X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=ac3ecea9252d56f9bc751be13cd6ad3ea5324753;hb=8edc2cf8ca866fe1aded3f7b3ccf6df277b2e9f7;hp=d7295ae3fe0bafb87dd3a1ea88e431ffd31cd32f;hpb=e314ba675b6ce6683395d04e4621aae2b5aca0ec;p=youtube-dl diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index d7295ae3f..ac3ecea92 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -3,7 +3,9 @@ from __future__ import absolute_import +import base64 import datetime +import itertools import netrc import os import re @@ -34,15 +36,16 @@ class InfoExtractor(object): 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: Full name of the video uploader. + upload_date: Video upload date (YYYYMMDD). uploader_id: Nickname or id of the video uploader. + location: Physical location of the video. player_url: SWF Player URL (used for rtmpdump). subtitles: The .srt file contents. urlhandle: [internal] The urlHandle to be used to download the file, @@ -105,6 +108,25 @@ class InfoExtractor(object): def IE_NAME(self): return type(self).__name__[:-2] + def _request_webpage(self, url_or_request, video_id, note=None, errnote=None): + """ Returns the response handle """ + if note is None: + note = u'Downloading video webpage' + self._downloader.to_screen(u'[%s] %s: %s' % (self.IE_NAME, video_id, note)) + try: + return compat_urllib_request.urlopen(url_or_request) + 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]) + + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None): + """ Returns the data of the page as a string """ + urlh = self._request_webpage(url_or_request, video_id, note, errnote) + webpage_bytes = urlh.read() + return webpage_bytes.decode('utf-8', 'replace') + + class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" @@ -242,13 +264,18 @@ class YoutubeIE(InfoExtractor): 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)) + params = compat_urllib_parse.urlencode({ + 'lang': srt_lang, + 'name': srt_lang_list[srt_lang].encode('utf-8'), + 'v': video_id, + }) + url = 'http://www.youtube.com/api/timedtext?' + params try: - srt_xml = compat_urllib_request.urlopen(request).read().decode('utf-8') + srt_xml = compat_urllib_request.urlopen(url).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 (u'WARNING: Did not fetch video subtitles', None) return (None, self._closed_captions_xml_to_srt(srt_xml)) def _print_formats(self, formats): @@ -397,7 +424,7 @@ class YoutubeIE(InfoExtractor): # uploader_id video_uploader_id = None - mobj = re.search(r'', video_webpage) + mobj = re.search(r'', video_webpage) if mobj is not None: video_uploader_id = mobj.group(1) else: @@ -660,10 +687,6 @@ class DailymotionIE(InfoExtractor): 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) @@ -682,13 +705,7 @@ class DailymotionIE(InfoExtractor): # Retrieve video webpage to extract further information request = compat_urllib_request.Request(url) request.add_header('Cookie', 'family_filter=off') - 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 retrieve video webpage: %s' % compat_str(err)) - return + webpage = self._download_webpage(request, video_id) # Extract URL, uploader and title from webpage self.report_extraction(video_id) @@ -961,7 +978,7 @@ class VimeoIE(InfoExtractor): """Information extractor for vimeo.com.""" # _VALID_URL matches Vimeo URLs - _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?:videos?/)?([0-9]+)' + _VALID_URL = r'(?Phttps?://)?(?:(?:www|player)\.)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?Pplay_redirect_hls\?clip_id=)?(?:videos?/)?(?P[0-9]+)' IE_NAME = u'vimeo' def __init__(self, downloader=None): @@ -982,7 +999,11 @@ class VimeoIE(InfoExtractor): self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) return - video_id = mobj.group(1) + video_id = mobj.group('id') + if not mobj.group('proto'): + url = 'https://' + url + if mobj.group('direct_link'): + url = 'https://vimeo.com/' + video_id # Retrieve video webpage to extract further information request = compat_urllib_request.Request(url, None, std_headers) @@ -1910,10 +1931,6 @@ 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.""" @@ -1973,62 +1990,14 @@ class DepositFilesIE(InfoExtractor): class FacebookIE(InfoExtractor): """Information Extractor for Facebook""" - _WORKING = False _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P\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'
(.*?)
