([^"]+)"?', configJSON.headers['Content-Type']) + configJSON = configJSON.read().decode(m.group(1) if m else 'utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download configuration: ' + compat_str(err)) + return + + # Technically, it's JavaScript, not JSON + configJSON = configJSON.replace("'", '"') + + try: + config = json.loads(configJSON) + except (ValueError,) as err: + self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + compat_str(err)) + return + + playlist = config['playlist'] + videoUrl = playlist[1]['url'] + + info = { + 'id': videoId, + 'url': videoUrl, + 'uploader': showName, + 'upload_date': None, + 'title': showName, + 'ext': 'flv', + 'thumbnail': imgUrl, + 'description': description, + 'player_url': playerUrl, + } + + return [info] class CollegeHumorIE(InfoExtractor): - """Information extractor for collegehumor.com""" - - _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$' - IE_NAME = u'collegehumor' - - def report_webpage(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - video_id = mobj.group('videoid') - - self.report_webpage(video_id) - request = urllib2.Request(url) - try: - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) - return - - m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage) - if m is None: - self._downloader.trouble(u'ERROR: Cannot extract internal video ID') - return - internal_video_id = m.group('internalvideoid') - - info = { - 'id': video_id, - 'internal_id': internal_video_id, - } - - self.report_extraction(video_id) - xmlUrl = 'http://www.collegehumor.com/moogaloop/video:' + internal_video_id - try: - metaXml = urllib2.urlopen(xmlUrl).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % str(err)) - return - - mdoc = xml.etree.ElementTree.fromstring(metaXml) - try: - videoNode = mdoc.findall('./video')[0] - info['description'] = videoNode.findall('./description')[0].text - info['title'] = videoNode.findall('./caption')[0].text - info['url'] = videoNode.findall('./file')[0].text - info['thumbnail'] = videoNode.findall('./thumbnail')[0].text - info['ext'] = info['url'].rpartition('.')[2] - info['format'] = info['ext'] - except IndexError: - self._downloader.trouble(u'\nERROR: Invalid metadata XML file') - return - - return [info] + """Information extractor for collegehumor.com""" + + _WORKING = False + _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$' + IE_NAME = u'collegehumor' + + def report_manifest(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Downloading XML manifest' % (self.IE_NAME, video_id)) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group('videoid') + + info = { + 'id': video_id, + 'uploader': None, + 'upload_date': None, + } + + self.report_extraction(video_id) + xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id + try: + metaXml = compat_urllib_request.urlopen(xmlUrl).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err)) + return + + mdoc = xml.etree.ElementTree.fromstring(metaXml) + try: + videoNode = mdoc.findall('./video')[0] + info['description'] = videoNode.findall('./description')[0].text + info['title'] = videoNode.findall('./caption')[0].text + info['thumbnail'] = videoNode.findall('./thumbnail')[0].text + manifest_url = videoNode.findall('./file')[0].text + except IndexError: + self._downloader.trouble(u'\nERROR: Invalid metadata XML file') + return + + manifest_url += '?hdcore=2.10.3' + self.report_manifest(video_id) + try: + manifestXml = compat_urllib_request.urlopen(manifest_url).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err)) + return + + adoc = xml.etree.ElementTree.fromstring(manifestXml) + try: + media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0] + node_id = media_node.attrib['url'] + video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text + except IndexError as err: + self._downloader.trouble(u'\nERROR: Invalid manifest file') + return + + url_pr = compat_urllib_parse_urlparse(manifest_url) + url = url_pr.scheme + '://' + url_pr.netloc + '/z' + video_id[:-2] + '/' + node_id + 'Seg1-Frag1' + + info['url'] = url + info['ext'] = 'f4f' + return [info] class XVideosIE(InfoExtractor): - """Information extractor for xvideos.com""" - - _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' - IE_NAME = u'xvideos' - - def report_webpage(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) + """Information extractor for xvideos.com""" - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' + IE_NAME = u'xvideos' - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - video_id = mobj.group(1).decode('utf-8') + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) - self.report_webpage(video_id) + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group(1) - request = urllib2.Request(r'http://www.xvideos.com/video' + video_id) - try: - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) - return + webpage = self._download_webpage(url, video_id) - self.report_extraction(video_id) + self.report_extraction(video_id) - # Extract video URL - mobj = re.search(r'flv_url=(.+?)&', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video url') - return - video_url = urllib2.unquote(mobj.group(1).decode('utf-8')) + # Extract video URL + mobj = re.search(r'flv_url=(.+?)&', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video url') + return + video_url = compat_urllib_parse.unquote(mobj.group(1)) - # Extract title - mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video title') - return - video_title = mobj.group(1).decode('utf-8') + # Extract title + mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = mobj.group(1) - # Extract video thumbnail - mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video thumbnail') - return - video_thumbnail = mobj.group(0).decode('utf-8') + # Extract video thumbnail + mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = mobj.group(0) - info = { - 'id': video_id, - 'url': video_url, - 'uploader': None, - 'upload_date': None, - 'title': video_title, - 'ext': 'flv', - 'format': 'flv', - 'thumbnail': video_thumbnail, - 'description': None, - 'player_url': None, - } + info = { + 'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': None, + 'title': video_title, + 'ext': 'flv', + 'thumbnail': video_thumbnail, + 'description': None, + } - return [info] + return [info] class SoundcloudIE(InfoExtractor): - """Information extractor for soundcloud.com - To access the media, the uid of the song and a stream token - must be extracted from the page source and the script must make - a request to media.soundcloud.com/crossdomain.xml. Then - the media can be grabbed by requesting from an url composed - of the stream token and uid - """ - - _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)' - IE_NAME = u'soundcloud' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_webpage(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - - # extract uploader (which is in the url) - uploader = mobj.group(1).decode('utf-8') - # extract simple title (uploader + slug of song title) - slug_title = mobj.group(2).decode('utf-8') - simple_title = uploader + u'-' + slug_title - - self.report_webpage('%s/%s' % (uploader, slug_title)) - - request = urllib2.Request('http://soundcloud.com/%s/%s' % (uploader, slug_title)) - try: - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) - return - - self.report_extraction('%s/%s' % (uploader, slug_title)) - - # extract uid and stream token that soundcloud hands out for access - mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage) - if mobj: - video_id = mobj.group(1) - stream_token = mobj.group(2) - - # extract unsimplified title - mobj = re.search('"title":"(.*?)",', webpage) - if mobj: - title = mobj.group(1).decode('utf-8') - else: - title = simple_title - - # construct media url (with uid/token) - mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s" - mediaURL = mediaURL % (video_id, stream_token) - - # description - description = u'No description available' - mobj = re.search('track-description-value"><p>(.*?)</p>', webpage) - if mobj: - description = mobj.group(1) - - # upload date - upload_date = None - mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)</abbr></h2>", webpage) - if mobj: - try: - upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d') - except Exception, e: - self._downloader.to_stderr(str(e)) - - # for soundcloud, a request to a cross domain is required for cookies - request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers) - - return [{ - 'id': video_id.decode('utf-8'), - 'url': mediaURL, - 'uploader': uploader.decode('utf-8'), - 'upload_date': upload_date, - 'title': title, - 'ext': u'mp3', - 'format': u'NA', - 'player_url': None, - 'description': description.decode('utf-8') - }] + """Information extractor for soundcloud.com + To access the media, the uid of the song and a stream token + must be extracted from the page source and the script must make + a request to media.soundcloud.com/crossdomain.xml. Then + the media can be grabbed by requesting from an url composed + of the stream token and uid + """ + + _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)' + IE_NAME = u'soundcloud' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_resolve(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Resolving id' % (self.IE_NAME, video_id)) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Retrieving stream' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + # extract uploader (which is in the url) + uploader = mobj.group(1) + # extract simple title (uploader + slug of song title) + slug_title = mobj.group(2) + simple_title = uploader + u'-' + slug_title + + self.report_resolve('%s/%s' % (uploader, slug_title)) + + url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title) + resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28' + request = compat_urllib_request.Request(resolv_url) + try: + info_json_bytes = compat_urllib_request.urlopen(request).read() + info_json = info_json_bytes.decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) + return + + info = json.loads(info_json) + video_id = info['id'] + self.report_extraction('%s/%s' % (uploader, slug_title)) + + streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28' + request = compat_urllib_request.Request(streams_url) + try: + stream_json_bytes = compat_urllib_request.urlopen(request).read() + stream_json = stream_json_bytes.decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download stream definitions: %s' % compat_str(err)) + return + + streams = json.loads(stream_json) + mediaURL = streams['http_mp3_128_url'] + + return [{ + 'id': info['id'], + 'url': mediaURL, + 'uploader': info['user']['username'], + 'upload_date': info['created_at'], + 'title': info['title'], + 'ext': u'mp3', + 'description': info['description'], + }] class InfoQIE(InfoExtractor): - """Information extractor for infoq.com""" - - _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$' - IE_NAME = u'infoq' - - def report_webpage(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - - self.report_webpage(url) - - request = urllib2.Request(url) - try: - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) - return - - self.report_extraction(url) - - - # Extract video URL - mobj = re.search(r"jsclassref='([^']*)'", webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video url') - return - video_url = 'rtmpe://video.infoq.com/cfx/st/' + urllib2.unquote(mobj.group(1).decode('base64')) - - - # Extract title - mobj = re.search(r'contentTitle = "(.*?)";', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video title') - return - video_title = mobj.group(1).decode('utf-8') - - # Extract description - video_description = u'No description available.' - mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage) - if mobj is not None: - video_description = mobj.group(1).decode('utf-8') - - video_filename = video_url.split('/')[-1] - video_id, extension = video_filename.split('.') - - info = { - 'id': video_id, - 'url': video_url, - 'uploader': None, - 'upload_date': None, - 'title': video_title, - 'ext': extension, - 'format': extension, # Extension is always(?) mp4, but seems to be flv - 'thumbnail': None, - 'description': video_description, - 'player_url': None, - } - - return [info] + """Information extractor for infoq.com""" + _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$' + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + webpage = self._download_webpage(url, video_id=url) + self.report_extraction(url) + + # Extract video URL + mobj = re.search(r"jsclassref='([^']*)'", webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video url') + return + real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8')) + video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id + + # Extract title + mobj = re.search(r'contentTitle = "(.*?)";', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = mobj.group(1) + + # Extract description + video_description = u'No description available.' + mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage) + if mobj is not None: + video_description = mobj.group(1) + + video_filename = video_url.split('/')[-1] + video_id, extension = video_filename.split('.') + + info = { + 'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': None, + 'title': video_title, + 'ext': extension, # Extension is always(?) mp4, but seems to be flv + 'thumbnail': None, + 'description': video_description, + } + + return [info] class MixcloudIE(InfoExtractor): - """Information extractor for www.mixcloud.com""" - _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)' - IE_NAME = u'mixcloud' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_json(self, file_id): - """Report JSON download.""" - self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME) - - def report_extraction(self, file_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) - - def get_urls(self, jsonData, fmt, bitrate='best'): - """Get urls from 'audio_formats' section in json""" - file_url = None - try: - bitrate_list = jsonData[fmt] - if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list: - bitrate = max(bitrate_list) # select highest - - url_list = jsonData[fmt][bitrate] - except TypeError: # we have no bitrate info. - url_list = jsonData[fmt] - return url_list - - def check_urls(self, url_list): - """Returns 1st active url from list""" - for url in url_list: - try: - urllib2.urlopen(url) - return url - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - url = None - - return None - - def _print_formats(self, formats): - print 'Available formats:' - for fmt in formats.keys(): - for b in formats[fmt]: - try: - ext = formats[fmt][b][0] - print '%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1]) - except TypeError: # we have no bitrate info - ext = formats[fmt][0] - print '%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1]) - break - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - # extract uploader & filename from url - uploader = mobj.group(1).decode('utf-8') - file_id = uploader + "-" + mobj.group(2).decode('utf-8') - - # construct API request - file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json' - # retrieve .json file with links to files - request = urllib2.Request(file_url) - try: - self.report_download_json(file_url) - jsonData = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % str(err)) - return - - # parse JSON - json_data = json.loads(jsonData) - player_url = json_data['player_swf_url'] - formats = dict(json_data['audio_formats']) - - req_format = self._downloader.params.get('format', None) - bitrate = None - - if self._downloader.params.get('listformats', None): - self._print_formats(formats) - return - - if req_format is None or req_format == 'best': - for format_param in formats.keys(): - url_list = self.get_urls(formats, format_param) - # check urls - file_url = self.check_urls(url_list) - if file_url is not None: - break # got it! - else: - if req_format not in formats.keys(): - self._downloader.trouble(u'ERROR: format is not available') - return - - url_list = self.get_urls(formats, req_format) - file_url = self.check_urls(url_list) - format_param = req_format - - return [{ - 'id': file_id.decode('utf-8'), - 'url': file_url.decode('utf-8'), - 'uploader': uploader.decode('utf-8'), - 'upload_date': u'NA', - 'title': json_data['name'], - 'ext': file_url.split('.')[-1].decode('utf-8'), - 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), - 'thumbnail': json_data['thumbnail_url'], - 'description': json_data['description'], - 'player_url': player_url.decode('utf-8'), - }] + """Information extractor for www.mixcloud.com""" + + _WORKING = False # New API, but it seems good http://www.mixcloud.com/developers/documentation/ + _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)' + IE_NAME = u'mixcloud' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_json(self, file_id): + """Report JSON download.""" + self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME) + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) + + def get_urls(self, jsonData, fmt, bitrate='best'): + """Get urls from 'audio_formats' section in json""" + file_url = None + try: + bitrate_list = jsonData[fmt] + if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list: + bitrate = max(bitrate_list) # select highest + + url_list = jsonData[fmt][bitrate] + except TypeError: # we have no bitrate info. + url_list = jsonData[fmt] + return url_list + + def check_urls(self, url_list): + """Returns 1st active url from list""" + for url in url_list: + try: + compat_urllib_request.urlopen(url) + return url + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + url = None + + return None + + def _print_formats(self, formats): + print('Available formats:') + for fmt in formats.keys(): + for b in formats[fmt]: + try: + ext = formats[fmt][b][0] + print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1])) + except TypeError: # we have no bitrate info + ext = formats[fmt][0] + print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1])) + break + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + # extract uploader & filename from url + uploader = mobj.group(1).decode('utf-8') + file_id = uploader + "-" + mobj.group(2).decode('utf-8') + + # construct API request + file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json' + # retrieve .json file with links to files + request = compat_urllib_request.Request(file_url) + try: + self.report_download_json(file_url) + jsonData = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % compat_str(err)) + return + + # parse JSON + json_data = json.loads(jsonData) + player_url = json_data['player_swf_url'] + formats = dict(json_data['audio_formats']) + + req_format = self._downloader.params.get('format', None) + bitrate = None + + if self._downloader.params.get('listformats', None): + self._print_formats(formats) + return + + if req_format is None or req_format == 'best': + for format_param in formats.keys(): + url_list = self.get_urls(formats, format_param) + # check urls + file_url = self.check_urls(url_list) + if file_url is not None: + break # got it! + else: + if req_format not in formats: + self._downloader.trouble(u'ERROR: format is not available') + return + + url_list = self.get_urls(formats, req_format) + file_url = self.check_urls(url_list) + format_param = req_format + + return [{ + 'id': file_id.decode('utf-8'), + 'url': file_url.decode('utf-8'), + 'uploader': uploader.decode('utf-8'), + 'upload_date': None, + 'title': json_data['name'], + 'ext': file_url.split('.')