diff options
| -rwxr-xr-x | youtube-dl | 311 |
1 files changed, 285 insertions, 26 deletions
diff --git a/youtube-dl b/youtube-dl index e8b19c8d0..67e1a0ffd 100755 --- a/youtube-dl +++ b/youtube-dl @@ -7,11 +7,10 @@ # Author: Witold Baryluk # Author: Paweł Paprota # Author: Gergely Imreh +# Author: Philipp Hagemeister <phihag@phihag.de> # License: Public domain code import cookielib -import ctypes import datetime -import email.utils import gzip import htmlentitydefs import httplib @@ -23,20 +22,37 @@ import os.path import re import socket import string -import StringIO import subprocess import sys import time import urllib import urllib2 +import warnings import zlib +if os.name == 'nt': + import ctypes + +try: + import email.utils +except ImportError: # Python 2.4 + import email.Utils +try: + import cStringIO as StringIO +except ImportError: + import StringIO + # parse_qs was moved from the cgi module to the urlparse module recently. try: from urlparse import parse_qs except ImportError: from cgi import parse_qs +try: + import lxml.etree +except ImportError: + pass # Handled below + std_headers = { 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1', 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', @@ -47,6 +63,119 @@ std_headers = { simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii') +try: + import json +except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson): + import re + class json(object): + @staticmethod + def loads(s): + s = s.decode('UTF-8') + def raiseError(msg, i): + raise ValueError(msg + ' at position ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:])) + def skipSpace(i, expectMore=True): + while i < len(s) and s[i] in ' \t\r\n': + i += 1 + if expectMore: + if i >= len(s): + raiseError('Premature end', i) + return i + def decodeEscape(match): + esc = match.group(1) + _STATIC = { + '"': '"', + '\\': '\\', + '/': '/', + 'b': unichr(0x8), + 'f': unichr(0xc), + 'n': '\n', + 'r': '\r', + 't': '\t', + } + if esc in _STATIC: + return _STATIC[esc] + if esc[0] == 'u': + if len(esc) == 1+4: + return unichr(int(esc[1:5], 16)) + if len(esc) == 5+6 and esc[5:7] == '\\u': + hi = int(esc[1:5], 16) + low = int(esc[7:11], 16) + return unichr((hi - 0xd800) * 0x400 + low - 0xdc00 + 0x10000) + raise ValueError('Unknown escape ' + str(esc)) + def parseString(i): + i += 1 + e = i + while True: + e = s.index('"', e) + bslashes = 0 + while s[e-bslashes-1] == '\\': + bslashes += 1 + if bslashes % 2 == 1: + e += 1 + continue + break + rexp = re.compile(r'\\(u[dD][89aAbB][0-9a-fA-F]{2}\\u[0-9a-fA-F]{4}|u[0-9a-fA-F]{4}|.|$)') + stri = rexp.sub(decodeEscape, s[i:e]) + return (e+1,stri) + def parseObj(i): + i += 1 + res = {} + i = skipSpace(i) + if s[i] == '}': # Empty dictionary + return (i+1,res) + while True: + if s[i] != '"': + raiseError('Expected a string object key', i) + i,key = parseString(i) + i = skipSpace(i) + if i >= len(s) or s[i] != ':': + raiseError('Expected a colon', i) + i,val = parse(i+1) + res[key] = val + i = skipSpace(i) + if s[i] == '}': + return (i+1, res) + if s[i] != ',': + raiseError('Expected comma or closing curly brace', i) + i = skipSpace(i+1) + def parseArray(i): + res = [] + i = skipSpace(i+1) + if s[i] == ']': # Empty array + return (i+1,res) + while True: + i,val = parse(i) + res.append(val) + i = skipSpace(i) # Raise exception if premature end + if s[i] == ']': + return (i+1, res) + if s[i] != ',': + raiseError('Expected a comma or closing bracket', i) + i = skipSpace(i+1) + def parseDiscrete(i): + for k,v in {'true': True, 'false': False, 'null': None}.items(): + if s.startswith(k, i): + return (i+len(k), v) + raiseError('Not a boolean (or null)', i) + def parseNumber(i): + mobj = re.match('^(-?(0|[1-9][0-9]*)(\.[0-9]*)?([eE][+-]?[0-9]+)?)', s[i:]) + if mobj is None: + raiseError('Not a number', i) + nums = mobj.group(1) + if '.' in nums or 'e' in nums or 'E' in nums: + return (i+len(nums), float(nums)) + return (i+len(nums), int(nums)) + CHARMAP = {'{': parseObj, '[': parseArray, '"': parseString, 't': parseDiscrete, 'f': parseDiscrete, 'n': parseDiscrete} + def parse(i): + i = skipSpace(i) + i,res = CHARMAP.get(s[i], parseNumber)(i) + i = skipSpace(i, False) + return (i,res) + i,res = parse(0) + if i < len(s): + raise ValueError('Extra data at end of input (index ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]) + ')') + return res + def preferredencoding(): """Get preferred encoding. @@ -286,6 +415,8 @@ class FileDownloader(object): 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 """ params = None @@ -481,6 +612,14 @@ class FileDownloader(object): except: pass + def report_writedescription(self, descfn): + """ Report that the description file is being written """ + self.to_screen(u'[info] Writing video description to: %s' % descfn, ignore_encoding_errors=True) + + def report_writeinfojson(self, infofn): + """ Report that the metadata file has been written """ + self.to_screen(u'[info] Video description metadata as JSON to: %s' % infofn, ignore_encoding_errors=True) + def report_destination(self, filename): """Report destination filename.""" self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True) @@ -567,6 +706,37 @@ class FileDownloader(object): self.trouble(u'ERROR: unable to create directories: %s' % str(err)) return + if self.params.get('writedescription', False): + try: + descfn = filename + '.description' + self.report_writedescription(descfn) + descfile = open(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: %s' % str(descfn)) + return + + if self.params.get('writeinfojson', False): + infofn = filename + '.