', - 'owner': r'\("video_owner_name", "(.*?)"\)', - 'thumbnail': r'\("thumb_url", "(?P.*?)"\)', - } - 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 + self._downloader.to_screen(u'[%s] Logging in' % self.IE_NAME) def _real_initialize(self): if self._downloader is None: @@ -2081,100 +2050,35 @@ class FacebookIE(InfoExtractor): 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 = 'https://www.facebook.com/video/video.php?v=%s' % video_id + webpage = self._download_webpage(url, video_id) - 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 + BEFORE = '[["allowFullScreen","true"],["allowScriptAccess","always"],["salign","tl"],["scale","noscale"],["wmode","opaque"]].forEach(function(param) {swf.addParam(param[0], param[1]);});\n' + AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' + m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage) + if not m: + raise ExtractorError(u'Cannot parse data') + data = dict(json.loads(m.group(1))) + params_raw = compat_urllib_parse.unquote(data['params']) + params = json.loads(params_raw) + video_url = params['hd_src'] + video_duration = int(params['video_duration']) + + m = re.search('

([^<]+)

', webpage) + if not m: + raise ExtractorError(u'Cannot find title in webpage') + video_title = unescapeHTML(m.group(1)) - results = [] - for format_param, video_real_url in video_url_list: - # Extension - video_extension = self._video_extensions.get(format_param, 'mp4') + info = { + 'id': video_id, + 'title': video_title, + 'url': video_url, + 'ext': 'mp4', + 'duration': video_duration, + 'thumbnail': params['thumbnail_src'], + } + return [info] - 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""" @@ -2203,6 +2107,7 @@ class BlipTVIE(InfoExtractor): cchar = '?' json_url = url + cchar + 'skin=json&version=2&no_wrap=1' request = compat_urllib_request.Request(json_url) + request.add_header('User-Agent', 'iTunes/10.6.1') self.report_extraction(mobj.group(1)) info = None try: @@ -2223,8 +2128,7 @@ class BlipTVIE(InfoExtractor): '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 + raise ExtractorError(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) if info is None: # Regular URL try: json_code_bytes = urlh.read() @@ -2257,13 +2161,13 @@ class BlipTVIE(InfoExtractor): 'format': data['media']['mimeType'], 'thumbnail': data['thumbnailUrl'], 'description': data['description'], - 'player_url': data['embedUrl'] + 'player_url': data['embedUrl'], + 'user_agent': 'iTunes/10.6.1', } 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] @@ -2276,10 +2180,6 @@ class MyVideoIE(InfoExtractor): 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) @@ -2293,13 +2193,8 @@ class MyVideoIE(InfoExtractor): video_id = mobj.group(1) # Get video webpage - request = compat_urllib_request.Request('http://www.myvideo.de/watch/%s' % video_id) - try: - self.report_download_webpage(video_id) - 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 + 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'', @@ -2341,7 +2236,6 @@ class ComedyCentralIE(InfoExtractor): (the-colbert-report-(videos|collections)/(?P[0-9]+)/[^/]*/(?P.*?)) |(watch/(?P[^/]*)/(?P.*))))) $""" - IE_NAME = u'comedycentral' _available_formats = ['3500', '2200', '1700', '1200', '750', '400'] @@ -2369,16 +2263,12 @@ class ComedyCentralIE(InfoExtractor): def report_extraction(self, episode_id): self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) - def report_config_download(self, episode_id): - self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id) + def report_config_download(self, episode_id, media_id): + self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration for %s' % (episode_id, media_id)) def report_index_download(self, episode_id): self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id) - def report_player_url(self, episode_id): - self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id) - - def _print_formats(self, formats): print('Available formats:') for x in formats: @@ -2417,6 +2307,7 @@ class ComedyCentralIE(InfoExtractor): try: htmlHandle = compat_urllib_request.urlopen(req) html = htmlHandle.read() + webpage = html.decode('utf-8') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) return @@ -2431,29 +2322,20 @@ class ComedyCentralIE(InfoExtractor): return epTitle = mobj.group('episode') - mMovieParams = re.findall('(?:gsp.comedystor/.