[-1].decode('utf-8'), + 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), + 'thumbnail': json_data['thumbnail_url'], + 'description': json_data['description'], + 'player_url': player_url.decode('utf-8'), + }] class StanfordOpenClassroomIE(InfoExtractor): - """Information extractor for Stanford's Open ClassRoom""" - - _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$' - IE_NAME = u'stanfordoc' - - def report_download_webpage(self, objid): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid)) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - - if mobj.group('course') and mobj.group('video'): # A specific video - course = mobj.group('course') - video = mobj.group('video') - info = { - 'id': course + '_' + video, - } - - self.report_extraction(info['id']) - baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/' - xmlUrl = baseUrl + video + '.xml' - try: - metaXml = urllib2.urlopen(xmlUrl).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % unicode(err)) - return - mdoc = xml.etree.ElementTree.fromstring(metaXml) - try: - info['title'] = mdoc.findall('./title')[0].text - info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text - except IndexError: - self._downloader.trouble(u'\nERROR: Invalid metadata XML file') - return - info['ext'] = info['url'].rpartition('.')[2] - info['format'] = info['ext'] - return [info] - elif mobj.group('course'): # A course page - course = mobj.group('course') - info = { - 'id': course, - 'type': 'playlist', - } - - self.report_download_webpage(info['id']) - try: - coursepage = urllib2.urlopen(url).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err)) - return - - m = re.search('<h1>([^<]+)</h1>', coursepage) - if m: - info['title'] = unescapeHTML(m.group(1)) - else: - info['title'] = info['id'] - - m = re.search('<description>([^<]+)</description>', coursepage) - if m: - info['description'] = unescapeHTML(m.group(1)) - - links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage)) - info['list'] = [ - { - 'type': 'reference', - 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage), - } - for vpage in links] - results = [] - for entry in info['list']: - assert entry['type'] == 'reference' - results += self.extract(entry['url']) - return results - - else: # Root page - info = { - 'id': 'Stanford OpenClassroom', - 'type': 'playlist', - } - - self.report_download_webpage(info['id']) - rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php' - try: - rootpage = urllib2.urlopen(rootURL).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err)) - return - - info['title'] = info['id'] - - links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage)) - info['list'] = [ - { - 'type': 'reference', - 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage), - } - for cpage in links] - - results = [] - for entry in info['list']: - assert entry['type'] == 'reference' - results += self.extract(entry['url']) - return results + """Information extractor for Stanford's Open ClassRoom""" + + _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$' + IE_NAME = u'stanfordoc' + + def report_download_webpage(self, objid): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid)) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + if mobj.group('course') and mobj.group('video'): # A specific video + course = mobj.group('course') + video = mobj.group('video') + info = { + 'id': course + '_' + video, + 'uploader': None, + 'upload_date': None, + } + + self.report_extraction(info['id']) + baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/' + xmlUrl = baseUrl + video + '.xml' + try: + metaXml = compat_urllib_request.urlopen(xmlUrl).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err)) + return + mdoc = xml.etree.ElementTree.fromstring(metaXml) + try: + info['title'] = mdoc.findall('./title')[0].text + info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text + except IndexError: + self._downloader.trouble(u'\nERROR: Invalid metadata XML file') + return + info['ext'] = info['url'].rpartition('.')[2] + return [info] + elif mobj.group('course'): # A course page + course = mobj.group('course') + info = { + 'id': course, + 'type': 'playlist', + 'uploader': None, + 'upload_date': None, + } + + self.report_download_webpage(info['id']) + try: + coursepage = compat_urllib_request.urlopen(url).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download course info page: ' + compat_str(err)) + return + + m = re.search('<h1>([^<]+)</h1>', coursepage) + if m: + info['title'] = unescapeHTML(m.group(1)) + else: + info['title'] = info['id'] + + m = re.search('<description>([^<]+)</description>', coursepage) + if m: + info['description'] = unescapeHTML(m.group(1)) + + links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage)) + info['list'] = [ + { + 'type': 'reference', + 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage), + } + for vpage in links] + results = [] + for entry in info['list']: + assert entry['type'] == 'reference' + results += self.extract(entry['url']) + return results + + else: # Root page + info = { + 'id': 'Stanford OpenClassroom', + 'type': 'playlist', + 'uploader': None, + 'upload_date': None, + } + + self.report_download_webpage(info['id']) + rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php' + try: + rootpage = compat_urllib_request.urlopen(rootURL).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download course info page: ' + compat_str(err)) + return + + info['title'] = info['id'] + + links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage)) + info['list'] = [ + { + 'type': 'reference', + 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage), + } + for cpage in links] + + results = [] + for entry in info['list']: + assert entry['type'] == 'reference' + results += self.extract(entry['url']) + return results class MTVIE(InfoExtractor): - """Information extractor for MTV.com""" - - _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$' - IE_NAME = u'mtv' - - def report_webpage(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - if not mobj.group('proto'): - url = 'http://' + url - video_id = mobj.group('videoid') - self.report_webpage(video_id) - - request = urllib2.Request(url) - try: - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) - return - - mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract song name') - return - song_name = unescapeHTML(mobj.group(1).decode('iso-8859-1')) - mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract performer') - return - performer = unescapeHTML(mobj.group(1).decode('iso-8859-1')) - video_title = performer + ' - ' + song_name - - mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to mtvn_uri') - return - mtvn_uri = mobj.group(1) - - mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract content id') - return - content_id = mobj.group(1) - - videogen_url = 'http://www.mtv.com/player/includes/mediaGen.jhtml?uri=' + mtvn_uri + '&id=' + content_id + '&vid=' + video_id + '&ref=www.mtvn.com&viewUri=' + mtvn_uri - self.report_extraction(video_id) - request = urllib2.Request(videogen_url) - try: - metadataXml = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % str(err)) - return - - mdoc = xml.etree.ElementTree.fromstring(metadataXml) - renditions = mdoc.findall('.//rendition') - - # For now, always pick the highest quality. - rendition = renditions[-1] - - try: - _,_,ext = rendition.attrib['type'].partition('/') - format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate'] - video_url = rendition.find('./src').text - except KeyError: - self._downloader.trouble('Invalid rendition field.') - return - - info = { - 'id': video_id, - 'url': video_url, - 'uploader': performer, - 'title': video_title, - 'ext': ext, - 'format': format, - } - - return [info] + """Information extractor for MTV.com""" + + _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$' + IE_NAME = u'mtv' + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + if not mobj.group('proto'): + url = 'http://' + url + video_id = mobj.group('videoid') + + webpage = self._download_webpage(url, video_id) + + mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract song name') + return + song_name = unescapeHTML(mobj.group(1).decode('iso-8859-1')) + mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract performer') + return + performer = unescapeHTML(mobj.group(1).decode('iso-8859-1')) + video_title = performer + ' - ' + song_name + + mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to mtvn_uri') + return + mtvn_uri = mobj.group(1) + + mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract content id') + return + content_id = mobj.group(1) + + videogen_url = 'http://www.mtv.com/player/includes/mediaGen.jhtml?uri=' + mtvn_uri + '&id=' + content_id + '&vid=' + video_id + '&ref=www.mtvn.com&viewUri=' + mtvn_uri + self.report_extraction(video_id) + request = compat_urllib_request.Request(videogen_url) + try: + metadataXml = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % compat_str(err)) + return + + mdoc = xml.etree.ElementTree.fromstring(metadataXml) + renditions = mdoc.findall('.//rendition') + + # For now, always pick the highest quality. + rendition = renditions[-1] + + try: + _,_,ext = rendition.attrib['type'].partition('/') + format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate'] + video_url = rendition.find('./src').text + except KeyError: + self._downloader.trouble('Invalid rendition field.') + return + + info = { + 'id': video_id, + 'url': video_url, + 'uploader': performer, + 'upload_date': None, + 'title': video_title, + 'ext': ext, + 'format': format, + } + + return [info] class YoukuIE(InfoExtractor): - - _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html' - IE_NAME = u'Youku' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, file_id): - """Report webpage download.""" - self._downloader.to_screen(u'[Youku] %s: Downloading webpage' % file_id) - - def report_extraction(self, file_id): - """Report information extraction.""" - self._downloader.to_screen(u'[Youku] %s: Extracting information' % file_id) - - def _gen_sid(self): - nowTime = int(time.time() * 1000) - random1 = random.randint(1000,1998) - random2 = random.randint(1000,9999) - - return "%d%d%d" %(nowTime,random1,random2) - - def _get_file_ID_mix_string(self, seed): - mixed = [] - source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890") - seed = float(seed) - for i in range(len(source)): - seed = (seed * 211 + 30031 ) % 65536 - index = math.floor(seed / 65536 * len(source) ) - mixed.append(source[int(index)]) - source.remove(source[int(index)]) - #return ''.join(mixed) - return mixed - - def _get_file_id(self, fileId, seed): - mixed = self._get_file_ID_mix_string(seed) - ids = fileId.split('*') - realId = [] - for ch in ids: - if ch: - realId.append(mixed[int(ch)]) - return ''.join(realId) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - video_id = mobj.group('ID') - - info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id - - request = urllib2.Request(info_url, None, std_headers) - try: - self.report_download_webpage(video_id) - jsondata = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) - return - - self.report_extraction(video_id) - try: - config = json.loads(jsondata) - - video_title = config['data'][0]['title'] - seed = config['data'][0]['seed'] - - format = self._downloader.params.get('format', None) - supported_format = config['data'][0]['streamfileids'].keys() - - if format is None or format == 'best': - if 'hd2' in supported_format: - format = 'hd2' - else: - format = 'flv' - ext = u'flv' - elif format == 'worst': - format = 'mp4' - ext = u'mp4' - else: - format = 'flv' - ext = u'flv' - - - fileid = config['data'][0]['streamfileids'][format] - seg_number = len(config['data'][0]['segs'][format]) - - keys=[] - for i in xrange(seg_number): - keys.append(config['data'][0]['segs'][format][i]['k']) - - #TODO check error - #youku only could be viewed from mainland china - except: - self._downloader.trouble(u'ERROR: unable to extract info section') - return - - files_info=[] - sid = self._gen_sid() - fileid = self._get_file_id(fileid, seed) - - #column 8,9 of fileid represent the segment number - #fileid[7:9] should be changed - for index, key in enumerate(keys): - - temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:]) - download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key) - - info = { - 'id': '%s_part%02d' % (video_id, index), - 'url': download_url, - 'uploader': None, - 'title': video_title, - 'ext': ext, - 'format': u'NA' - } - files_info.append(info) - - return files_info + _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html' + + def report_download_webpage(self, file_id): + """Report webpage download.""" + self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, file_id)) + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) + + def _gen_sid(self): + nowTime = int(time.time() * 1000) + random1 = random.randint(1000,1998) + random2 = random.randint(1000,9999) + + return "%d%d%d" %(nowTime,random1,random2) + + def _get_file_ID_mix_string(self, seed): + mixed = [] + source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890") + seed = float(seed) + for i in range(len(source)): + seed = (seed * 211 + 30031 ) % 65536 + index = math.floor(seed / 65536 * len(source) ) + mixed.append(source[int(index)]) + source.remove(source[int(index)]) + #return ''.join(mixed) + return mixed + + def _get_file_id(self, fileId, seed): + mixed = self._get_file_ID_mix_string(seed) + ids = fileId.split('*') + realId = [] + for ch in ids: + if ch: + realId.append(mixed[int(ch)]) + return ''.join(realId) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group('ID') + + info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id + + request = compat_urllib_request.Request(info_url, None, std_headers) + try: + self.report_download_webpage(video_id) + jsondata = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) + return + + self.report_extraction(video_id) + try: + jsonstr = jsondata.decode('utf-8') + config = json.loads(jsonstr) + + video_title = config['data'][0]['title'] + seed = config['data'][0]['seed'] + + format = self._downloader.params.get('format', None) + supported_format = list(config['data'][0]['streamfileids'].keys()) + + if format is None or format == 'best': + if 'hd2' in supported_format: + format = 'hd2' + else: + format = 'flv' + ext = u'flv' + elif format == 'worst': + format = 'mp4' + ext = u'mp4' + else: + format = 'flv' + ext = u'flv' + + + fileid = config['data'][0]['streamfileids'][format] + keys = [s['k'] for s in config['data'][0]['segs'][format]] + except (UnicodeDecodeError, ValueError, KeyError): + self._downloader.trouble(u'ERROR: unable to extract info section') + return + + files_info=[] + sid = self._gen_sid() + fileid = self._get_file_id(fileid, seed) + + #column 8,9 of fileid represent the segment number + #fileid[7:9] should be changed + for index, key in enumerate(keys): + + temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:]) + download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key) + + info = { + 'id': '%s_part%02d' % (video_id, index), + 'url': download_url, + 'uploader': None, + 'upload_date': None, + 'title': video_title, + 'ext': ext, + } + files_info.append(info) + + return files_info class XNXXIE(InfoExtractor): - """Information extractor for xnxx.com""" - - _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)' - IE_NAME = u'xnxx' - VIDEO_URL_RE = r'flv_url=(.*?)&' - VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM' - VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&' - - def report_webpage(self, video_id): - """Report information extraction""" - self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) - - def report_extraction(self, video_id): - """Report information extraction""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - video_id = mobj.group(1).decode('utf-8') - - self.report_webpage(video_id) - - # Get webpage content - try: - webpage = urllib2.urlopen(url).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) - return - - result = re.search(self.VIDEO_URL_RE, webpage) - if result is None: - self._downloader.trouble(u'ERROR: unable to extract video url') - return - video_url = urllib.unquote(result.group(1).decode('utf-8')) - - result = re.search(self.VIDEO_TITLE_RE, webpage) - if result is None: - self._downloader.trouble(u'ERROR: unable to extract video title') - return - video_title = result.group(1).decode('utf-8') - - result = re.search(self.VIDEO_THUMB_RE, webpage) - if result is None: - self._downloader.trouble(u'ERROR: unable to extract video thumbnail') - return - video_thumbnail = result.group(1).decode('utf-8') - - info = {'id': video_id, - 'url': video_url, - 'uploader': None, - 'upload_date': None, - 'title': video_title, - 'ext': 'flv', - 'format': 'flv', - 'thumbnail': video_thumbnail, - 'description': None, - 'player_url': None} - - return [info] + """Information extractor for xnxx.com""" + + _VALID_URL = r'^http://video\.xnxx\.com/video([0-9]+)/(.