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(infofn, 'wb') + try: + json.dump(info_dict, infof) + finally: + infof.close() + except (OSError, IOError): + self.trouble(u'ERROR: Cannot write metadata to JSON file: %s' % str(infofn)) + return + try: success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None)) except (OSError, IOError), err: @@ -858,7 +1028,7 @@ class InfoExtractor(object): class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$' + _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$' _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' @@ -1067,11 +1237,19 @@ class YoutubeIE(InfoExtractor): pass # description - video_description = 'No description available.' - if self._downloader.params.get('forcedescription', False): - mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage) - if mobj is not None: - video_description = mobj.group(1) + try: + lxml.etree + except NameError: + video_description = u'No description available.' + if self._downloader.params.get('forcedescription', False) or self._downloader.params.get('writedescription', False): + mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage) + if mobj is not None: + video_description = mobj.group(1).decode('utf-8') + else: + html_parser = lxml.etree.HTMLParser(encoding='utf-8') + vwebpage_doc = lxml.etree.parse(StringIO.StringIO(video_webpage), html_parser) + video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()')) + # TODO use another parser # token video_token = urllib.unquote_plus(video_info['token'][0]) @@ -1079,10 +1257,15 @@ class YoutubeIE(InfoExtractor): # Decide which formats to download req_format = self._downloader.params.get('format', None) - if 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1: + 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 = [dict(pairStr.split('=') for pairStr in uds.split('&')) for uds in url_data_strs] - url_map = dict((ud['itag'], urllib.unquote(ud['url'])) for ud in url_data) + 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) + 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):] @@ -1102,13 +1285,8 @@ class YoutubeIE(InfoExtractor): self._downloader.trouble(u'ERROR: requested format not available') return video_url_list = [(req_format, url_map[req_format])] # Specific format - - elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): - self.report_rtmp_download() - video_url_list = [(None, video_info['conn'][0])] - else: - self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info') + self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info') return for format_param, video_real_url in video_url_list: @@ -1118,7 +1296,6 @@ class YoutubeIE(InfoExtractor): # Extension video_extension = self._video_extensions.get(format_param, 'flv') - # Find the video URL in fmt_url_map or conn paramters try: # Process video information self._downloader.process_info({ @@ -1131,7 +1308,7 @@ class YoutubeIE(InfoExtractor): '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'), + 'description': video_description, 'player_url': player_url, }) except UnavailableVideoError, err: @@ -2508,10 +2685,7 @@ class FacebookIE(InfoExtractor): pass # description - video_description = 'No description available.' - if (self._downloader.params.get('forcedescription', False) and - 'description' in video_info): - video_description = video_info['description'] + video_description = video_info.get('description', 'No description available.') url_map = video_info['video_urls'] if len(url_map.keys()) > 0: @@ -2546,7 +2720,6 @@ class FacebookIE(InfoExtractor): # Extension video_extension = self._video_extensions.get(format_param, 'mp4') - # Find the video URL in fmt_url_map or conn paramters try: # Process video information self._downloader.process_info({ @@ -2565,6 +2738,82 @@ class FacebookIE(InfoExtractor): except UnavailableVideoError, err: self._downloader.trouble(u'\nERROR: unable to download video') +class BlipTVIE(InfoExtractor): + """Information extractor for blip.tv""" + + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$' + _URL_EXT = r'^.*\.([a-z0-9]+)$' + + @staticmethod + def suitable(url): + return (re.match(BlipTVIE._VALID_URL, url) is not None) + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[blip.tv] %s: Extracting information' % file_id) + + def _simplify_title(self, title): + res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title) + res = res.strip(ur'_') + return res + + 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) + self.report_extraction(mobj.group(1)) + try: + json_code = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download 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) + + self._downloader.increment_downloads() + + info = { + 'id': data['item_id'], + 'url': video_url, + 'uploader': data['display_name'], + 'upload_date': upload_date, + 'title': data['title'], + 'stitle': self._simplify_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 + + try: + self._downloader.process_info(info) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download video') + + class PostProcessor(object): """Post Processor class. @@ -2725,7 +2974,7 @@ if __name__ == '__main__': # Parse command line parser = optparse.OptionParser( usage='Usage: %prog [options] url...', - version='2011.08.04', + version='2011.08.04-phihag', conflict_handler='resolve', ) @@ -2815,6 +3064,12 @@ if __name__ == '__main__': 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) parser.add_option_group(filesystem) postproc = optparse.OptionGroup(parser, 'Post-processing Options') @@ -2913,6 +3168,7 @@ if __name__ == '__main__': yahoo_search_ie = YahooSearchIE(yahoo_ie) deposit_files_ie = DepositFilesIE() facebook_ie = FacebookIE() + bliptv_ie = BlipTVIE() generic_ie = GenericIE() # File downloader @@ -2951,6 +3207,8 @@ if __name__ == '__main__': 'consoletitle': opts.consoletitle, 'nopart': opts.nopart, 'updatetime': opts.updatetime, + 'writedescription': opts.writedescription, + 'writeinfojson': opts.writeinfojson, }) fd.add_info_extractor(youtube_search_ie) fd.add_info_extractor(youtube_pl_ie) @@ -2965,6 +3223,7 @@ if __name__ == '__main__': fd.add_info_extractor(yahoo_search_ie) fd.add_info_extractor(deposit_files_ie) fd.add_info_extractor(facebook_ie) + fd.add_info_extractor(bliptv_ie) # This must come last since it's the # fallback if none of the others work |