*)$', rtmp_video_url) + if not m: + raise ExtractorError(u'Cannot transform RTMP url') + base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/' + video_url = base + m.group('finalid') - if video_url.startswith(broken_cdn): - video_url = video_url.replace(broken_cdn, better_cdn) - - effTitle = showId + u'-' + epTitle + effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1) info = { 'id': shortMediaId, 'url': video_url, @@ -2529,9 +2409,7 @@ class ComedyCentralIE(InfoExtractor): 'format': format, 'thumbnail': None, 'description': officialTitle, - 'player_url': None #playerUrl } - results.append(info) return results @@ -2611,7 +2489,6 @@ class EscapistIE(InfoExtractor): return [info] - class CollegeHumorIE(InfoExtractor): """Information extractor for collegehumor.com""" @@ -2690,10 +2567,6 @@ class XVideosIE(InfoExtractor): _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)) - def report_extraction(self, video_id): """Report information extraction.""" self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) @@ -2705,15 +2578,7 @@ class XVideosIE(InfoExtractor): return video_id = mobj.group(1) - self.report_webpage(video_id) - - request = compat_urllib_request.Request(r'http://www.xvideos.com/video' + video_id) - try: - webpage_bytes = compat_urllib_request.urlopen(request).read() - webpage = webpage_bytes.decode('utf-8', 'replace') - 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 + webpage = self._download_webpage(url, video_id) self.report_extraction(video_id) @@ -2812,7 +2677,7 @@ class SoundcloudIE(InfoExtractor): 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 video webpage: %s' % compat_str(err)) + self._downloader.trouble(u'ERROR: unable to download stream definitions: %s' % compat_str(err)) return streams = json.loads(stream_json) @@ -2831,13 +2696,7 @@ class SoundcloudIE(InfoExtractor): 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.""" @@ -2849,38 +2708,29 @@ class InfoQIE(InfoExtractor): self._downloader.trouble(u'ERROR: invalid URL: %s' % url) return - self.report_webpage(url) - - 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 download video webpage: %s' % compat_str(err)) - 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 - video_url = 'rtmpe://video.infoq.com/cfx/st/' + compat_urllib_parse.unquote(mobj.group(1).decode('base64')) - + 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).decode('utf-8') + video_title = mobj.group(1) # Extract description video_description = u'No description available.' mobj = re.search(r'', webpage) if mobj is not None: - video_description = mobj.group(1).decode('utf-8') + video_description = mobj.group(1) video_filename = video_url.split('/')[-1] video_id, extension = video_filename.split('.') @@ -3030,8 +2880,7 @@ class StanfordOpenClassroomIE(InfoExtractor): 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 + raise ExtractorError(u'Invalid URL: %s' % url) if mobj.group('course') and mobj.group('video'): # A specific video course = mobj.group('course') @@ -3068,12 +2917,9 @@ class StanfordOpenClassroomIE(InfoExtractor): '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 + coursepage = self._download_webpage(url, info['id'], + note='Downloading course info page', + errnote='Unable to download course info page') m = re.search('

([^<]+)

', coursepage) if m: @@ -3097,7 +2943,6 @@ class StanfordOpenClassroomIE(InfoExtractor): assert entry['type'] == 'reference' results += self.extract(entry['url']) return results - else: # Root page info = { 'id': 'Stanford OpenClassroom', @@ -3136,10 +2981,6 @@ class MTVIE(InfoExtractor): _VALID_URL = r'^(?Phttps?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P[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)) @@ -3152,14 +2993,8 @@ class MTVIE(InfoExtractor): if not mobj.group('proto'): url = 'http://' + url video_id = mobj.group('videoid') - self.report_webpage(video_id) - 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 download video webpage: %s' % compat_str(err)) - return + webpage = self._download_webpage(url, video_id) mobj = re.search(r'', webpage) if mobj is None: @@ -3222,20 +3057,15 @@ class MTVIE(InfoExtractor): class YoukuIE(InfoExtractor): - _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P[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) + 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'[Youku] %s: Extracting information' % file_id) + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) def _gen_sid(self): nowTime = int(time.time() * 1000) @@ -3340,7 +3170,7 @@ class YoukuIE(InfoExtractor): class XNXXIE(InfoExtractor): """Information extractor for xnxx.com""" - _VALID_URL = r'^http://video\.xnxx\.com/video([0-9]+)/(.*)' + _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)' IE_NAME = u'xnxx' VIDEO_URL_RE = r'flv_url=(.*?)&' VIDEO_TITLE_RE = r'(.*?)\s+-\s+XNXX.COM' @@ -3529,9 +3359,6 @@ class NBAIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*)(\?.*)?