*)' + IE_NAME = u'xnxx' + VIDEO_URL_RE = r'flv_url=(.*?)&' + VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM' + VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&' + + def report_webpage(self, video_id): + """Report information extraction""" + self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) + + def report_extraction(self, video_id): + """Report information extraction""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group(1) + + self.report_webpage(video_id) + + # Get webpage content + try: + webpage_bytes = compat_urllib_request.urlopen(url).read() + webpage = webpage_bytes.decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) + return + + result = re.search(self.VIDEO_URL_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video url') + return + video_url = compat_urllib_parse.unquote(result.group(1)) + + result = re.search(self.VIDEO_TITLE_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = result.group(1) + + result = re.search(self.VIDEO_THUMB_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = result.group(1) + + return [{ + 'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': None, + 'title': video_title, + 'ext': 'flv', + 'thumbnail': video_thumbnail, + 'description': None, + }] class GooglePlusIE(InfoExtractor): - """Information extractor for plus.google.com.""" - - _VALID_URL = r'(?:https://)?plus\.google\.com/(?:\w+/)*?(\d+)/posts/(\w+)' - IE_NAME = u'plus.google' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_extract_entry(self, url): - """Report downloading extry""" - self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url.decode('utf-8')) - - def report_date(self, upload_date): - """Report downloading extry""" - self._downloader.to_screen(u'[plus.google] Entry date: %s' % upload_date) - - def report_uploader(self, uploader): - """Report downloading extry""" - self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader.decode('utf-8')) - - def report_title(self, video_title): - """Report downloading extry""" - self._downloader.to_screen(u'[plus.google] Title: %s' % video_title.decode('utf-8')) - - def report_extract_vid_page(self, video_page): - """Report information extraction.""" - self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page.decode('utf-8')) - - def _real_extract(self, url): - # Extract id from URL - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - - post_url = mobj.group(0) - video_id = mobj.group(2) - - video_extension = 'flv' - - # Step 1, Retrieve post webpage to extract further information - self.report_extract_entry(post_url) - request = urllib2.Request(post_url) - try: - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % str(err)) - return - - # Extract update date - upload_date = u'NA' - pattern = 'title="Timestamp">(.*?)</a>' - mobj = re.search(pattern, webpage) - if mobj: - upload_date = mobj.group(1) - # Convert timestring to a format suitable for filename - upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d") - upload_date = upload_date.strftime('%Y%m%d') - self.report_date(upload_date) - - # Extract uploader - uploader = u'NA' - pattern = r'rel\="author".*?>(.*?)</a>' - mobj = re.search(pattern, webpage) - if mobj: - uploader = mobj.group(1) - self.report_uploader(uploader) - - # Extract title - # Get the first line for title - video_title = u'NA' - pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]' - mobj = re.search(pattern, webpage) - if mobj: - video_title = mobj.group(1) - self.report_title(video_title) - - # Step 2, Stimulate clicking the image box to launch video - pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]' - mobj = re.search(pattern, webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video page URL') - - video_page = mobj.group(1) - request = urllib2.Request(video_page) - try: - webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) - return - self.report_extract_vid_page(video_page) - - - # Extract video links on video page - """Extract video links of all sizes""" - pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"' - mobj = re.findall(pattern, webpage) - if len(mobj) == 0: - self._downloader.trouble(u'ERROR: unable to extract video links') - - # Sort in resolution - links = sorted(mobj) - - # Choose the lowest of the sort, i.e. highest resolution - video_url = links[-1] - # Only get the url. The resolution part in the tuple has no use anymore - video_url = video_url[-1] - # Treat escaped \u0026 style hex - video_url = unicode(video_url, "unicode_escape") - - - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_url, - 'uploader': uploader.decode('utf-8'), - 'upload_date': upload_date.decode('utf-8'), - 'title': video_title.decode('utf-8'), - 'ext': video_extension.decode('utf-8'), - 'format': u'NA', - 'player_url': None, - }] - - - -class YouPornIE(InfoExtractor): - """Information extractor for youporn.com.""" - - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)' - IE_NAME = u'youporn' - VIDEO_TITLE_RE = r'videoTitleArea">(?P<title>.*)</h1>' - VIDEO_DATE_RE = r'Date:</b>(?P<date>.*)</li>' - VIDEO_UPLOADER_RE = r'Submitted:</b>(?P<uploader>.*)</li>' - DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>' - LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_id(self, video_id): - """Report finding video ID""" - self._downloader.to_screen(u'[youporn] Video ID: %s' % video_id) - - def report_webpage(self, url): - """Report downloading page""" - self._downloader.to_screen(u'[youporn] Downloaded page: %s' % url) - - def report_title(self, video_title): - """Report dfinding title""" - self._downloader.to_screen(u'[youporn] Title: %s' % video_title) - - def report_uploader(self, uploader): - """Report dfinding title""" - self._downloader.to_screen(u'[youporn] Uploader: %s' % uploader) - - def report_upload_date(self, video_date): - """Report finding date""" - self._downloader.to_screen(u'[youporn] Date: %s' % video_date) - - def _print_formats(self, formats): - """Print all available formats""" - print 'Available formats:' - print u'ext\t\tformat' - print u'---------------------------------' - for format in formats: - print u'%s\t\t%s' % (format['ext'], format['format']) - - def _specific(self, req_format, formats): - for x in formats: - if(x["format"]==req_format): - return x - return None - - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - - video_id = mobj.group('videoid').decode('utf-8') - self.report_id(video_id) - - # Get webpage content - try: - webpage = urllib2.urlopen(url).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) - return - self.report_webpage(url) - - # Get the video title - result = re.search(self.VIDEO_TITLE_RE, webpage) - if result is None: - self._downloader.trouble(u'ERROR: unable to extract video title') - return - video_title = result.group('title').decode('utf-8').strip() - self.report_title(video_title) - - # Get the video date - result = re.search(self.VIDEO_DATE_RE, webpage) - if result is None: - self._downloader.trouble(u'ERROR: unable to extract video date') - return - upload_date = result.group('date').decode('utf-8').strip() - self.report_upload_date(upload_date) - - # Get the video uploader - result = re.search(self.VIDEO_UPLOADER_RE, webpage) - if result is None: - self._downloader.trouble(u'ERROR: unable to extract uploader') - return - video_uploader = result.group('uploader').decode('utf-8').strip() - video_uploader = clean_html( video_uploader ) - self.report_uploader(video_uploader) - - # Get all of the formats available - result = re.search(self.DOWNLOAD_LIST_RE, webpage) - if result is None: - self._downloader.trouble(u'ERROR: unable to extract download list') - return - download_list_html = result.group('download_list').decode('utf-8').strip() - - # Get all of the links from the page - links = re.findall(self.LINK_RE, download_list_html) - if(len(links) == 0): - self._downloader.trouble(u'ERROR: no known formats available for video') - return - - self._downloader.to_screen(u'[youporn] Links found: %d' % len(links)) - - formats = [] - for link in links: - - # A link looks like this: - # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0 - # A path looks like this: - # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4 - video_url = unescapeHTML( link.decode('utf-8') ) - path = urlparse( video_url ).path - extension = os.path.splitext( path )[1][1:] - format = path.split('/')[4].split('_')[:2] - size = format[0] - bitrate = format[1] - format = "-".join( format ) - title = u'%s-%s-%s' % (video_title, size, bitrate) - - formats.append({ - 'id': video_id, - 'url': video_url, - 'uploader': video_uploader, - 'upload_date': upload_date, - 'title': title, - 'ext': extension, - 'format': format, - 'thumbnail': None, - 'description': None, - 'player_url': None - }) - - if self._downloader.params.get('listformats', None): - self._print_formats(formats) - return - - req_format = self._downloader.params.get('format', None) - #format_limit = self._downloader.params.get('format_limit', None) - self._downloader.to_screen(u'[youporn] Format: %s' % req_format) - - - if req_format is None or req_format == 'best': - return [formats[0]] - elif req_format == 'worst': - return [formats[-1]] - elif req_format in ('-1', 'all'): - return formats - else: - format = self._specific( req_format, formats ) - if result is None: - self._downloader.trouble(u'ERROR: requested format not available') - return - return [format] - - - - -class PornotubeIE(InfoExtractor): - """Information extractor for pornotube.com.""" - - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' - IE_NAME = u'pornotube' - VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' - VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' - - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_extract_entry(self, url): - """Report downloading extry""" - self._downloader.to_screen(u'[pornotube] Downloading entry: %s' % url.decode('utf-8')) - - def report_date(self, upload_date): - """Report finding uploaded date""" - self._downloader.to_screen(u'[pornotube] Entry date: %s' % upload_date) - - def report_webpage(self, url): - """Report downloading page""" - self._downloader.to_screen(u'[pornotube] Downloaded page: %s' % url) - - def report_title(self, video_title): - """Report downloading extry""" - self._downloader.to_screen(u'[pornotube] Title: %s' % video_title.decode('utf-8')) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - - video_id = mobj.group('videoid').decode('utf-8') - video_title = mobj.group('title').decode('utf-8') - self.report_title(video_title); - - # Get webpage content - try: - webpage = urllib2.urlopen(url).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) - return - self.report_webpage(url) - - # Get the video URL - result = re.search(self.VIDEO_URL_RE, webpage) - if result is None: - self._downloader.trouble(u'ERROR: unable to extract video url') - return - video_url = urllib.unquote(result.group('url').decode('utf-8')) - self.report_extract_entry(video_url) - - #Get the uploaded date - result = re.search(self.VIDEO_UPLOADED_RE, webpage) - if result is None: - self._downloader.trouble(u'ERROR: unable to extract video title') - return - upload_date = result.group('date').decode('utf-8') - self.report_date(upload_date); - - - info = {'id': video_id, - 'url': video_url, - 'uploader': None, - 'upload_date': upload_date, - 'title': video_title, - 'ext': 'flv', - 'format': 'flv', - 'thumbnail': None, - 'description': None, - 'player_url': None} - - return [info] - - - - -class YouJizzIE(InfoExtractor): - """Information extractor for youjizz.com.""" - - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/([^.]+).html$' - IE_NAME = u'youjizz' - VIDEO_TITLE_RE = r'<title>(?P<title>.*)</title>' - EMBED_PAGE_RE = r'http://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)' - SOURCE_RE = r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_extract_entry(self, url): - """Report downloading extry""" - self._downloader.to_screen(u'[youjizz] Downloading entry: %s' % url.decode('utf-8')) - - def report_webpage(self, url): - """Report downloading page""" - self._downloader.to_screen(u'[youjizz] Downloaded page: %s' % url) - - def report_title(self, video_title): - """Report downloading extry""" - self._downloader.to_screen(u'[youjizz] Title: %s' % video_title.decode('utf-8')) - - def report_embed_page(self, embed_page): - """Report downloading extry""" - self._downloader.to_screen(u'[youjizz] Embed Page: %s' % embed_page.decode('utf-8')) - - def _real_extract(self, url): - # Get webpage content - try: - webpage = urllib2.urlopen(url).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) - return - self.report_webpage(url) - - # Get the video title - result = re.search(self.VIDEO_TITLE_RE, webpage) - if result is None: - self._downloader.trouble(u'ERROR: unable to extract video title') - return - video_title = result.group('title').decode('utf-8').strip() - self.report_title(video_title) - - # Get the embed page - result = re.search(self.EMBED_PAGE_RE, webpage) - if result is None: - self._downloader.trouble(u'ERROR: unable to extract embed page') - return - - embed_page_url = result.group(0).decode('utf-8').strip() - video_id = result.group('videoid').decode('utf-8') - self.report_embed_page(embed_page_url) - - try: - webpage = urllib2.urlopen(embed_page_url).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video embed page: %s' % err) - return - - # Get the video URL - result = re.search(self.SOURCE_RE, webpage) - if result is None: - self._downloader.trouble(u'ERROR: unable to extract video url') - return - video_url = result.group('source').decode('utf-8') - self.report_extract_entry(video_url) - - info = {'id': video_id, - 'url': video_url, - 'uploader': None, - 'upload_date': None, - 'title': video_title, - 'ext': 'flv', - 'format': 'flv', - 'thumbnail': None, - 'description': None, - 'player_url': embed_page_url} - - return [info] + """Information extractor for plus.google.com.""" + + _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)' + IE_NAME = u'plus.google' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_extract_entry(self, url): + """Report downloading extry""" + self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url) + + def report_date(self, upload_date): + """Report downloading extry""" + self._downloader.to_screen(u'[plus.google] Entry date: %s' % upload_date) + + def report_uploader(self, uploader): + """Report downloading extry""" + self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader) + + def report_title(self, video_title): + """Report downloading extry""" + self._downloader.to_screen(u'[plus.google] Title: %s' % video_title) + + def report_extract_vid_page(self, video_page): + """Report information extraction.""" + self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page) + + def _real_extract(self, url): + # Extract id from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + post_url = mobj.group(0) + video_id = mobj.group(1) + + video_extension = 'flv' + + # Step 1, Retrieve post webpage to extract further information + self.report_extract_entry(post_url) + request = compat_urllib_request.Request(post_url) + try: + webpage = compat_urllib_request.urlopen(request).read().decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % compat_str(err)) + return + + # Extract update date + upload_date = None + pattern = 'title="Timestamp">(.*?)</a>' + mobj = re.search(pattern, webpage) + if mobj: + upload_date = mobj.group(1) + # Convert timestring to a format suitable for filename + upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d") + upload_date = upload_date.strftime('%Y%m%d') + self.report_date(upload_date) + + # Extract uploader + uploader = None + pattern = r'rel\="author".*?>(.*?)</a>' + mobj = re.search(pattern, webpage) + if mobj: + uploader = mobj.group(1) + self.report_uploader(uploader) + + # Extract title + # Get the first line for title + video_title = u'NA' + pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]' + mobj = re.search(pattern, webpage) + if mobj: + video_title = mobj.group(1) + self.report_title(video_title) + + # Step 2, Stimulate clicking the image box to launch video + pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]' + mobj = re.search(pattern, webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video page URL') + + video_page = mobj.group(1) + request = compat_urllib_request.Request(video_page) + try: + webpage = compat_urllib_request.urlopen(request).read().decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) + return + self.report_extract_vid_page(video_page) + + + # Extract video links on video page + """Extract video links of all sizes""" + pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"' + mobj = re.findall(pattern, webpage) + if len(mobj) == 0: + self._downloader.trouble(u'ERROR: unable to extract video links') + + # Sort in resolution + links = sorted(mobj) + + # Choose the lowest of the sort, i.e. highest resolution + video_url = links[-1] + # Only get the url. The resolution part in the tuple has no use anymore + video_url = video_url[-1] + # Treat escaped \u0026 style hex + try: + video_url = video_url.decode("unicode_escape") + except AttributeError: # Python 3 + video_url = bytes(video_url, 'ascii').decode('unicode-escape') + + + return [{ + 'id': video_id, + 'url': video_url, + 'uploader': uploader, + 'upload_date': upload_date, + 'title': video_title, + 'ext': video_extension, + }] + +class NBAIE(InfoExtractor): + _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*)(\?.*)?$' + IE_NAME = u'nba' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + video_id = mobj.group(1) + if video_id.endswith('/index.html'): + video_id = video_id[:-len('/index.html')] + + webpage = self._download_webpage(url, video_id) + + video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4' + def _findProp(rexp, default=None): + m = re.search(rexp, webpage) + if m: + return unescapeHTML(m.group(1)) + else: + return default + + shortened_video_id = video_id.rpartition('/')[2] + title = _findProp(r'<meta property="og:title" content="(.