diff options
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/FileDownloader.py | 130 | ||||
-rw-r--r-- | youtube_dl/InfoExtractors.py | 754 | ||||
-rw-r--r-- | youtube_dl/PostProcessor.py | 25 | ||||
-rw-r--r-- | youtube_dl/__init__.py | 84 | ||||
-rw-r--r-- | youtube_dl/utils.py | 42 |
5 files changed, 830 insertions, 205 deletions
diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 724de17c7..b6aebe4ac 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -13,7 +13,7 @@ import urllib2 if os.name == 'nt': import ctypes - + from utils import * @@ -44,39 +44,38 @@ class FileDownloader(object): 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 - 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 + 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 + 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 @@ -95,6 +94,9 @@ class FileDownloader(object): 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: @@ -141,23 +143,23 @@ class FileDownloader(object): 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) + return int(new_max) rate = bytes / elapsed_time if rate > new_max: - return long(new_max) + return int(new_max) if rate < new_min: - return long(new_min) - return long(rate) + return int(new_min) + return int(rate) @staticmethod def parse_bytes(bytestr): - """Parse a string indicating a byte quantity into a long integer.""" + """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 long(round(number * multiplier)) + return int(round(number * multiplier)) def add_info_extractor(self, ie): """Add an InfoExtractor object to the end of the list.""" @@ -175,7 +177,6 @@ class FileDownloader(object): 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) @@ -183,7 +184,8 @@ class FileDownloader(object): def to_stderr(self, message): """Print message to stderr.""" - print >>sys.stderr, message.encode(preferredencoding()) + assert type(message) == type(u'') + sys.stderr.write((message + u'\n').encode(preferredencoding())) def to_cons_title(self, message): """Set console/terminal window title to message.""" @@ -323,7 +325,7 @@ class FileDownloader(object): """Generate the output filename.""" try: template_dict = dict(info_dict) - template_dict['epoch'] = unicode(long(time.time())) + template_dict['epoch'] = unicode(int(time.time())) template_dict['autonumber'] = unicode('%05d' % self._num_downloads) filename = self.params['outtmpl'] % template_dict return filename @@ -336,17 +338,22 @@ class FileDownloader(object): title = info_dict['title'] matchtitle = self.params.get('matchtitle', False) - if matchtitle and not re.search(matchtitle, title, re.IGNORECASE): - return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"' + 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 and re.search(rejecttitle, title, re.IGNORECASE): - return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"' + 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']) + # Keep for backwards compatibility + info_dict['stitle'] = info_dict['title'] reason = self._match_entry(info_dict) if reason is not None: @@ -359,20 +366,21 @@ class FileDownloader(object): raise MaxDownloadsReached() filename = self.prepare_filename(info_dict) - + filename = sanitize_filename(filename, self.params.get('restrictfilenames')) + # Forced printings if self.params.get('forcetitle', False): - print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace') + print(info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')) if self.params.get('forceurl', False): - print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace') + 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') + 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') + print(info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')) if self.params.get('forcefilename', False) and filename is not None: - print filename.encode(preferredencoding(), 'xmlcharrefreplace') + print(filename.encode(preferredencoding(), 'xmlcharrefreplace')) if self.params.get('forceformat', False): - print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace') + print(info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace')) # Do nothing else if in simulate mode if self.params.get('simulate', False): @@ -401,10 +409,10 @@ class FileDownloader(object): 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 + # that way it will silently go on when used with unsupporting IE try: srtfn = filename.rsplit('.', 1)[0] + u'.srt' self.report_writesubtitles(srtfn) @@ -450,7 +458,7 @@ class FileDownloader(object): 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) @@ -476,6 +484,7 @@ class FileDownloader(object): # 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) @@ -635,7 +644,7 @@ class FileDownloader(object): data_len = long(data_len) + resume_len data_len_str = self.format_bytes(data_len) byte_counter = 0 + resume_len - block_size = self.params.get('buffersize', 1024) + block_size = 1024 start = time.time() while True: # Download and write @@ -661,8 +670,7 @@ class FileDownloader(object): except (IOError, OSError), 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)) + 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) diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index baf859ea8..13b04ab5b 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -13,6 +13,8 @@ import urllib import urllib2 import email.utils import xml.etree.ElementTree +import random +import math from urlparse import parse_qs try: @@ -95,7 +97,26 @@ class InfoExtractor(object): class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$' + _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' @@ -134,6 +155,10 @@ class YoutubeIE(InfoExtractor): } 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') @@ -188,9 +213,9 @@ class YoutubeIE(InfoExtractor): return srt def _print_formats(self, formats): - print 'Available 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, '???')) + 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: @@ -213,7 +238,7 @@ class YoutubeIE(InfoExtractor): 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)) + self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err)) return # Set language @@ -222,7 +247,7 @@ class YoutubeIE(InfoExtractor): 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)) + self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_str(err)) return # No authentication to be performed @@ -245,7 +270,7 @@ class YoutubeIE(InfoExtractor): 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)) + self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err)) return # Confirm age @@ -258,7 +283,7 @@ class YoutubeIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err)) return def _real_extract(self, url): @@ -268,7 +293,7 @@ class YoutubeIE(InfoExtractor): url = 'http://www.youtube.com/' + urllib.unquote(mobj.group(1)).lstrip('/') # Extract video id from URL - mobj = re.match(self._VALID_URL, url) + mobj = re.match(self._VALID_URL, url, re.VERBOSE) if mobj is None: self._downloader.trouble(u'ERROR: invalid URL: %s' % url) return @@ -280,7 +305,7 @@ class YoutubeIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) return # Attempt to extract SWF player URL @@ -302,7 +327,7 @@ class YoutubeIE(InfoExtractor): 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)) + 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: @@ -365,8 +390,9 @@ class YoutubeIE(InfoExtractor): 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'lang_code="([\w\-]+)"', srt_list) + raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_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): @@ -374,18 +400,26 @@ class YoutubeIE(InfoExtractor): elif 'en' in srt_lang_list: srt_lang = 'en' else: - srt_lang = srt_lang_list[0] + 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://video.google.com/timedtext?hl=en&lang=%s&v=%s' % (srt_lang, video_id)) + 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)) + raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_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]) @@ -399,7 +433,7 @@ class YoutubeIE(InfoExtractor): 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]) for ud in 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 @@ -452,7 +486,8 @@ class YoutubeIE(InfoExtractor): 'thumbnail': video_thumbnail.decode('utf-8'), 'description': video_description, 'player_url': player_url, - 'subtitles': video_subtitles + 'subtitles': video_subtitles, + 'duration': video_duration }) return results @@ -491,7 +526,7 @@ class MetacafeIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % compat_str(err)) return # Confirm age @@ -504,7 +539,7 @@ class MetacafeIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err)) return def _real_extract(self, url): @@ -528,7 +563,7 @@ class MetacafeIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err)) return # Extract URL, uploader and title from webpage @@ -568,7 +603,7 @@ class MetacafeIE(InfoExtractor): return video_title = mobj.group(1).decode('utf-8') - mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage) + mobj = re.search(r'submitter=(.*?);', webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract uploader nickname') return @@ -589,7 +624,7 @@ class MetacafeIE(InfoExtractor): class DailymotionIE(InfoExtractor): """Information Extractor for Dailymotion""" - _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)' + _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)' IE_NAME = u'dailymotion' def __init__(self, downloader=None): @@ -610,9 +645,9 @@ class DailymotionIE(InfoExtractor): self._downloader.trouble(u'ERROR: invalid URL: %s' % url) return - video_id = mobj.group(1) + video_id = mobj.group(1).split('_')[0].split('?')[0] - video_extension = 'flv' + video_extension = 'mp4' # Retrieve video webpage to extract further information request = urllib2.Request(url) @@ -621,25 +656,34 @@ class DailymotionIE(InfoExtractor): 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)) + 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'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage) + mobj = re.search(r'\s*var flashvars = (.*)', webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract media URL') return - sequence = urllib.unquote(mobj.group(1)) - mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence) + 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 media URL') + self._downloader.trouble(u'ERROR: unable to extract video URL') return - mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '') - # if needed add http://www.dailymotion.com/ if relative URL + video_url = urllib.unquote(mobj.group(1)).replace('\\/', '/') - video_url = mediaURL + # TODO: support choosing qualities mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage) if mobj is None: @@ -647,17 +691,28 @@ class DailymotionIE(InfoExtractor): return video_title = unescapeHTML(mobj.group('title').decode('utf-8')) - mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage) + video_uploader = u'NA' + mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract uploader nickname') - return - video_uploader = mobj.group(1) + # 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': u'NA', + 'upload_date': video_upload_date, 'title': video_title, 'ext': video_extension.decode('utf-8'), 'format': u'NA', @@ -699,7 +754,7 @@ class GoogleIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return # Extract URL, uploader, and title from webpage @@ -738,7 +793,7 @@ class GoogleIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage) if mobj is None: @@ -794,7 +849,7 @@ class PhotobucketIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return # Extract URL, uploader, and title from webpage @@ -864,7 +919,7 @@ class YahooIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) @@ -888,7 +943,7 @@ class YahooIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return # Extract uploader and title from webpage @@ -946,7 +1001,7 @@ class YahooIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return # Extract media URL from playlist XML @@ -975,7 +1030,7 @@ 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]+)' + _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?:videos?/)?([0-9]+)' IE_NAME = u'vimeo' def __init__(self, downloader=None): @@ -1004,7 +1059,7 @@ class VimeoIE(InfoExtractor): 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)) + 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 @@ -1045,21 +1100,32 @@ class VimeoIE(InfoExtractor): 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')] - 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' + 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, quality, video_codec.upper()) + %(video_id, sig, timestamp, video_quality, video_codec.upper()) return [{ 'id': video_id, @@ -1159,7 +1225,7 @@ class GenericIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return except ValueError, err: # since this is the last-resort InfoExtractor, if @@ -1280,7 +1346,7 @@ class YoutubeSearchIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to download API page: %s' % compat_str(err)) return api_response = json.loads(data)['data'] @@ -1357,7 +1423,7 @@ class GoogleSearchIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) return # Extract video identifiers @@ -1440,7 +1506,7 @@ class YahooSearchIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) return # Extract video identifiers @@ -1466,9 +1532,9 @@ class YahooSearchIE(InfoExtractor): 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)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*' + _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=(PL)?%s&' + _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&([^&"]+&)*list=.*?%s' _MORE_PAGES_INDICATOR = r'yt-uix-pager-next' IE_NAME = u'youtube:playlist' @@ -1510,7 +1576,7 @@ class YoutubePlaylistIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) return # Extract video identifiers @@ -1536,6 +1602,56 @@ class YoutubePlaylistIE(InfoExtractor): 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' % 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 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 + + class YoutubeUserIE(InfoExtractor): """Information Extractor for YouTube users.""" @@ -1580,7 +1696,7 @@ class YoutubeUserIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) return # Extract video identifiers @@ -1619,6 +1735,98 @@ class YoutubeUserIE(InfoExtractor): self._downloader.download(['http://www.youtube.com/watch?v=%s' % video_id]) +class BlipTVUserIE(InfoExtractor): + """Information Extractor for blip.tv users.""" + + _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 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 + + username = mobj.group(1) + + page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1' + + request = urllib2.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' % 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. + + video_ids = [] + pagenum = 1 + + while True: + self.report_download_page(username, pagenum) + + request = urllib2.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 + + # 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))) + + 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. + + if len(ids_in_page) < self._PAGE_SIZE: + break + + pagenum += 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] + + 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]) + + class DepositFilesIE(InfoExtractor): """Information extractor for depositfiles.com""" @@ -1648,7 +1856,7 @@ class DepositFilesIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % compat_str(err)) return # Search for the real file URL @@ -1765,7 +1973,7 @@ class FacebookIE(InfoExtractor): 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)) + self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err)) return if useremail is None: @@ -1785,7 +1993,7 @@ class FacebookIE(InfoExtractor): 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)) + self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err)) return def _real_extract(self, url): @@ -1802,7 +2010,7 @@ class FacebookIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) return # Start extracting information @@ -1917,7 +2125,7 @@ class BlipTVIE(InfoExtractor): else: cchar = '?' json_url = url + cchar + 'skin=json&version=2&no_wrap=1' - request = urllib2.Request(json_url) + request = urllib2.Request(json_url.encode('utf-8')) self.report_extraction(mobj.group(1)) info = None try: @@ -1936,13 +2144,13 @@ class BlipTVIE(InfoExtractor): 'urlhandle': urlh } except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(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 = urlh.read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % compat_str(err)) return try: @@ -1975,6 +2183,7 @@ class BlipTVIE(InfoExtractor): self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err)) return + std_headers['User-Agent'] = 'iTunes/10.6.1' return [info] @@ -2009,7 +2218,7 @@ class MyVideoIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return self.report_extraction(video_id) @@ -2044,6 +2253,25 @@ class ComedyCentralIE(InfoExtractor): _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' + _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 report_extraction(self, episode_id): self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) @@ -2056,6 +2284,13 @@ class ComedyCentralIE(InfoExtractor): 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) if mobj is None: @@ -2096,10 +2331,19 @@ class ComedyCentralIE(InfoExtractor): 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 + # 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.*?:.*?)"', 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: @@ -2148,10 +2392,31 @@ class ComedyCentralIE(InfoExtractor): 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, @@ -2163,7 +2428,7 @@ class ComedyCentralIE(InfoExtractor): 'format': format, 'thumbnail': None, 'description': officialTitle, - 'player_url': playerUrl + 'player_url': None #playerUrl } results.append(info) @@ -2193,12 +2458,14 @@ class EscapistIE(InfoExtractor): self.report_extraction(showName) try: - webPageBytes = urllib2.urlopen(url).read() + 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 - webPage = webPageBytes.decode('utf-8') descMatch = re.search('<meta name="description" content="([^"]*)"', webPage) description = unescapeHTML(descMatch.group(1)) imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage) @@ -2269,7 +2536,7 @@ class CollegeHumorIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) return m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage) @@ -2288,7 +2555,7 @@ class CollegeHumorIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err)) return mdoc = xml.etree.ElementTree.fromstring(metaXml) @@ -2334,7 +2601,7 @@ class XVideosIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) return self.report_extraction(video_id) @@ -2357,11 +2624,11 @@ class XVideosIE(InfoExtractor): # 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.]+jpg)', webpage) + 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(1).decode('utf-8') + video_thumbnail = mobj.group(0).decode('utf-8') info = { 'id': video_id, @@ -2420,7 +2687,7 @@ class SoundcloudIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) return self.report_extraction('%s/%s' % (uploader, slug_title)) @@ -2447,7 +2714,7 @@ class SoundcloudIE(InfoExtractor): 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) @@ -2455,7 +2722,7 @@ class SoundcloudIE(InfoExtractor): 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)) + self._downloader.to_stderr(compat_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) @@ -2499,7 +2766,7 @@ class InfoQIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) return self.report_extraction(url) @@ -2585,15 +2852,15 @@ class MixcloudIE(InfoExtractor): return None def _print_formats(self, formats): - print 'Available 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]) + 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]) + print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1])) break def _real_extract(self, url): @@ -2613,7 +2880,7 @@ class MixcloudIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % compat_str(err)) return # parse JSON @@ -2797,7 +3064,7 @@ class MTVIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) return mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage) @@ -2830,7 +3097,7 @@ class MTVIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % compat_str(err)) return mdoc = xml.etree.ElementTree.fromstring(metadataXml) @@ -2857,3 +3124,314 @@ class MTVIE(InfoExtractor): } 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' % compat_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 + + +class XNXXIE(InfoExtractor): + """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).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] + + +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' % compat_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' % 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 + 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, + }] diff --git a/youtube_dl/PostProcessor.py b/youtube_dl/PostProcessor.py index 527dc3a3d..0501cc7f6 100644 --- a/youtube_dl/PostProcessor.py +++ b/youtube_dl/PostProcessor.py @@ -71,13 +71,14 @@ class FFmpegExtractAudioPP(PostProcessor): @staticmethod def detect_executables(): - available = {'avprobe' : False, 'avconv' : False, 'ffmpeg' : False, 'ffprobe' : False} - for path in os.environ["PATH"].split(os.pathsep): - for program in available.keys(): - exe_file = os.path.join(path, program) - if os.path.isfile(exe_file) and os.access(exe_file, os.X_OK): - available[program] = exe_file - return available + 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 @@ -142,14 +143,20 @@ class FFmpegExtractAudioPP(PostProcessor): extension = 'mp3' more_opts = [] if self._preferredquality is not None: - more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality] + 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: - more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality] + 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': diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 15f835a31..5fc39184a 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -1,6 +1,8 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- +from __future__ import with_statement + __authors__ = ( 'Ricardo Garcia Gonzalez', 'Danny Colligan', @@ -19,7 +21,7 @@ __authors__ = ( ) __license__ = 'Public Domain' -__version__ = '2012.02.27' +__version__ = '2012.11.28' 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' @@ -46,7 +48,7 @@ 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) @@ -64,7 +66,7 @@ def updateSelf(downloader, 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() @@ -73,20 +75,18 @@ def updateSelf(downloader, filename): 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, """ + b.write(""" echo Updating youtube-dl... ping 127.0.0.1 -n 5 -w 1000 > NUL move /Y "%s.new" "%s" del "%s" - """ %(exe, exe, bat) - + \n""" %(exe, exe, bat)) b.close() - + os.startfile(bat) except (IOError, OSError), err: sys.exit('ERROR: unable to overwrite current version') @@ -186,21 +186,18 @@ def parseOpts(): 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 10)', default=10) - general.add_option('--buffer-size', - dest='buffersize', metavar='SIZE', help='size of download buffer (e.g. 1024 or 16k) (default is 1024)', 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) + 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 1)', default=1) + 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)') @@ -266,13 +263,18 @@ def parseOpts(): 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) + 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 %(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), and %% for a literal percent. Use - to output to stdout.') + dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(title)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('--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', @@ -297,12 +299,12 @@ def parseOpts(): help='write video metadata to a .info.json file', default=False) - postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', 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='128K', - help='ffmpeg/avconv audio bitrate specification, 128k 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') @@ -331,6 +333,7 @@ def gen_extractors(): """ return [ YoutubePlaylistIE(), + YoutubeChannelIE(), YoutubeUserIE(), YoutubeSearchIE(), YoutubeIE(), @@ -343,6 +346,7 @@ def gen_extractors(): YahooSearchIE(), DepositFilesIE(), FacebookIE(), + BlipTVUserIE(), BlipTVIE(), VimeoIE(), MyVideoIE(), @@ -355,6 +359,9 @@ def gen_extractors(): MixcloudIE(), StanfordOpenClassroomIE(), MTVIE(), + YoukuIE(), + XNXXIE(), + GooglePlusIE(), GenericIE() ] @@ -372,6 +379,9 @@ def _real_main(): 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: @@ -417,10 +427,10 @@ def _real_main(): 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): - parser.error(u'using output template conflicts with using title, literal title or auto number') - if opts.usetitle and opts.useliteral: - parser.error(u'using title conflicts with using literal title') + 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: @@ -433,11 +443,6 @@ def _real_main(): opts.retries = long(opts.retries) except (TypeError, ValueError), 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: @@ -453,6 +458,10 @@ def _real_main(): 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({ @@ -472,21 +481,18 @@ def _real_main(): '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 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-%(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.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'), + '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, @@ -526,7 +532,7 @@ def _real_main(): parser.error(u'you must provide at least one URL') else: sys.exit() - + try: retcode = fd.download(all_urls) except MaxDownloadsReached: diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 2853ba50f..4ace22c2f 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -19,13 +19,18 @@ except ImportError: import StringIO std_headers = { - 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1', + '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', } +try: + compat_str = unicode # Python 2 +except NameError: + compat_str = str + def preferredencoding(): """Get preferred encoding. @@ -83,7 +88,6 @@ class IDParser(HTMLParser.HTMLParser): 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 @@ -190,14 +194,36 @@ def timeconvert(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 sanitize_filename(s, restricted=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. + """ def replace_insane(char): - if char in u' .\\/|?*<>:"' or ord(char) < 32: + 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 - return u''.join(map(replace_insane, s)).strip('_') + + result = u''.join(map(replace_insane, s)) + 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 """ @@ -223,7 +249,7 @@ def encodeFilename(s): assert type(s) == type(u'') - if sys.platform == 'win32' and sys.getwindowsversion().major >= 5: + 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.) |