$' IE_NAME = u'nba' - def report_extraction(self, video_id): - 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: @@ -3542,14 +3369,7 @@ class NBAIE(InfoExtractor): if video_id.endswith('/index.html'): video_id = video_id[:-len('/index.html')] - self.report_extraction(video_id) - 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 XML: %s' % compat_str(err)) - return + 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): @@ -3602,17 +3422,25 @@ class JustinTVIE(InfoExtractor): return response = json.loads(webpage) + if type(response) != list: + error_text = response.get('error', 'unknown error') + self._downloader.trouble(u'ERROR: Justin.tv API: %s' % error_text) + return 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]) + video_date = re.sub('-', '', clip['start_time'][:10]) + video_uploader_id = clip.get('user_id', clip.get('channel_id')) + video_id = clip['id'] + video_title = clip.get('title', video_id) info.append({ - 'id': clip['id'], + 'id': video_id, 'url': video_url, - 'title': clip['title'], - 'uploader': clip.get('user_id', clip.get('channel_id')), + 'title': video_title, + 'uploader': clip.get('channel_name', video_uploader_id), + 'uploader_id': video_uploader_id, 'upload_date': video_date, 'ext': video_extension, }) @@ -3631,7 +3459,7 @@ class JustinTVIE(InfoExtractor): paged = True api += '/channel/archives/%s.json' else: - api += '/clip/show/%s.json' + api += '/broadcast/by_archive/%s.json' api = api % (video_id,) self.report_extraction(video_id) @@ -3652,10 +3480,6 @@ class JustinTVIE(InfoExtractor): class FunnyOrDieIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$' - IE_NAME = u'FunnyOrDie' - - def report_extraction(self, video_id): - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -3664,14 +3488,7 @@ class FunnyOrDieIE(InfoExtractor): return video_id = mobj.group('id') - self.report_extraction(video_id) - try: - urlh = compat_urllib_request.urlopen(url) - webpage_bytes = urlh.read() - webpage = webpage_bytes.decode('utf-8', 'ignore') - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) - return + webpage = self._download_webpage(url, video_id) m = re.search(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"', webpage, re.DOTALL) if not m: @@ -3701,9 +3518,6 @@ class FunnyOrDieIE(InfoExtractor): class TweetReelIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?tweetreel\.com/[?](?P<id>[0-9a-z]+)$' - def report_extraction(self, video_id): - 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: @@ -3711,14 +3525,7 @@ class TweetReelIE(InfoExtractor): return video_id = mobj.group('id') - self.report_extraction(video_id) - 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 webpage: %s' % compat_str(err)) - return + webpage = self._download_webpage(url, video_id) m = re.search(r'<div id="left" status_id="([0-9]+)">', webpage) if not m: @@ -3763,45 +3570,392 @@ class SteamIE(InfoExtractor): (?P<gameID>\d+)/? (?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID """ - IE_NAME = u'Steam' - + 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_download_video_page(self, game_id): - self._downloader.to_screen(u'[%s] %s: Downloading video page' % (self.IE_NAME, game_id)) - + 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 - try: - self.report_download_video_page(gameID) - urlh = compat_urllib_request.urlopen(videourl) - 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 webpage: %s' % compat_str(err)) - return + webpage = self._download_webpage(videourl, gameID) mweb = re.finditer(urlRE, webpage) - namesRE = r'<span class=\"title\">(?P<videoName>[\w:/\.\?=\+\s-]+)</span>' - titles = list(re.finditer(namesRE, webpage)) + namesRE = r'<span class="title">(?P<videoName>.+?)</span>' + titles = re.finditer(namesRE, webpage) videos = [] - i = 0 - for vid in mweb: + for vid,vtitle in zip(mweb,titles): video_id = vid.group('videoID') - title = titles[i].group('videoName') - video_url=vid.group('videoURL') + 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) - i += 1 info = { 'id':video_id, 'url':video_url, 'ext': 'flv', - 'title': title + 'title': unescapeHTML(title) } videos.append(info) return videos + +class UstreamIE(InfoExtractor): + _VALID_URL = r'https?://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] + +class RBMARadioIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$' + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('videoID') + + webpage = self._download_webpage(url, video_id) + m = re.search(r'<script>window.gon = {.*?};gon\.show=(.+?);</script>', webpage) + if not m: + raise ExtractorError(u'Cannot find metadata') + json_data = m.group(1) + + try: + data = json.loads(json_data) + except ValueError as e: + raise ExtractorError(u'Invalid JSON: ' + str(e)) + + video_url = data['akamai_url'] + '&cbr=256' + url_parts = compat_urllib_parse_urlparse(video_url) + video_ext = url_parts.path.rpartition('.')