*?)"', shortened_video_id).replace('NBA.com: ', '') + info = { + 'id': shortened_video_id, + 'url': video_url, + 'ext': 'mp4', + 'title': title, + 'uploader_date': _findProp(r'<b>Date:</b> (.*?)</div>'), + 'description': _findProp(r'<div class="description">(.*?)</h1>'), + } + return [info] + +class JustinTVIE(InfoExtractor): + """Information extractor for justin.tv and twitch.tv""" + # TODO: One broadcast may be split into multiple videos. The key + # 'broadcast_id' is the same for all parts, and 'broadcast_part' + # starts at 1 and increases. Can we treat all parts as one video? + + _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?(?:twitch|justin)\.tv/ + ([^/]+)(?:/b/([^/]+))?/?(?:\#.*)?$""" + _JUSTIN_PAGE_LIMIT = 100 + IE_NAME = u'justin.tv' + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) + + def report_download_page(self, channel, offset): + """Report attempt to download a single page of videos.""" + self._downloader.to_screen(u'[%s] %s: Downloading video information from %d to %d' % + (self.IE_NAME, channel, offset, offset + self._JUSTIN_PAGE_LIMIT)) + + # Return count of items, list of *valid* items + def _parse_page(self, url): + try: + urlh = compat_urllib_request.urlopen(url) + webpage_bytes = urlh.read() + webpage = webpage_bytes.decode('utf-8', 'ignore') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download video info JSON: %s' % compat_str(err)) + return + + response = json.loads(webpage) + info = [] + for clip in response: + video_url = clip['video_file_url'] + if video_url: + video_extension = os.path.splitext(video_url)[1][1:] + video_date = re.sub('-', '', clip['created_on'][:10]) + info.append({ + 'id': clip['id'], + 'url': video_url, + 'title': clip['title'], + 'uploader': clip.get('user_id', clip.get('channel_id')), + 'upload_date': video_date, + 'ext': video_extension, + }) + return (len(response), info) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + api = 'http://api.justin.tv' + video_id = mobj.group(mobj.lastindex) + paged = False + if mobj.lastindex == 1: + paged = True + api += '/channel/archives/%s.json' + else: + api += '/clip/show/%s.json' + api = api % (video_id,) + + self.report_extraction(video_id) + + info = [] + offset = 0 + limit = self._JUSTIN_PAGE_LIMIT + while True: + if paged: + self.report_download_page(video_id, offset) + page_url = api + ('?offset=%d&limit=%d' % (offset, limit)) + page_count, page_info = self._parse_page(page_url) + info.extend(page_info) + if not paged or page_count != limit: + break + offset += limit + return info + +class FunnyOrDieIE(InfoExtractor): + _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + m = re.search(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"', webpage, re.DOTALL) + if not m: + self._downloader.trouble(u'ERROR: unable to find video information') + video_url = unescapeHTML(m.group('url')) + + m = re.search(r"class='player_page_h1'>\s+<a.*?>(?P<title>.*?)</a>", webpage) + if not m: + self._downloader.trouble(u'Cannot find video title') + title = unescapeHTML(m.group('title')) + + m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage) + if m: + desc = unescapeHTML(m.group('desc')) + else: + desc = None + + info = { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'title': title, + 'description': desc, + } + return [info] + +class TweetReelIE(InfoExtractor): + _VALID_URL = r'^(?:https?://)?(?:www\.)?tweetreel\.com/[?](?P<id>[0-9a-z]+)$' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + m = re.search(r'<div id="left" status_id="([0-9]+)">', webpage) + if not m: + self._downloader.trouble(u'ERROR: Cannot find status ID') + status_id = m.group(1) + + m = re.search(r'<div class="tweet_text">(.*?)</div>', webpage, flags=re.DOTALL) + if not m: + self._downloader.trouble(u'WARNING: Cannot find description') + desc = unescapeHTML(re.sub('<a.*?</a>', '', m.group(1))).strip() + + m = re.search(r'<div class="tweet_info">.*?from <a target="_blank" href="https?://twitter.com/(?P<uploader_id>.+?)">(?P<uploader>.+?)</a>', webpage, flags=re.DOTALL) + if not m: + self._downloader.trouble(u'ERROR: Cannot find uploader') + uploader = unescapeHTML(m.group('uploader')) + uploader_id = unescapeHTML(m.group('uploader_id')) + + m = re.search(r'<span unixtime="([0-9]+)"', webpage) + if not m: + self._downloader.trouble(u'ERROR: Cannot find upload date') + upload_date = datetime.datetime.fromtimestamp(int(m.group(1))).strftime('%Y%m%d') + + title = desc + video_url = 'http://files.tweetreel.com/video/' + status_id + '.mov' + + info = { + 'id': video_id, + 'url': video_url, + 'ext': 'mov', + 'title': title, + 'description': desc, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'internal_id': status_id, + 'upload_date': upload_date + } + return [info] + +class SteamIE(InfoExtractor): + _VALID_URL = r"""http://store.steampowered.com/ + (?P<urltype>video|app)/ #If the page is only for videos or for a game + (?P<gameID>\d+)/? + (?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID + """ + + def suitable(self, url): + """Receives a URL and returns True if suitable for this IE.""" + return re.match(self._VALID_URL, url, re.VERBOSE) is not None + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url, re.VERBOSE) + urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\}," + gameID = m.group('gameID') + videourl = 'http://store.steampowered.com/video/%s/' % gameID + webpage = self._download_webpage(videourl, gameID) + mweb = re.finditer(urlRE, webpage) + namesRE = r'<span class="title">(?P<videoName>.+?)</span>' + titles = re.finditer(namesRE, webpage) + videos = [] + for vid,vtitle in zip(mweb,titles): + video_id = vid.group('videoID') + title = vtitle.group('videoName') + video_url = vid.group('videoURL') + if not video_url: + self._downloader.trouble(u'ERROR: Cannot find video url for %s' % video_id) + info = { + 'id':video_id, + 'url':video_url, + 'ext': 'flv', + 'title': unescapeHTML(title) + } + videos.append(info) + return videos + +class UstreamIE(InfoExtractor): + _VALID_URL = r'http://www.ustream.tv/recorded/(?P<videoID>\d+)' + IE_NAME = u'ustream' + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('videoID') + video_url = u'http://tcdn.ustream.tv/video/%s' % video_id + webpage = self._download_webpage(url, video_id) + m = re.search(r'data-title="(?P<title>.+)"',webpage) + title = m.group('title') + m = re.search(r'<a class="state" data-content-type="channel" data-content-id="(?P<uploader>\d+)"',webpage) + uploader = m.group('uploader') + info = { + 'id':video_id, + 'url':video_url, + 'ext': 'flv', + 'title': title, + 'uploader': uploader + } + return [info] + + +def gen_extractors(): + """ Return a list of an instance of every supported extractor. + The order does matter; the first extractor matched is the one handling the URL. + """ + return [ + YoutubePlaylistIE(), + YoutubeChannelIE(), + YoutubeUserIE(), + YoutubeSearchIE(), + YoutubeIE(), + MetacafeIE(), + DailymotionIE(), + GoogleSearchIE(), + PhotobucketIE(), + YahooIE(), + YahooSearchIE(), + DepositFilesIE(), + FacebookIE(), + BlipTVUserIE(), + BlipTVIE(), + VimeoIE(), + MyVideoIE(), + ComedyCentralIE(), + EscapistIE(), + CollegeHumorIE(), + XVideosIE(), + SoundcloudIE(), + InfoQIE(), + MixcloudIE(), + StanfordOpenClassroomIE(), + MTVIE(), + YoukuIE(), + XNXXIE(), + GooglePlusIE(), + ArteTvIE(), + NBAIE(), + JustinTVIE(), + FunnyOrDieIE(), + TweetReelIE(), + SteamIE(), + UstreamIE(), + GenericIE() + ] + diff --git a/youtube_dl/PostProcessor.py b/youtube_dl/PostProcessor.py index 0501cc7f6..a04828518 100644 --- a/youtube_dl/PostProcessor.py +++ b/youtube_dl/PostProcessor.py @@ -1,198 +1,204 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- +from __future__ import absolute_import + import os import subprocess import sys import time -from utils import * +from .utils import * class PostProcessor(object): - """Post Processor class. + """Post Processor class. - PostProcessor objects can be added to downloaders with their - add_post_processor() method. When the downloader has finished a - successful download, it will take its internal chain of PostProcessors - and start calling the run() method on each one of them, first with - an initial argument and then with the returned value of the previous - PostProcessor. + PostProcessor objects can be added to downloaders with their + add_post_processor() method. When the downloader has finished a + successful download, it will take its internal chain of PostProcessors + and start calling the run() method on each one of them, first with + an initial argument and then with the returned value of the previous + PostProcessor. - The chain will be stopped if one of them ever returns None or the end - of the chain is reached. + The chain will be stopped if one of them ever returns None or the end + of the chain is reached. - PostProcessor objects follow a "mutual registration" process similar - to InfoExtractor objects. - """ + PostProcessor objects follow a "mutual registration" process similar + to InfoExtractor objects. + """ - _downloader = None + _downloader = None - def __init__(self, downloader=None): - self._downloader = downloader + def __init__(self, downloader=None): + self._downloader = downloader - def set_downloader(self, downloader): - """Sets the downloader for this PP.""" - self._downloader = downloader + def set_downloader(self, downloader): + """Sets the downloader for this PP.""" + self._downloader = downloader - def run(self, information): - """Run the PostProcessor. + def run(self, information): + """Run the PostProcessor. - The "information" argument is a dictionary like the ones - composed by InfoExtractors. The only difference is that this - one has an extra field called "filepath" that points to the - downloaded file. + The "information" argument is a dictionary like the ones + composed by InfoExtractors. The only difference is that this + one has an extra field called "filepath" that points to the + downloaded file. - When this method returns None, the postprocessing chain is - stopped. However, this method may return an information - dictionary that will be passed to the next postprocessing - object in the chain. It can be the one it received after - changing some fields. + When this method returns None, the postprocessing chain is + stopped. However, this method may return an information + dictionary that will be passed to the next postprocessing + object in the chain. It can be the one it received after + changing some fields. - In addition, this method may raise a PostProcessingError - exception that will be taken into account by the downloader - it was called from. - """ - return information # by default, do nothing + In addition, this method may raise a PostProcessingError + exception that will be taken into account by the downloader + it was called from. + """ + return information # by default, do nothing class AudioConversionError(BaseException): - def __init__(self, message): - self.message = message + def __init__(self, message): + self.message = message class FFmpegExtractAudioPP(PostProcessor): - def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False): - PostProcessor.__init__(self, downloader) - if preferredcodec is None: - preferredcodec = 'best' - self._preferredcodec = preferredcodec - self._preferredquality = preferredquality - self._keepvideo = keepvideo - self._exes = self.detect_executables() - - @staticmethod - def detect_executables(): - def executable(exe): - try: - subprocess.Popen([exe, '-version'], stdout=subprocess.PIPE, stderr=subprocess.PIPE).communicate() - except OSError: - return False - return exe - programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe'] - return dict((program, executable(program)) for program in programs) - - def get_audio_codec(self, path): - if not self._exes['ffprobe'] and not self._exes['avprobe']: return None - try: - cmd = [self._exes['avprobe'] or self._exes['ffprobe'], '-show_streams', '--', encodeFilename(path)] - handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE) - output = handle.communicate()[0] - if handle.wait() != 0: - return None - except (IOError, OSError): - return None - audio_codec = None - for line in output.split('\n'): - if line.startswith('codec_name='): - audio_codec = line.split('=')[1].strip() - elif line.strip() == 'codec_type=audio' and audio_codec is not None: - return audio_codec - return None - - def run_ffmpeg(self, path, out_path, codec, more_opts): - if not self._exes['ffmpeg'] and not self._exes['avconv']: - raise AudioConversionError('ffmpeg or avconv not found. Please install one.') - if codec is None: - acodec_opts = [] - else: - acodec_opts = ['-acodec', codec] - cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y', '-i', encodeFilename(path), '-vn'] - + acodec_opts + more_opts + - ['--', encodeFilename(out_path)]) - p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) - stdout,stderr = p.communicate() - if p.returncode != 0: - msg = stderr.strip().split('\n')[-1] - raise AudioConversionError(msg) - - def run(self, information): - path = information['filepath'] - - filecodec = self.get_audio_codec(path) - if filecodec is None: - self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe') - return None - - more_opts = [] - if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'): - if self._preferredcodec == 'm4a' and filecodec == 'aac': - # Lossless, but in another container - acodec = 'copy' - extension = self._preferredcodec - more_opts = [self._exes['avconv'] and '-bsf:a' or '-absf', 'aac_adtstoasc'] - elif filecodec in ['aac', 'mp3', 'vorbis']: - # Lossless if possible - acodec = 'copy' - extension = filecodec - if filecodec == 'aac': - more_opts = ['-f', 'adts'] - if filecodec == 'vorbis': - extension = 'ogg' - else: - # MP3 otherwise. - acodec = 'libmp3lame' - extension = 'mp3' - more_opts = [] - if self._preferredquality is not None: - if int(self._preferredquality) < 10: - more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality] - else: - more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality + 'k'] - else: - # We convert the audio (lossy) - acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec] - extension = self._preferredcodec - more_opts = [] - if self._preferredquality is not None: - if int(self._preferredquality) < 10: - more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality] - else: - more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality + 'k'] - if self._preferredcodec == 'aac': - more_opts += ['-f', 'adts'] - if self._preferredcodec == 'm4a': - more_opts += [self._exes['avconv'] and '-bsf:a' or '-absf', 'aac_adtstoasc'] - if self._preferredcodec == 'vorbis': - extension = 'ogg' - if self._preferredcodec == 'wav': - extension = 'wav' - more_opts += ['-f', 'wav'] - - prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups - new_path = prefix + sep + extension - self._downloader.to_screen(u'[' + (self._exes['avconv'] and 'avconv' or 'ffmpeg') + '] Destination: ' + new_path) - try: - self.run_ffmpeg(path, new_path, acodec, more_opts) - except: - etype,e,tb = sys.exc_info() - if isinstance(e, AudioConversionError): - self._downloader.to_stderr(u'ERROR: audio conversion failed: ' + e.message) - else: - self._downloader.to_stderr(u'ERROR: error running ' + (self._exes['avconv'] and 'avconv' or 'ffmpeg')) - return None - - # Try to update the date time for extracted audio file. - if information.get('filetime') is not None: - try: - os.utime(encodeFilename(new_path), (time.time(), information['filetime'])) - except: - self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file') - - if not self._keepvideo: - try: - os.remove(encodeFilename(path)) - except (IOError, OSError): - self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file') - return None - - information['filepath'] = new_path - return information + def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False, nopostoverwrites=False): + PostProcessor.__init__(self, downloader) + if preferredcodec is None: + preferredcodec = 'best' + self._preferredcodec = preferredcodec + self._preferredquality = preferredquality + self._keepvideo = keepvideo + self._nopostoverwrites = nopostoverwrites + self._exes = self.detect_executables() + + @staticmethod + def detect_executables(): + def executable(exe): + try: + subprocess.Popen([exe, '-version'], stdout=subprocess.PIPE, stderr=subprocess.PIPE).communicate() + except OSError: + return False + return exe + programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe'] + return dict((program, executable(program)) for program in programs) + + def get_audio_codec(self, path): + if not self._exes['ffprobe'] and not self._exes['avprobe']: return None + try: + cmd = [self._exes['avprobe'] or self._exes['ffprobe'], '-show_streams', '--', encodeFilename(path)] + handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE) + output = handle.communicate()[0] + if handle.wait() != 0: + return None + except (IOError, OSError): + return None + audio_codec = None + for line in output.decode('ascii', 'ignore').split('\n'): + if line.startswith('codec_name='): + audio_codec = line.split('=')[1].strip() + elif line.strip() == 'codec_type=audio' and audio_codec is not None: + return audio_codec + return None + + def run_ffmpeg(self, path, out_path, codec, more_opts): + if not self._exes['ffmpeg'] and not self._exes['avconv']: + raise AudioConversionError('ffmpeg or avconv not found. Please install one.') + if codec is None: + acodec_opts = [] + else: + acodec_opts = ['-acodec', codec] + cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y', '-i', encodeFilename(path), '-vn'] + + acodec_opts + more_opts + + ['--', encodeFilename(out_path)]) + p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) + stdout,stderr = p.communicate() + if p.returncode != 0: + msg = stderr.strip().split('\n')[-1] + raise AudioConversionError(msg) + + def run(self, information): + path = information['filepath'] + + filecodec = self.get_audio_codec(path) + if filecodec is None: + self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe') + return None + + more_opts = [] + if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'): + if self._preferredcodec == 'm4a' and filecodec == 'aac': + # Lossless, but in another container + acodec = 'copy' + extension = self._preferredcodec + more_opts = [self._exes['avconv'] and '-bsf:a' or '-absf', 'aac_adtstoasc'] + elif filecodec in ['aac', 'mp3', 'vorbis']: + # Lossless if possible + acodec = 'copy' + extension = filecodec + if filecodec == 'aac': + more_opts = ['-f', 'adts'] + if filecodec == 'vorbis': + extension = 'ogg' + else: + # MP3 otherwise. + acodec = 'libmp3lame' + extension = 'mp3' + more_opts = [] + if self._preferredquality is not None: + if int(self._preferredquality) < 10: + more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality] + else: + more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality + 'k'] + else: + # We convert the audio (lossy) + acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec] + extension = self._preferredcodec + more_opts = [] + if self._preferredquality is not None: + if int(self._preferredquality) < 10: + more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality] + else: + more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality + 'k'] + if self._preferredcodec == 'aac': + more_opts += ['-f', 'adts'] + if self._preferredcodec == 'm4a': + more_opts += [self._exes['avconv'] and '-bsf:a' or '-absf', 'aac_adtstoasc'] + if self._preferredcodec == 'vorbis': + extension = 'ogg' + if self._preferredcodec == 'wav': + extension = 'wav' + more_opts += ['-f', 'wav'] + + prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups + new_path = prefix + sep + extension + try: + if self._nopostoverwrites and os.path.exists(encodeFilename(new_path)): + self._downloader.to_screen(u'[youtube] Post-process file %s exists, skipping' % new_path) + else: + self._downloader.to_screen(u'[' + (self._exes['avconv'] and 'avconv' or 'ffmpeg') + '] Destination: ' + new_path) + self.run_ffmpeg(path, new_path, acodec, more_opts) + except: + etype,e,tb = sys.exc_info() + if isinstance(e, AudioConversionError): + self._downloader.to_stderr(u'ERROR: audio conversion failed: ' + e.message) + else: + self._downloader.to_stderr(u'ERROR: error running ' + (self._exes['avconv'] and 'avconv' or 'ffmpeg')) + return None + + # Try to update the date time for extracted audio file. + if information.get('filetime') is not None: + try: + os.utime(encodeFilename(new_path), (time.time(), information['filetime'])) + except: + self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file') + + if not self._keepvideo: + try: + os.remove(encodeFilename(path)) + except (IOError, OSError): + self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file') + return None + + information['filepath'] = new_path + return information diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index e99ac2d59..1d914709f 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -2,33 +2,30 @@ # -*- coding: utf-8 -*- from __future__ import with_statement +from __future__ import absolute_import __authors__ = ( - 'Ricardo Garcia Gonzalez', - 'Danny Colligan', - 'Benjamin Johnson', - 'Vasyl\' Vavrychuk', - 'Witold Baryluk', - 'PaweÅ‚ Paprota', - 'Gergely Imreh', - 'Rogério Brito', - 'Philipp Hagemeister', - 'Sören Schulze', - 'Kevin Ngo', - 'Ori Avtalion', - 'shizeeg', - 'Filippo Valsorda', - ) + 'Ricardo Garcia Gonzalez', + 'Danny Colligan', + 'Benjamin Johnson', + 'Vasyl\' Vavrychuk', + 'Witold Baryluk', + 'PaweÅ‚ Paprota', + 'Gergely Imreh', + 'Rogério Brito', + 'Philipp Hagemeister', + 'Sören Schulze', + 'Kevin Ngo', + 'Ori Avtalion', + 'shizeeg', + 'Filippo Valsorda', + 'Christian Albrecht', + 'Dave Vasilevsky', + 'Jaime MarquÃnez Ferrándiz', + ) __license__ = 'Public Domain' -__version__ = '2012.10.09' -UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl' -UPDATE_URL_VERSION = 'https://raw.github.com/rg3/youtube-dl/master/LATEST_VERSION' -UPDATE_URL_EXE = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl.exe' - - -import cookielib import getpass import optparse import os @@ -37,530 +34,459 @@ import shlex import socket import subprocess import sys -import urllib2 import warnings +import platform -from utils import * -from FileDownloader import * -from InfoExtractors import * -from PostProcessor import * - -def updateSelf(downloader, filename): - ''' Update the program file with the latest version from the repository ''' - # Note: downloader only used for options - - if not os.access(filename, os.W_OK): - sys.exit('ERROR: no write permissions on %s' % filename) - - downloader.to_screen(u'Updating to latest version...') - - urlv = urllib2.urlopen(UPDATE_URL_VERSION) - newversion = urlv.read().strip() - if newversion == __version__: - downloader.to_screen(u'youtube-dl is up-to-date (' + __version__ + ')') - return - urlv.close() - - if hasattr(sys, "frozen"): #py2exe - exe = os.path.abspath(filename) - directory = os.path.dirname(exe) - if not os.access(directory, os.W_OK): - sys.exit('ERROR: no write permissions on %s' % directory) - - try: - urlh = urllib2.urlopen(UPDATE_URL_EXE) - newcontent = urlh.read() - urlh.close() - with open(exe + '.new', 'wb') as outf: - outf.write(newcontent) - except (IOError, OSError), err: - sys.exit('ERROR: unable to download latest version') - - try: - bat = os.path.join(directory, 'youtube-dl-updater.bat') - b = open(bat, 'w') - - print >> b, """ -echo Updating youtube-dl... -ping 127.0.0.1 -n 5 -w 1000 > NUL -move /Y "%s.new" "%s" -del "%s" - """ %(exe, exe, bat) - - b.close() - - os.startfile(bat) - except (IOError, OSError), err: - sys.exit('ERROR: unable to overwrite current version') - - else: - try: - urlh = urllib2.urlopen(UPDATE_URL) - newcontent = urlh.read() - urlh.close() - except (IOError, OSError), err: - sys.exit('ERROR: unable to download latest version') - - try: - with open(filename, 'wb') as outf: - outf.write(newcontent) - except (IOError, OSError), err: - sys.exit('ERROR: unable to overwrite current version') - - downloader.to_screen(u'Updated youtube-dl. Restart youtube-dl to use the new version.') +from .utils import * +from .update import update_self +from .version import __version__ +from .FileDownloader import * +from .InfoExtractors import gen_extractors +from .PostProcessor import * def parseOpts(): - def _readOptions(filename_bytes): - try: - optionf = open(filename_bytes) - except IOError: - return [] # silently skip if file is not present - try: - res = [] - for l in optionf: - res += shlex.split(l, comments=True) - finally: - optionf.close() - return res - - def _format_option_string(option): - ''' ('-o', '--option') -> -o, --format METAVAR''' - - opts = [] - - if option._short_opts: opts.append(option._short_opts[0]) - if option._long_opts: opts.append(option._long_opts[0]) - if len(opts) > 1: opts.insert(1, ', ') - - if option.takes_value(): opts.append(' %s' % option.metavar) - - return "".join(opts) - - def _find_term_columns(): - columns = os.environ.get('COLUMNS', None) - if columns: - return int(columns) - - try: - sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE) - out,err = sp.communicate() - return int(out.split()[1]) - except: - pass - return None - - max_width = 80 - max_help_position = 80 - - # No need to wrap help messages if we're on a wide console - columns = _find_term_columns() - if columns: max_width = columns - - fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position) - fmt.format_option_strings = _format_option_string - - kw = { - 'version' : __version__, - 'formatter' : fmt, - 'usage' : '%prog [options] url [url...]', - 'conflict_handler' : 'resolve', - } - - parser = optparse.OptionParser(**kw) - - # option groups - general = optparse.OptionGroup(parser, 'General Options') - selection = optparse.OptionGroup(parser, 'Video Selection') - authentication = optparse.OptionGroup(parser, 'Authentication Options') - video_format = optparse.OptionGroup(parser, 'Video Format Options') - postproc = optparse.OptionGroup(parser, 'Post-processing Options') - filesystem = optparse.OptionGroup(parser, 'Filesystem Options') - verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') - - general.add_option('-h', '--help', - action='help', help='print this help text and exit') - general.add_option('-v', '--version', - action='version', help='print program version and exit') - general.add_option('-U', '--update', - action='store_true', dest='update_self', help='update this program to latest version') - general.add_option('-i', '--ignore-errors', - action='store_true', dest='ignoreerrors', help='continue on download errors', default=False) - general.add_option('-r', '--rate-limit', - dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)') - general.add_option('-R', '--retries', - dest='retries', metavar='RETRIES', help='number of retries (default is %default)', default=10) - general.add_option('--dump-user-agent', - action='store_true', dest='dump_user_agent', - help='display the current browser identification', default=False) - general.add_option('--user-agent', - dest='user_agent', help='specify a custom user agent', metavar='UA') - general.add_option('--list-extractors', - action='store_true', dest='list_extractors', - help='List all supported extractors and the URLs they would handle', default=False) - - selection.add_option('--playlist-start', - dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is %default)', default=1) - selection.add_option('--playlist-end', - dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1) - selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)') - selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)') - selection.add_option('--max-downloads', metavar='NUMBER', dest='max_downloads', help='Abort after downloading NUMBER files', default=None) - - authentication.add_option('-u', '--username', - dest='username', metavar='USERNAME', help='account username') - authentication.add_option('-p', '--password', - dest='password', metavar='PASSWORD', help='account password') - authentication.add_option('-n', '--netrc', - action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False) - - - video_format.add_option('-f', '--format', - action='store', dest='format', metavar='FORMAT', help='video format code') - video_format.add_option('--all-formats', - action='store_const', dest='format', help='download all available video formats', const='all') - video_format.add_option('--prefer-free-formats', - action='store_true', dest='prefer_free_formats', default=False, help='prefer free video formats unless a specific one is requested') - video_format.add_option('--max-quality', - action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') - video_format.add_option('-F', '--list-formats', - action='store_true', dest='listformats', help='list all available formats (currently youtube only)') - video_format.add_option('--write-srt', - action='store_true', dest='writesubtitles', - help='write video closed captions to a .srt file (currently youtube only)', default=False) - video_format.add_option('--srt-lang', - action='store', dest='subtitleslang', metavar='LANG', - help='language of the closed captions to download (optional) use IETF language tags like \'en\'') - - - verbosity.add_option('-q', '--quiet', - action='store_true', dest='quiet', help='activates quiet mode', default=False) - verbosity.add_option('-s', '--simulate', - action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False) - verbosity.add_option('--skip-download', - action='store_true', dest='skip_download', help='do not download the video', default=False) - verbosity.add_option('-g', '--get-url', - action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False) - verbosity.add_option('-e', '--get-title', - action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False) - verbosity.add_option('--get-thumbnail', - action='store_true', dest='getthumbnail', - help='simulate, quiet but print thumbnail URL', default=False) - verbosity.add_option('--get-description', - action='store_true', dest='getdescription', - help='simulate, quiet but print video description', default=False) - verbosity.add_option('--get-filename', - action='store_true', dest='getfilename', - help='simulate, quiet but print output filename', default=False) - verbosity.add_option('--get-format', - action='store_true', dest='getformat', - help='simulate, quiet but print output format', default=False) - verbosity.add_option('--no-progress', - action='store_true', dest='noprogress', help='do not print progress bar', default=False) - verbosity.add_option('--console-title', - action='store_true', dest='consoletitle', - help='display progress in console titlebar', default=False) - verbosity.add_option('-v', '--verbose', - action='store_true', dest='verbose', help='print various debugging information', default=False) - - - filesystem.add_option('-t', '--title', - action='store_true', dest='usetitle', help='use title in file name', default=False) - filesystem.add_option('--id', - action='store_true', dest='useid', help='use video ID in file name', default=False) - filesystem.add_option('-l', '--literal', - action='store_true', dest='useliteral', help='use literal title in file name', default=False) - filesystem.add_option('-A', '--auto-number', - action='store_true', dest='autonumber', - help='number downloaded files starting from 00000', default=False) - filesystem.add_option('-o', '--output', - dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id and %% for a literal percent. Use - to output to stdout.') - filesystem.add_option('-a', '--batch-file', - dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)') - filesystem.add_option('-w', '--no-overwrites', - action='store_true', dest='nooverwrites', help='do not overwrite files', default=False) - filesystem.add_option('-c', '--continue', - action='store_true', dest='continue_dl', help='resume partially downloaded files', default=True) - filesystem.add_option('--no-continue', - action='store_false', dest='continue_dl', - help='do not resume partially downloaded files (restart from beginning)') - filesystem.add_option('--cookies', - dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in') - filesystem.add_option('--no-part', - action='store_true', dest='nopart', help='do not use .part files', default=False) - filesystem.add_option('--no-mtime', - action='store_false', dest='updatetime', - help='do not use the Last-modified header to set the file modification time', default=True) - filesystem.add_option('--write-description', - action='store_true', dest='writedescription', - help='write video description to a .description file', default=False) - filesystem.add_option('--write-info-json', - action='store_true', dest='writeinfojson', - help='write video metadata to a .info.json file', default=False) - - - postproc.add_option('-x', '--extract-audio', action='store_true', dest='extractaudio', default=False, - help='convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)') - postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best', - help='"best", "aac", "vorbis", "mp3", "m4a", or "wav"; best by default') - postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='5', - help='ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default 5)') - postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False, - help='keeps the video file on disk after the post-processing; the video is erased by default') - - - parser.add_option_group(general) - parser.add_option_group(selection) - parser.add_option_group(filesystem) - parser.add_option_group(verbosity) - parser.add_option_group(video_format) - parser.add_option_group(authentication) - parser.add_option_group(postproc) - - xdg_config_home = os.environ.get('XDG_CONFIG_HOME') - if xdg_config_home: - userConf = os.path.join(xdg_config_home, 'youtube-dl.conf') - else: - userConf = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf') - argv = _readOptions('/etc/youtube-dl.conf') + _readOptions(userConf) + sys.argv[1:] - opts, args = parser.parse_args(argv) - - return parser, opts, args - -def gen_extractors(): - """ Return a list of an instance of every supported extractor. - The order does matter; the first extractor matched is the one handling the URL. - """ - return [ - YoutubePlaylistIE(), - YoutubeChannelIE(), - YoutubeUserIE(), - YoutubeSearchIE(), - YoutubeIE(), - MetacafeIE(), - DailymotionIE(), - GoogleIE(), - GoogleSearchIE(), - PhotobucketIE(), - YahooIE(), - YahooSearchIE(), - DepositFilesIE(), - FacebookIE(), - BlipTVUserIE(), - BlipTVIE(), - VimeoIE(), - MyVideoIE(), - ComedyCentralIE(), - EscapistIE(), - CollegeHumorIE(), - XVideosIE(), - SoundcloudIE(), - InfoQIE(), - MixcloudIE(), - StanfordOpenClassroomIE(), - MTVIE(), - YoukuIE(), - XNXXIE(), - GooglePlusIE(), - PornotubeIE(), - YouPornIE(), - YouJizzIE(), - GenericIE() - ] + def _readOptions(filename_bytes): + try: + optionf = open(filename_bytes) + except IOError: + return [] # silently skip if file is not present + try: + res = [] + for l in optionf: + res += shlex.split(l, comments=True) + finally: + optionf.close() + return res + + def _format_option_string(option): + ''' ('-o', '--option') -> -o, --format METAVAR''' + + opts = [] + + if option._short_opts: + opts.append(option._short_opts[0]) + if option._long_opts: + opts.append(option._long_opts[0]) + if len(opts) > 1: + opts.insert(1, ', ') + + if option.takes_value(): opts.append(' %s' % option.metavar) + + return "".join(opts) + + def _find_term_columns(): + columns = os.environ.get('COLUMNS', None) + if columns: + return int(columns) + + try: + sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE) + out,err = sp.communicate() + return int(out.split()[1]) + except: + pass + return None + + max_width = 80 + max_help_position = 80 + + # No need to wrap help messages if we're on a wide console + columns = _find_term_columns() + if columns: max_width = columns + + fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position) + fmt.format_option_strings = _format_option_string + + kw = { + 'version' : __version__, + 'formatter' : fmt, + 'usage' : '%prog [options] url [url...]', + 'conflict_handler' : 'resolve', + } + + parser = optparse.OptionParser(**kw) + + # option groups + general = optparse.OptionGroup(parser, 'General Options') + selection = optparse.OptionGroup(parser, 'Video Selection') + authentication = optparse.OptionGroup(parser, 'Authentication Options') + video_format = optparse.OptionGroup(parser, 'Video Format Options') + postproc = optparse.OptionGroup(parser, 'Post-processing Options') + filesystem = optparse.OptionGroup(parser, 'Filesystem Options') + verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') + + general.add_option('-h', '--help', + action='help', help='print this help text and exit') + general.add_option('-v', '--version', + action='version', help='print program version and exit') + general.add_option('-U', '--update', + action='store_true', dest='update_self', help='update this program to latest version') + general.add_option('-i', '--ignore-errors', + action='store_true', dest='ignoreerrors', help='continue on download errors', default=False) + general.add_option('-r', '--rate-limit', + dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)') + general.add_option('-R', '--retries', + dest='retries', metavar='RETRIES', help='number of retries (default is %default)', default=10) + general.add_option('--buffer-size', + dest='buffersize', metavar='SIZE', help='size of download buffer (e.g. 1024 or 16k) (default is %default)', default="1024") + general.add_option('--no-resize-buffer', + action='store_true', dest='noresizebuffer', + help='do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.', default=False) + general.add_option('--dump-user-agent', + action='store_true', dest='dump_user_agent', + help='display the current browser identification', default=False) + general.add_option('--user-agent', + dest='user_agent', help='specify a custom user agent', metavar='UA') + general.add_option('--list-extractors', + action='store_true', dest='list_extractors', + help='List all supported extractors and the URLs they would handle', default=False) + general.add_option('--test', action='store_true', dest='test', default=False, help=optparse.SUPPRESS_HELP) + + selection.add_option('--playlist-start', + dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is %default)', default=1) + selection.add_option('--playlist-end', + dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1) + selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)') + selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)') + selection.add_option('--max-downloads', metavar='NUMBER', dest='max_downloads', help='Abort after downloading NUMBER files', default=None) + + authentication.add_option('-u', '--username', + dest='username', metavar='USERNAME', help='account username') + authentication.add_option('-p', '--password', + dest='password', metavar='PASSWORD', help='account password') + authentication.add_option('-n', '--netrc', + action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False) + + + video_format.add_option('-f', '--format', + action='store', dest='format', metavar='FORMAT', help='video format code') + video_format.add_option('--all-formats', + action='store_const', dest='format', help='download all available video formats', const='all') + video_format.add_option('--prefer-free-formats', + action='store_true', dest='prefer_free_formats', default=False, help='prefer free video formats unless a specific one is requested') + video_format.add_option('--max-quality', + action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') + video_format.add_option('-F', '--list-formats', + action='store_true', dest='listformats', help='list all available formats (currently youtube only)') + video_format.add_option('--write-srt', + action='store_true', dest='writesubtitles', + help='write video closed captions to a .srt file (currently youtube only)', default=False) + video_format.add_option('--srt-lang', + action='store', dest='subtitleslang', metavar='LANG', + help='language of the closed captions to download (optional) use IETF language tags like \'en\'') + + + verbosity.add_option('-q', '--quiet', + action='store_true', dest='quiet', help='activates quiet mode', default=False) + verbosity.add_option('-s', '--simulate', + action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False) + verbosity.add_option('--skip-download', + action='store_true', dest='skip_download', help='do not download the video', default=False) + verbosity.add_option('-g', '--get-url', + action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False) + verbosity.add_option('-e', '--get-title', + action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False) + verbosity.add_option('--get-thumbnail', + action='store_true', dest='getthumbnail', + help='simulate, quiet but print thumbnail URL', default=False) + verbosity.add_option('--get-description', + action='store_true', dest='getdescription', + help='simulate, quiet but print video description', default=False) + verbosity.add_option('--get-filename', + action='store_true', dest='getfilename', + help='simulate, quiet but print output filename', default=False) + verbosity.add_option('--get-format', + action='store_true', dest='getformat', + help='simulate, quiet but print output format', default=False) + verbosity.add_option('--no-progress', + action='store_true', dest='noprogress', help='do not print progress bar', default=False) + verbosity.add_option('--console-title', + action='store_true', dest='consoletitle', + help='display progress in console titlebar', default=False) + verbosity.add_option('-v', '--verbose', + action='store_true', dest='verbose', help='print various debugging information', default=False) + + + filesystem.add_option('-t', '--title', + action='store_true', dest='usetitle', help='use title in file name', default=False) + filesystem.add_option('--id', + action='store_true', dest='useid', help='use video ID in file name', default=False) + filesystem.add_option('-l', '--literal', + action='store_true', dest='usetitle', help='[deprecated] alias of --title', default=False) + filesystem.add_option('-A', '--auto-number', + action='store_true', dest='autonumber', + help='number downloaded files starting from 00000', default=False) + filesystem.add_option('-o', '--output', + dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id and %% for a literal percent. Use - to output to stdout. Can also be used to download to a different directory, for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .') + filesystem.add_option('--restrict-filenames', + action='store_true', dest='restrictfilenames', + help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False) + filesystem.add_option('-a', '--batch-file', + dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)') + filesystem.add_option('-w', '--no-overwrites', + action='store_true', dest='nooverwrites', help='do not overwrite files', default=False) + filesystem.add_option('-c', '--continue', + action='store_true', dest='continue_dl', help='resume partially downloaded files', default=True) + filesystem.add_option('--no-continue', + action='store_false', dest='continue_dl', + help='do not resume partially downloaded files (restart from beginning)') + filesystem.add_option('--cookies', + dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in') + filesystem.add_option('--no-part', + action='store_true', dest='nopart', help='do not use .part files', default=False) + filesystem.add_option('--no-mtime', + action='store_false', dest='updatetime', + help='do not use the Last-modified header to set the file modification time', default=True) + filesystem.add_option('--write-description', + action='store_true', dest='writedescription', + help='write video description to a .description file', default=False) + filesystem.add_option('--write-info-json', + action='store_true', dest='writeinfojson', + help='write video metadata to a .info.json file', default=False) + + + postproc.add_option('-x', '--extract-audio', action='store_true', dest='extractaudio', default=False, + help='convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)') + postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best', + help='"best", "aac", "vorbis", "mp3", "m4a", or "wav"; best by default') + postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='5', + help='ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default 5)') + postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False, + help='keeps the video file on disk after the post-processing; the video is erased by default') + postproc.add_option('--no-post-overwrites', action='store_true', dest='nopostoverwrites', default=False, + help='do not overwrite post-processed files; the post-processed files are overwritten by default') + + + parser.add_option_group(general) + parser.add_option_group(selection) + parser.add_option_group(filesystem) + parser.add_option_group(verbosity) + parser.add_option_group(video_format) + parser.add_option_group(authentication) + parser.add_option_group(postproc) + + xdg_config_home = os.environ.get('XDG_CONFIG_HOME') + if xdg_config_home: + userConf = os.path.join(xdg_config_home, 'youtube-dl.conf') + else: + userConf = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf') + argv = _readOptions('/etc/youtube-dl.conf') + _readOptions(userConf) + sys.argv[1:] + opts, args = parser.parse_args(argv) + + return parser, opts, args def _real_main(): - parser, opts, args = parseOpts() - - # Open appropriate CookieJar - if opts.cookiefile is None: - jar = cookielib.CookieJar() - else: - try: - jar = cookielib.MozillaCookieJar(opts.cookiefile) - if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK): - jar.load() - except (IOError, OSError), err: - sys.exit(u'ERROR: unable to open cookie file') - # Set user agent - if opts.user_agent is not None: - std_headers['User-Agent'] = opts.user_agent - - # Dump user agent - if opts.dump_user_agent: - print std_headers['User-Agent'] - sys.exit(0) - - # Batch file verification - batchurls = [] - if opts.batchfile is not None: - try: - if opts.batchfile == '-': - batchfd = sys.stdin - else: - batchfd = open(opts.batchfile, 'r') - batchurls = batchfd.readlines() - batchurls = [x.strip() for x in batchurls] - batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)] - except IOError: - sys.exit(u'ERROR: batch file could not be read') - all_urls = batchurls + args - all_urls = map(lambda url: url.strip(), all_urls) - - # General configuration - cookie_processor = urllib2.HTTPCookieProcessor(jar) - proxy_handler = urllib2.ProxyHandler() - opener = urllib2.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler()) - urllib2.install_opener(opener) - socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words) - - extractors = gen_extractors() - - if opts.list_extractors: - for ie in extractors: - print(ie.IE_NAME) - matchedUrls = filter(lambda url: ie.suitable(url), all_urls) - all_urls = filter(lambda url: url not in matchedUrls, all_urls) - for mu in matchedUrls: - print(u' ' + mu) - sys.exit(0) - - # Conflicting, missing and erroneous options - if opts.usenetrc and (opts.username is not None or opts.password is not None): - parser.error(u'using .netrc conflicts with giving username/password') - if opts.password is not None and opts.username is None: - parser.error(u'account username missing') - if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber or opts.useid): - parser.error(u'using output template conflicts with using title, literal title, video ID or auto number') - if opts.usetitle and opts.useliteral: - parser.error(u'using title conflicts with using literal title') - if opts.usetitle and opts.useid: - parser.error(u'using title conflicts with using video ID') - if opts.useliteral and opts.useid: - parser.error(u'using literal title conflicts with using video ID') - if opts.username is not None and opts.password is None: - opts.password = getpass.getpass(u'Type account password and press return:') - if opts.ratelimit is not None: - numeric_limit = FileDownloader.parse_bytes(opts.ratelimit) - if numeric_limit is None: - parser.error(u'invalid rate limit specified') - opts.ratelimit = numeric_limit - if opts.retries is not None: - try: - opts.retries = long(opts.retries) - except (TypeError, ValueError), err: - parser.error(u'invalid retry count specified') - try: - opts.playliststart = int(opts.playliststart) - if opts.playliststart <= 0: - raise ValueError(u'Playlist start must be positive') - except (TypeError, ValueError), err: - parser.error(u'invalid playlist start number specified') - try: - opts.playlistend = int(opts.playlistend) - if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart): - raise ValueError(u'Playlist end must be greater than playlist start') - except (TypeError, ValueError), err: - parser.error(u'invalid playlist end number specified') - if opts.extractaudio: - if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis', 'm4a', 'wav']: - parser.error(u'invalid audio format specified') - if opts.audioquality: - opts.audioquality = opts.audioquality.strip('k').strip('K') - if not opts.audioquality.isdigit(): - parser.error(u'invalid audio quality specified') - - # File downloader - fd = FileDownloader({ - 'usenetrc': opts.usenetrc, - 'username': opts.username, - 'password': opts.password, - 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat), - 'forceurl': opts.geturl, - 'forcetitle': opts.gettitle, - 'forcethumbnail': opts.getthumbnail, - 'forcedescription': opts.getdescription, - 'forcefilename': opts.getfilename, - 'forceformat': opts.getformat, - 'simulate': opts.simulate, - 'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat), - 'format': opts.format, - 'format_limit': opts.format_limit, - 'listformats': opts.listformats, - 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding())) - or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s') - or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s') - or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s') - or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s') - or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s') - or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s') - or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s') - or (opts.useid and u'%(id)s.%(ext)s') - or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s') - or u'%(id)s.%(ext)s'), - 'ignoreerrors': opts.ignoreerrors, - 'ratelimit': opts.ratelimit, - 'nooverwrites': opts.nooverwrites, - 'retries': opts.retries, - 'continuedl': opts.continue_dl, - 'noprogress': opts.noprogress, - 'playliststart': opts.playliststart, - 'playlistend': opts.playlistend, - 'logtostderr': opts.outtmpl == '-', - 'consoletitle': opts.consoletitle, - 'nopart': opts.nopart, - 'updatetime': opts.updatetime, - 'writedescription': opts.writedescription, - 'writeinfojson': opts.writeinfojson, - 'writesubtitles': opts.writesubtitles, - 'subtitleslang': opts.subtitleslang, - 'matchtitle': opts.matchtitle, - 'rejecttitle': opts.rejecttitle, - 'max_downloads': opts.max_downloads, - 'prefer_free_formats': opts.prefer_free_formats, - 'verbose': opts.verbose, - }) - - if opts.verbose: - fd.to_screen(u'[debug] Proxy map: ' + str(proxy_handler.proxies)) - - for extractor in extractors: - fd.add_info_extractor(extractor) - - # PostProcessors - if opts.extractaudio: - fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, keepvideo=opts.keepvideo)) - - # Update version - if opts.update_self: - updateSelf(fd, sys.argv[0]) - - # Maybe do nothing - if len(all_urls) < 1: - if not opts.update_self: - parser.error(u'you must provide at least one URL') - else: - sys.exit() - - try: - retcode = fd.download(all_urls) - except MaxDownloadsReached: - fd.to_screen(u'--max-download limit reached, aborting.') - retcode = 101 - - # Dump cookie jar if requested - if opts.cookiefile is not None: - try: - jar.save() - except (IOError, OSError), err: - sys.exit(u'ERROR: unable to save cookie jar') - - sys.exit(retcode) + parser, opts, args = parseOpts() + + # Open appropriate CookieJar + if opts.cookiefile is None: + jar = compat_cookiejar.CookieJar() + else: + try: + jar = compat_cookiejar.MozillaCookieJar(opts.cookiefile) + if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK): + jar.load() + except (IOError, OSError) as err: + sys.exit(u'ERROR: unable to open cookie file') + # Set user agent + if opts.user_agent is not None: + std_headers['User-Agent'] = opts.user_agent + + # Dump user agent + if opts.dump_user_agent: + print(std_headers['User-Agent']) + sys.exit(0) + + # Batch file verification + batchurls = [] + if opts.batchfile is not None: + try: + if opts.batchfile == '-': + batchfd = sys.stdin + else: + batchfd = open(opts.batchfile, 'r') + batchurls = batchfd.readlines() + batchurls = [x.strip() for x in batchurls] + batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)] + except IOError: + sys.exit(u'ERROR: batch file could not be read') + all_urls = batchurls + args + all_urls = [url.strip() for url in all_urls] + + # General configuration + cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar) + proxy_handler = compat_urllib_request.ProxyHandler() + opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler()) + compat_urllib_request.install_opener(opener) + socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words) + + extractors = gen_extractors() + + if opts.list_extractors: + for ie in extractors: + print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '')) + matchedUrls = [url for url in all_urls if ie.suitable(url)] + all_urls = [url for url in all_urls if url not in matchedUrls] + for mu in matchedUrls: + print(u' ' + mu) + sys.exit(0) + + # Conflicting, missing and erroneous options + if opts.usenetrc and (opts.username is not None or opts.password is not None): + parser.error(u'using .netrc conflicts with giving username/password') + if opts.password is not None and opts.username is None: + parser.error(u'account username missing') + if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid): + parser.error(u'using output template conflicts with using title, video ID or auto number') + if opts.usetitle and opts.useid: + parser.error(u'using title conflicts with using video ID') + if opts.username is not None and opts.password is None: + opts.password = getpass.getpass(u'Type account password and press return:') + if opts.ratelimit is not None: + numeric_limit = FileDownloader.parse_bytes(opts.ratelimit) + if numeric_limit is None: + parser.error(u'invalid rate limit specified') + opts.ratelimit = numeric_limit + if opts.retries is not None: + try: + opts.retries = int(opts.retries) + except (TypeError, ValueError) as err: + parser.error(u'invalid retry count specified') + if opts.buffersize is not None: + numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize) + if numeric_buffersize is None: + parser.error(u'invalid buffer size specified') + opts.buffersize = numeric_buffersize + try: + opts.playliststart = int(opts.playliststart) + if opts.playliststart <= 0: + raise ValueError(u'Playlist start must be positive') + except (TypeError, ValueError) as err: + parser.error(u'invalid playlist start number specified') + try: + opts.playlistend = int(opts.playlistend) + if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart): + raise ValueError(u'Playlist end must be greater than playlist start') + except (TypeError, ValueError) as err: + parser.error(u'invalid playlist end number specified') + if opts.extractaudio: + if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis', 'm4a', 'wav']: + parser.error(u'invalid audio format specified') + if opts.audioquality: + opts.audioquality = opts.audioquality.strip('k').strip('K') + if not opts.audioquality.isdigit(): + parser.error(u'invalid audio quality specified') + + if sys.version_info < (3,): + # In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems) + if opts.outtmpl is not None: + opts.outtmpl = opts.outtmpl.decode(preferredencoding()) + outtmpl =((opts.outtmpl is not None and opts.outtmpl) + or (opts.format == '-1' and opts.usetitle and u'%(title)s-%(id)s-%(format)s.%(ext)s') + or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s') + or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s') + or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s') + or (opts.useid and u'%(id)s.%(ext)s') + or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s') + or u'%(id)s.%(ext)s') + # File downloader + fd = FileDownloader({ + 'usenetrc': opts.usenetrc, + 'username': opts.username, + 'password': opts.password, + 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat), + 'forceurl': opts.geturl, + 'forcetitle': opts.gettitle, + 'forcethumbnail': opts.getthumbnail, + 'forcedescription': opts.getdescription, + 'forcefilename': opts.getfilename, + 'forceformat': opts.getformat, + 'simulate': opts.simulate, + 'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat), + 'format': opts.format, + 'format_limit': opts.format_limit, + 'listformats': opts.listformats, + 'outtmpl': outtmpl, + 'restrictfilenames': opts.restrictfilenames, + 'ignoreerrors': opts.ignoreerrors, + 'ratelimit': opts.ratelimit, + 'nooverwrites': opts.nooverwrites, + 'retries': opts.retries, + 'buffersize': opts.buffersize, + 'noresizebuffer': opts.noresizebuffer, + 'continuedl': opts.continue_dl, + 'noprogress': opts.noprogress, + 'playliststart': opts.playliststart, + 'playlistend': opts.playlistend, + 'logtostderr': opts.outtmpl == '-', + 'consoletitle': opts.consoletitle, + 'nopart': opts.nopart, + 'updatetime': opts.updatetime, + 'writedescription': opts.writedescription, + 'writeinfojson': opts.writeinfojson, + 'writesubtitles': opts.writesubtitles, + 'subtitleslang': opts.subtitleslang, + 'matchtitle': opts.matchtitle, + 'rejecttitle': opts.rejecttitle, + 'max_downloads': opts.max_downloads, + 'prefer_free_formats': opts.prefer_free_formats, + 'verbose': opts.verbose, + 'test': opts.test, + }) + + if opts.verbose: + fd.to_screen(u'[debug] youtube-dl version ' + __version__) + try: + sp = subprocess.Popen(['git', 'rev-parse', '--short', 'HEAD'], stdout=subprocess.PIPE, stderr=subprocess.PIPE, + cwd=os.path.dirname(os.path.abspath(__file__))) + out, err = sp.communicate() + out = out.decode().strip() + if re.match('[0-9a-f]+', out): + fd.to_screen(u'[debug] Git HEAD: ' + out) + except: + pass + fd.to_screen(u'[debug] Python version %s - %s' %(platform.python_version(), platform.platform())) + fd.to_screen(u'[debug] Proxy map: ' + str(proxy_handler.proxies)) + + for extractor in extractors: + fd.add_info_extractor(extractor) + + # PostProcessors + if opts.extractaudio: + fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, keepvideo=opts.keepvideo, nopostoverwrites=opts.nopostoverwrites)) + + # Update version + if opts.update_self: + update_self(fd.to_screen, opts.verbose, sys.argv[0]) + + # Maybe do nothing + if len(all_urls) < 1: + if not opts.update_self: + parser.error(u'you must provide at least one URL') + else: + sys.exit() + + try: + retcode = fd.download(all_urls) + except MaxDownloadsReached: + fd.to_screen(u'--max-download limit reached, aborting.') + retcode = 101 + + # Dump cookie jar if requested + if opts.cookiefile is not None: + try: + jar.save() + except (IOError, OSError) as err: + sys.exit(u'ERROR: unable to save cookie jar') + + sys.exit(retcode) def main(): - try: - _real_main() - except DownloadError: - sys.exit(1) - except SameFileError: - sys.exit(u'ERROR: fixed output name but more than one file to download') - except KeyboardInterrupt: - sys.exit(u'\nERROR: Interrupted by user') + try: + _real_main() + except DownloadError: + sys.exit(1) + except SameFileError: + sys.exit(u'ERROR: fixed output name but more than one file to download') + except KeyboardInterrupt: + sys.exit(u'\nERROR: Interrupted by user') diff --git a/youtube_dl/__main__.py b/youtube_dl/__main__.py index 6f20402e2..7022ea4be 100755 --- a/youtube_dl/__main__.py +++ b/youtube_dl/__main__.py @@ -1,7 +1,17 @@ #!/usr/bin/env python -# -*- coding: utf-8 -*- -import __init__ +# Execute with +# $ python youtube_dl/__main__.py (2.6+) +# $ python -m youtube_dl (2.7+) + +import sys + +if __package__ is None and not hasattr(sys, "frozen"): + # direct call of __main__.py + import os.path + sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +import youtube_dl if __name__ == '__main__': - __init__.main() + youtube_dl.main() diff --git a/youtube_dl/update.py b/youtube_dl/update.py new file mode 100644 index 000000000..f6e3e5c69 --- /dev/null +++ b/youtube_dl/update.py @@ -0,0 +1,160 @@ +import json +import traceback +import hashlib +from zipimport import zipimporter + +from .utils import * +from .version import __version__ + +def rsa_verify(message, signature, key): + from struct import pack + from hashlib import sha256 + from sys import version_info + def b(x): + if version_info[0] == 2: return x + else: return x.encode('latin1') + assert(type(message) == type(b(''))) + block_size = 0 + n = key[0] + while n: + block_size += 1 + n >>= 8 + signature = pow(int(signature, 16), key[1], key[0]) + raw_bytes = [] + while signature: + raw_bytes.insert(0, pack("B", signature & 0xFF)) + signature >>= 8 + signature = (block_size - len(raw_bytes)) * b('\x00') + b('').join(raw_bytes) + if signature[0:2] != b('\x00\x01'): return False + signature = signature[2:] + if not b('\x00') in signature: return False + signature = signature[signature.index(b('\x00'))+1:] + if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')): return False + signature = signature[19:] + if signature != sha256(message).digest(): return False + return True + +def update_self(to_screen, verbose, filename): + """Update the program file with the latest version from the repository""" + + UPDATE_URL = "http://rg3.github.com/youtube-dl/update/" + VERSION_URL = UPDATE_URL + 'LATEST_VERSION' + JSON_URL = UPDATE_URL + 'versions.json' + UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537) + + + if not isinstance(globals().get('__loader__'), zipimporter) and not hasattr(sys, "frozen"): + to_screen(u'It looks like you installed youtube-dl with pip, setup.py or a tarball. Please use that to update.') + return + + # Check if there is a new version + try: + newversion = compat_urllib_request.urlopen(VERSION_URL).read().decode('utf-8').strip() + except: + if verbose: to_screen(compat_str(traceback.format_exc())) + to_screen(u'ERROR: can\'t find the current version. Please try again later.') + return + if newversion == __version__: + to_screen(u'youtube-dl is up-to-date (' + __version__ + ')') + return + + # Download and check versions info + try: + versions_info = compat_urllib_request.urlopen(JSON_URL).read().decode('utf-8') + versions_info = json.loads(versions_info) + except: + if verbose: to_screen(compat_str(traceback.format_exc())) + to_screen(u'ERROR: can\'t obtain versions info. Please try again later.') + return + if not 'signature' in versions_info: + to_screen(u'ERROR: the versions file is not signed or corrupted. Aborting.') + return + signature = versions_info['signature'] + del versions_info['signature'] + if not rsa_verify(json.dumps(versions_info, sort_keys=True).encode('utf-8'), signature, UPDATES_RSA_KEY): + to_screen(u'ERROR: the versions file signature is invalid. Aborting.') + return + + to_screen(u'Updating to version ' + versions_info['latest'] + '...') + version = versions_info['versions'][versions_info['latest']] + if version.get('notes'): + to_screen(u'PLEASE NOTE:') + for note in version['notes']: + to_screen(note) + + if not os.access(filename, os.W_OK): + to_screen(u'ERROR: no write permissions on %s' % filename) + return + + # Py2EXE + if hasattr(sys, "frozen"): + exe = os.path.abspath(filename) + directory = os.path.dirname(exe) + if not os.access(directory, os.W_OK): + to_screen(u'ERROR: no write permissions on %s' % directory) + return + + try: + urlh = compat_urllib_request.urlopen(version['exe'][0]) + newcontent = urlh.read() + urlh.close() + except (IOError, OSError) as err: + if verbose: to_screen(compat_str(traceback.format_exc())) + to_screen(u'ERROR: unable to download latest version') + return + + newcontent_hash = hashlib.sha256(newcontent).hexdigest() + if newcontent_hash != version['exe'][1]: + to_screen(u'ERROR: the downloaded file hash does not match. Aborting.') + return + + try: + with open(exe + '.new', 'wb') as outf: + outf.write(newcontent) + except (IOError, OSError) as err: + if verbose: to_screen(compat_str(traceback.format_exc())) + to_screen(u'ERROR: unable to write the new version') + return + + try: + bat = os.path.join(directory, 'youtube-dl-updater.bat') + b = open(bat, 'w') + b.write(""" +echo Updating youtube-dl... +ping 127.0.0.1 -n 5 -w 1000 > NUL +move /Y "%s.new" "%s" +del "%s" + \n""" %(exe, exe, bat)) + b.close() + + os.startfile(bat) + except (IOError, OSError) as err: + if verbose: to_screen(compat_str(traceback.format_exc())) + to_screen(u'ERROR: unable to overwrite current version') + return + + # Zip unix package + elif isinstance(globals().get('__loader__'), zipimporter): + try: + urlh = compat_urllib_request.urlopen(version['bin'][0]) + newcontent = urlh.read() + urlh.close() + except (IOError, OSError) as err: + if verbose: to_screen(compat_str(traceback.format_exc())) + to_screen(u'ERROR: unable to download latest version') + return + + newcontent_hash = hashlib.sha256(newcontent).hexdigest() + if newcontent_hash != version['bin'][1]: + to_screen(u'ERROR: the downloaded file hash does not match. Aborting.') + return + + try: + with open(filename, 'wb') as outf: + outf.write(newcontent) + except (IOError, OSError) as err: + if verbose: to_screen(compat_str(traceback.format_exc())) + to_screen(u'ERROR: unable to overwrite current version') + return + + to_screen(u'Updated youtube-dl. Restart youtube-dl to use the new version.') diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 56d046145..8f856ee8c 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -2,363 +2,542 @@ # -*- coding: utf-8 -*- import gzip -import htmlentitydefs -import HTMLParser +import io +import json import locale import os import re import sys +import traceback import zlib -import urllib2 import email.utils import json try: - import cStringIO as StringIO + import urllib.request as compat_urllib_request +except ImportError: # Python 2 + import urllib2 as compat_urllib_request + +try: + import urllib.error as compat_urllib_error +except ImportError: # Python 2 + import urllib2 as compat_urllib_error + +try: + import urllib.parse as compat_urllib_parse +except ImportError: # Python 2 + import urllib as compat_urllib_parse + +try: + from urllib.parse import urlparse as compat_urllib_parse_urlparse +except ImportError: # Python 2 + from urlparse import urlparse as compat_urllib_parse_urlparse + +try: + import http.cookiejar as compat_cookiejar +except ImportError: # Python 2 + import cookielib as compat_cookiejar + +try: + import html.entities as compat_html_entities +except ImportError: # Python 2 + import htmlentitydefs as compat_html_entities + +try: + import html.parser as compat_html_parser +except ImportError: # Python 2 + import HTMLParser as compat_html_parser + +try: + import http.client as compat_http_client +except ImportError: # Python 2 + import httplib as compat_http_client + +try: + from subprocess import DEVNULL + compat_subprocess_get_DEVNULL = lambda: DEVNULL except ImportError: - import StringIO + compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w') + +try: + from urllib.parse import parse_qs as compat_parse_qs +except ImportError: # Python 2 + # HACK: The following is the correct parse_qs implementation from cpython 3's stdlib. + # Python 2's version is apparently totally broken + def _unquote(string, encoding='utf-8', errors='replace'): + if string == '': + return string + res = string.split('%') + if len(res) == 1: + return string + if encoding is None: + encoding = 'utf-8' + if errors is None: + errors = 'replace' + # pct_sequence: contiguous sequence of percent-encoded bytes, decoded + pct_sequence = b'' + string = res[0] + for item in res[1:]: + try: + if not item: + raise ValueError + pct_sequence += item[:2].decode('hex') + rest = item[2:] + if not rest: + # This segment was just a single percent-encoded character. + # May be part of a sequence of code units, so delay decoding. + # (Stored in pct_sequence). + continue + except ValueError: + rest = '%' + item + # Encountered non-percent-encoded characters. Flush the current + # pct_sequence. + string += pct_sequence.decode(encoding, errors) + rest + pct_sequence = b'' + if pct_sequence: + # Flush the final pct_sequence + string += pct_sequence.decode(encoding, errors) + return string + + def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False, + encoding='utf-8', errors='replace'): + qs, _coerce_result = qs, unicode + pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')] + r = [] + for name_value in pairs: + if not name_value and not strict_parsing: + continue + nv = name_value.split('=', 1) + if len(nv) != 2: + if strict_parsing: + raise ValueError("bad query field: %r" % (name_value,)) + # Handle case of a control-name with no equal sign + if keep_blank_values: + nv.append('') + else: + continue + if len(nv[1]) or keep_blank_values: + name = nv[0].replace('+', ' ') + name = _unquote(name, encoding=encoding, errors=errors) + name = _coerce_result(name) + value = nv[1].replace('+', ' ') + value = _unquote(value, encoding=encoding, errors=errors) + value = _coerce_result(value) + r.append((name, value)) + return r + + def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False, + encoding='utf-8', errors='replace'): + parsed_result = {} + pairs = _parse_qsl(qs, keep_blank_values, strict_parsing, + encoding=encoding, errors=errors) + for name, value in pairs: + if name in parsed_result: + parsed_result[name].append(value) + else: + parsed_result[name] = [value] + return parsed_result + +try: + compat_str = unicode # Python 2 +except NameError: + compat_str = str + +try: + compat_chr = unichr # Python 2 +except NameError: + compat_chr = chr std_headers = { - 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0', - 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', - 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', - 'Accept-Encoding': 'gzip, deflate', - 'Accept-Language': 'en-us,en;q=0.5', + 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0', + 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', + 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', + 'Accept-Encoding': 'gzip, deflate', + 'Accept-Language': 'en-us,en;q=0.5', } def preferredencoding(): - """Get preferred encoding. - - Returns the best encoding scheme for the system, based on - locale.getpreferredencoding() and some further tweaks. - """ - def yield_preferredencoding(): - try: - pref = locale.getpreferredencoding() - u'TEST'.encode(pref) - except: - pref = 'UTF-8' - while True: - yield pref - return yield_preferredencoding().next() - + """Get preferred encoding. + + Returns the best encoding scheme for the system, based on + locale.getpreferredencoding() and some further tweaks. + """ + try: + pref = locale.getpreferredencoding() + u'TEST'.encode(pref) + except: + pref = 'UTF-8' + + return pref + +if sys.version_info < (3,0): + def compat_print(s): + print(s.encode(preferredencoding(), 'xmlcharrefreplace')) +else: + def compat_print(s): + assert type(s) == type(u'') + print(s) + +# In Python 2.x, json.dump expects a bytestream. +# In Python 3.x, it writes to a character stream +if sys.version_info < (3,0): + def write_json_file(obj, fn): + with open(fn, 'wb') as f: + json.dump(obj, f) +else: + def write_json_file(obj, fn): + with open(fn, 'w', encoding='utf-8') as f: + json.dump(obj, f) def htmlentity_transform(matchobj): - """Transforms an HTML entity to a Unicode character. - - This function receives a match object and is intended to be used with - the re.sub() function. - """ - entity = matchobj.group(1) - - # Known non-numeric HTML entity - if entity in htmlentitydefs.name2codepoint: - return unichr(htmlentitydefs.name2codepoint[entity]) - - # Unicode character - mobj = re.match(ur'(?u)#(x?\d+)', entity) - if mobj is not None: - numstr = mobj.group(1) - if numstr.startswith(u'x'): - base = 16 - numstr = u'0%s' % numstr - else: - base = 10 - return unichr(long(numstr, base)) - - # Unknown entity in name, return its literal representation - return (u'&%s;' % entity) - -HTMLParser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix -class IDParser(HTMLParser.HTMLParser): - """Modified HTMLParser that isolates a tag with the specified id""" - def __init__(self, id): - self.id = id - self.result = None - self.started = False - self.depth = {} - self.html = None - self.watch_startpos = False - self.error_count = 0 - HTMLParser.HTMLParser.__init__(self) - - def error(self, message): - #print >> sys.stderr, self.getpos() - if self.error_count > 10 or self.started: - raise HTMLParser.HTMLParseError(message, self.getpos()) - self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line - self.error_count += 1 - self.goahead(1) - - def loads(self, html): - self.html = html - self.feed(html) - self.close() - - def handle_starttag(self, tag, attrs): - attrs = dict(attrs) - if self.started: - self.find_startpos(None) - if 'id' in attrs and attrs['id'] == self.id: - self.result = [tag] - self.started = True - self.watch_startpos = True - if self.started: - if not tag in self.depth: self.depth[tag] = 0 - self.depth[tag] += 1 - - def handle_endtag(self, tag): - if self.started: - if tag in self.depth: self.depth[tag] -= 1 - if self.depth[self.result[0]] == 0: - self.started = False - self.result.append(self.getpos()) - - def find_startpos(self, x): - """Needed to put the start position of the result (self.result[1]) - after the opening tag with the requested id""" - if self.watch_startpos: - self.watch_startpos = False - self.result.append(self.getpos()) - handle_entityref = handle_charref = handle_data = handle_comment = \ - handle_decl = handle_pi = unknown_decl = find_startpos - - def get_result(self): - if self.result == None: return None - if len(self.result) != 3: return None - lines = self.html.split('\n') - lines = lines[self.result[1][0]-1:self.result[2][0]] - lines[0] = lines[0][self.result[1][1]:] - if len(lines) == 1: - lines[-1] = lines[-1][:self.result[2][1]-self.result[1][1]] - lines[-1] = lines[-1][:self.result[2][1]] - return '\n'.join(lines).strip() + """Transforms an HTML entity to a character. + + This function receives a match object and is intended to be used with + the re.sub() function. + """ + entity = matchobj.group(1) + + # Known non-numeric HTML entity + if entity in compat_html_entities.name2codepoint: + return compat_chr(compat_html_entities.name2codepoint[entity]) + + mobj = re.match(u'(?u)#(x?\\d+)', entity) + if mobj is not None: + numstr = mobj.group(1) + if numstr.startswith(u'x'): + base = 16 + numstr = u'0%s' % numstr + else: + base = 10 + return compat_chr(int(numstr, base)) + + # Unknown entity in name, return its literal representation + return (u'&%s;' % entity) + +compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix +class AttrParser(compat_html_parser.HTMLParser): + """Modified HTMLParser that isolates a tag with the specified attribute""" + def __init__(self, attribute, value): + self.attribute = attribute + self.value = value + self.result = None + self.started = False + self.depth = {} + self.html = None + self.watch_startpos = False + self.error_count = 0 + compat_html_parser.HTMLParser.__init__(self) + + def error(self, message): + if self.error_count > 10 or self.started: + raise compat_html_parser.HTMLParseError(message, self.getpos()) + self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line + self.error_count += 1 + self.goahead(1) + + def loads(self, html): + self.html = html + self.feed(html) + self.close() + + def handle_starttag(self, tag, attrs): + attrs = dict(attrs) + if self.started: + self.find_startpos(None) + if self.attribute in attrs and attrs[self.attribute] == self.value: + self.result = [tag] + self.started = True + self.watch_startpos = True + if self.started: + if not tag in self.depth: self.depth[tag] = 0 + self.depth[tag] += 1 + + def handle_endtag(self, tag): + if self.started: + if tag in self.depth: self.depth[tag] -= 1 + if self.depth[self.result[0]] == 0: + self.started = False + self.result.append(self.getpos()) + + def find_startpos(self, x): + """Needed to put the start position of the result (self.result[1]) + after the opening tag with the requested id""" + if self.watch_startpos: + self.watch_startpos = False + self.result.append(self.getpos()) + handle_entityref = handle_charref = handle_data = handle_comment = \ + handle_decl = handle_pi = unknown_decl = find_startpos + + def get_result(self): + if self.result is None: + return None + if len(self.result) != 3: + return None + lines = self.html.split('\n') + lines = lines[self.result[1][0]-1:self.result[2][0]] + lines[0] = lines[0][self.result[1][1]:] + if len(lines) == 1: + lines[-1] = lines[-1][:self.result[2][1]-self.result[1][1]] + lines[-1] = lines[-1][:self.result[2][1]] + return '\n'.join(lines).strip() def get_element_by_id(id, html): - """Return the content of the tag with the specified id in the passed HTML document""" - parser = IDParser(id) - try: - parser.loads(html) - except HTMLParser.HTMLParseError: - pass - return parser.get_result() + """Return the content of the tag with the specified ID in the passed HTML document""" + return get_element_by_attribute("id", id, html) + +def get_element_by_attribute(attribute, value, html): + """Return the content of the tag with the specified attribute in the passed HTML document""" + parser = AttrParser(attribute, value) + try: + parser.loads(html) + except compat_html_parser.HTMLParseError: + pass + return parser.get_result() def clean_html(html): - """Clean an HTML snippet into a readable string""" - # Newline vs <br /> - html = html.replace('\n', ' ') - html = re.sub('\s*<\s*br\s*/?\s*>\s*', '\n', html) - # Strip html tags - html = re.sub('<.*?>', '', html) - # Replace html entities - html = unescapeHTML(html) - return html + """Clean an HTML snippet into a readable string""" + # Newline vs <br /> + html = html.replace('\n', ' ') + html = re.sub(r'\s*<\s*br\s*/?\s*>\s*', '\n', html) + html = re.sub(r'<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html) + # Strip html tags + html = re.sub('<.*?>', '', html) + # Replace html entities + html = unescapeHTML(html) + return html def sanitize_open(filename, open_mode): - """Try to open the given filename, and slightly tweak it if this fails. - - Attempts to open the given filename. If this fails, it tries to change - the filename slightly, step by step, until it's either able to open it - or it fails and raises a final exception, like the standard open() - function. - - It returns the tuple (stream, definitive_file_name). - """ - try: - if filename == u'-': - if sys.platform == 'win32': - import msvcrt - msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY) - return (sys.stdout, filename) - stream = open(encodeFilename(filename), open_mode) - return (stream, filename) - except (IOError, OSError), err: - # In case of error, try to remove win32 forbidden chars - filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename) - - # An exception here should be caught in the caller - stream = open(encodeFilename(filename), open_mode) - return (stream, filename) + """Try to open the given filename, and slightly tweak it if this fails. + + Attempts to open the given filename. If this fails, it tries to change + the filename slightly, step by step, until it's either able to open it + or it fails and raises a final exception, like the standard open() + function. + + It returns the tuple (stream, definitive_file_name). + """ + try: + if filename == u'-': + if sys.platform == 'win32': + import msvcrt + msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY) + return (sys.stdout, filename) + stream = open(encodeFilename(filename), open_mode) + return (stream, filename) + except (IOError, OSError) as err: + # In case of error, try to remove win32 forbidden chars + filename = re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', filename) + + # An exception here should be caught in the caller + stream = open(encodeFilename(filename), open_mode) + return (stream, filename) def timeconvert(timestr): - """Convert RFC 2822 defined time string into system timestamp""" - timestamp = None - timetuple = email.utils.parsedate_tz(timestr) - if timetuple is not None: - timestamp = email.utils.mktime_tz(timetuple) - return timestamp - -def sanitize_filename(s): - """Sanitizes a string so it could be used as part of a filename.""" - def replace_insane(char): - if char == '?' or ord(char) < 32 or ord(char) == 127: - return '' - elif char == '"': - return '\'' - elif char == ':': - return ' -' - elif char in '\\/|*<>': - return '-' - return char - - result = u''.join(map(replace_insane, s)) - while '--' in result: - result = result.replace('--', '-') - return result.strip('-') + """Convert RFC 2822 defined time string into system timestamp""" + timestamp = None + timetuple = email.utils.parsedate_tz(timestr) + if timetuple is not None: + timestamp = email.utils.mktime_tz(timetuple) + return timestamp + +def sanitize_filename(s, restricted=False, is_id=False): + """Sanitizes a string so it could be used as part of a filename. + If restricted is set, use a stricter subset of allowed characters. + Set is_id if this is not an arbitrary string, but an ID that should be kept if possible + """ + def replace_insane(char): + if char == '?' or ord(char) < 32 or ord(char) == 127: + return '' + elif char == '"': + return '' if restricted else '\'' + elif char == ':': + return '_-' if restricted else ' -' + elif char in '\\/|*<>': + return '_' + if restricted and (char in '!&\'()[]{}$;`^,#' or char.isspace()): + return '_' + if restricted and ord(char) > 127: + return '_' + return char + + result = u''.join(map(replace_insane, s)) + if not is_id: + while '__' in result: + result = result.replace('__', '_') + result = result.strip('_') + # Common case of "Foreign band name - English song title" + if restricted and result.startswith('-_'): + result = result[2:] + if not result: + result = '_' + return result def orderedSet(iterable): - """ Remove all duplicates from the input iterable """ - res = [] - for el in iterable: - if el not in res: - res.append(el) - return res + """ Remove all duplicates from the input iterable """ + res = [] + for el in iterable: + if el not in res: + res.append(el) + return res def unescapeHTML(s): - """ - @param s a string (of type unicode) - """ - assert type(s) == type(u'') + """ + @param s a string + """ + assert type(s) == type(u'') - result = re.sub(ur'(?u)&(.+?);', htmlentity_transform, s) - return result + result = re.sub(u'(?u)&(.+?);', htmlentity_transform, s) + return result def encodeFilename(s): - """ - @param s The name of the file (of type unicode) - """ + """ + @param s The name of the file + """ + + assert type(s) == type(u'') + + # Python 3 has a Unicode API + if sys.version_info >= (3, 0): + return s + + if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5: + # Pass u'' directly to use Unicode APIs on Windows 2000 and up + # (Detecting Windows NT 4 is tricky because 'major >= 4' would + # match Windows 9x series as well. Besides, NT 4 is obsolete.) + return s + else: + return s.encode(sys.getfilesystemencoding(), 'ignore') + + +class ExtractorError(Exception): + """Error during info extraction.""" + def __init__(self, msg, tb=None): + """ tb, if given, is the original traceback (so that it can be printed out). """ + super(ExtractorError, self).__init__(msg) + self.traceback = tb - assert type(s) == type(u'') + def format_traceback(self): + if self.traceback is None: + return None + return u''.join(traceback.format_tb(self.traceback)) - if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5: - # Pass u'' directly to use Unicode APIs on Windows 2000 and up - # (Detecting Windows NT 4 is tricky because 'major >= 4' would - # match Windows 9x series as well. Besides, NT 4 is obsolete.) - return s - else: - return s.encode(sys.getfilesystemencoding(), 'ignore') class DownloadError(Exception): - """Download Error exception. + """Download Error exception. - This exception may be thrown by FileDownloader objects if they are not - configured to continue on errors. They will contain the appropriate - error message. - """ - pass + This exception may be thrown by FileDownloader objects if they are not + configured to continue on errors. They will contain the appropriate + error message. + """ + pass class SameFileError(Exception): - """Same File exception. + """Same File exception. - This exception will be thrown by FileDownloader objects if they detect - multiple files would have to be downloaded to the same file on disk. - """ - pass + This exception will be thrown by FileDownloader objects if they detect + multiple files would have to be downloaded to the same file on disk. + """ + pass class PostProcessingError(Exception): - """Post Processing exception. + """Post Processing exception. - This exception may be raised by PostProcessor's .run() method to - indicate an error in the postprocessing task. - """ - pass + This exception may be raised by PostProcessor's .run() method to + indicate an error in the postprocessing task. + """ + pass class MaxDownloadsReached(Exception): - """ --max-downloads limit has been reached. """ - pass + """ --max-downloads limit has been reached. """ + pass class UnavailableVideoError(Exception): - """Unavailable Format exception. + """Unavailable Format exception. - This exception will be thrown when a video is requested - in a format that is not available for that video. - """ - pass + This exception will be thrown when a video is requested + in a format that is not available for that video. + """ + pass class ContentTooShortError(Exception): - """Content Too Short exception. - - This exception may be raised by FileDownloader objects when a file they - download is too small for what the server announced first, indicating - the connection was probably interrupted. - """ - # Both in bytes - downloaded = None - expected = None - - def __init__(self, downloaded, expected): - self.downloaded = downloaded - self.expected = expected - - -class Trouble(Exception): - """Trouble helper exception - - This is an exception to be handled with - FileDownloader.trouble - """ - -class YoutubeDLHandler(urllib2.HTTPHandler): - """Handler for HTTP requests and responses. - - This class, when installed with an OpenerDirector, automatically adds - the standard headers to every HTTP request and handles gzipped and - deflated responses from web servers. If compression is to be avoided in - a particular request, the original request in the program code only has - to include the HTTP header "Youtubedl-No-Compression", which will be - removed before making the real request. - - Part of this code was copied from: - - http://techknack.net/python-urllib2-handlers/ - - Andrew Rowls, the author of that code, agreed to release it to the - public domain. - """ - - @staticmethod - def deflate(data): - try: - return zlib.decompress(data, -zlib.MAX_WBITS) - except zlib.error: - return zlib.decompress(data) - - @staticmethod - def addinfourl_wrapper(stream, headers, url, code): - if hasattr(urllib2.addinfourl, 'getcode'): - return urllib2.addinfourl(stream, headers, url, code) - ret = urllib2.addinfourl(stream, headers, url) - ret.code = code - return ret - - def http_request(self, req): - for h in std_headers: - if h in req.headers: - del req.headers[h] - req.add_header(h, std_headers[h]) - if 'Youtubedl-no-compression' in req.headers: - if 'Accept-encoding' in req.headers: - del req.headers['Accept-encoding'] - del req.headers['Youtubedl-no-compression'] - return req - - def http_response(self, req, resp): - old_resp = resp - # gzip - if resp.headers.get('Content-encoding', '') == 'gzip': - gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r') - resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) - resp.msg = old_resp.msg - # deflate - if resp.headers.get('Content-encoding', '') == 'deflate': - gz = StringIO.StringIO(self.deflate(resp.read())) - resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) - resp.msg = old_resp.msg - return resp + """Content Too Short exception. + + This exception may be raised by FileDownloader objects when a file they + download is too small for what the server announced first, indicating + the connection was probably interrupted. + """ + # Both in bytes + downloaded = None + expected = None + + def __init__(self, downloaded, expected): + self.downloaded = downloaded + self.expected = expected + +class YoutubeDLHandler(compat_urllib_request.HTTPHandler): + """Handler for HTTP requests and responses. + + This class, when installed with an OpenerDirector, automatically adds + the standard headers to every HTTP request and handles gzipped and + deflated responses from web servers. If compression is to be avoided in + a particular request, the original request in the program code only has + to include the HTTP header "Youtubedl-No-Compression", which will be + removed before making the real request. + + Part of this code was copied from: + + http://techknack.net/python-urllib2-handlers/ + + Andrew Rowls, the author of that code, agreed to release it to the + public domain. + """ + + @staticmethod + def deflate(data): + try: + return zlib.decompress(data, -zlib.MAX_WBITS) + except zlib.error: + return zlib.decompress(data) + + @staticmethod + def addinfourl_wrapper(stream, headers, url, code): + if hasattr(compat_urllib_request.addinfourl, 'getcode'): + return compat_urllib_request.addinfourl(stream, headers, url, code) + ret = compat_urllib_request.addinfourl(stream, headers, url) + ret.code = code + return ret + + def http_request(self, req): + for h in std_headers: + if h in req.headers: + del req.headers[h] + req.add_header(h, std_headers[h]) + if 'Youtubedl-no-compression' in req.headers: + if 'Accept-encoding' in req.headers: + del req.headers['Accept-encoding'] + del req.headers['Youtubedl-no-compression'] + return req + + def http_response(self, req, resp): + old_resp = resp + # gzip + if resp.headers.get('Content-encoding', '') == 'gzip': + gz = gzip.GzipFile(fileobj=io.BytesIO(resp.read()), mode='r') + resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) + resp.msg = old_resp.msg + # deflate + if resp.headers.get('Content-encoding', '') == 'deflate': + gz = io.BytesIO(self.deflate(resp.read())) + resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) + resp.msg = old_resp.msg + return resp + + https_request = http_request + https_response = http_response diff --git a/youtube_dl/version.py b/youtube_dl/version.py new file mode 100644 index 000000000..a4e9d2478 --- /dev/null +++ b/youtube_dl/version.py @@ -0,0 +1,2 @@ + +__version__ = '2013.01.02' |