[2] + info = { + 'id': video_id, + 'url': video_url, + 'ext': video_ext, + 'title': data['title'], + 'description': data.get('teaser_text'), + 'location': data.get('country_of_origin'), + 'uploader': data.get('host', {}).get('name'), + 'uploader_id': data.get('host', {}).get('slug'), + 'thumbnail': data.get('image', {}).get('large_url_2x'), + 'duration': data.get('duration'), + } + return [info] + + +class YouPornIE(InfoExtractor): + """Information extractor for youporn.com.""" + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)' + + def _print_formats(self, formats): + """Print all available formats""" + print(u'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') + + req = compat_urllib_request.Request(url) + req.add_header('Cookie', 'age_verified=1') + webpage = self._download_webpage(req, video_id) + + # Get the video title + result = re.search(r'videoTitleArea">(?P<title>.*)</h1>', webpage) + if result is None: + raise ExtractorError(u'ERROR: unable to extract video title') + video_title = result.group('title').strip() + + # Get the video date + result = re.search(r'Date:</b>(?P<date>.*)</li>', webpage) + if result is None: + self._downloader.to_stderr(u'WARNING: unable to extract video date') + upload_date = None + else: + upload_date = result.group('date').strip() + + # Get the video uploader + result = re.search(r'Submitted:</b>(?P<uploader>.*)</li>', webpage) + if result is None: + self._downloader.to_stderr(u'ERROR: unable to extract uploader') + video_uploader = None + else: + video_uploader = result.group('uploader').strip() + video_uploader = clean_html( video_uploader ) + + # Get all of the formats available + DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>' + result = re.search(DOWNLOAD_LIST_RE, webpage) + if result is None: + raise ExtractorError(u'Unable to extract download list') + download_list_html = result.group('download_list').strip() + + # Get all of the links from the page + LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">' + links = re.findall(LINK_RE, download_list_html) + if(len(links) == 0): + raise ExtractorError(u'ERROR: no known formats available for video') + + 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 ) + path = compat_urllib_parse_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) + 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>.+))$' + + 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') + video_title = mobj.group('title') + + # Get webpage content + webpage = self._download_webpage(url, video_id) + + # Get the video URL + VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' + result = re.search(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('url')) + + #Get the uploaded date + VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' + result = re.search(VIDEO_UPLOADED_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + upload_date = result.group('date') + + info = {'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': upload_date, + 'title': video_title, + 'ext': 'flv', + 'format': 'flv'} + + return [info] + +class YouJizzIE(InfoExtractor): + """Information extractor for youjizz.com.""" + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$' + + 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') + + # Get webpage content + webpage = self._download_webpage(url, video_id) + + # Get the video title + result = re.search(r'<title>(?P<title>.*)', webpage) + if result is None: + raise ExtractorError(u'ERROR: unable to extract video title') + video_title = result.group('title').strip() + + # Get the embed page + result = re.search(r'https?://www.youjizz.com/videos/embed/(?P[0-9]+)', webpage) + if result is None: + raise ExtractorError(u'ERROR: unable to extract embed page') + + embed_page_url = result.group(0).strip() + video_id = result.group('videoid') + + webpage = self._download_webpage(embed_page_url, video_id) + + # Get the video URL + result = re.search(r'so.addVariable\("file",encodeURIComponent\("(?P[^"]+)"\)\);', webpage) + if result is None: + raise ExtractorError(u'ERROR: unable to extract video url') + video_url = result.group('source') + + info = {'id': video_id, + 'url': video_url, + 'title': video_title, + 'ext': 'flv', + 'format': 'flv', + 'player_url': embed_page_url} + + return [info] + +class EightTracksIE(InfoExtractor): + IE_NAME = '8tracks' + _VALID_URL = r'https?://8tracks.com/(?P[^/]+)/(?P[^/#]+)(?:#.*)?$' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + raise ExtractorError(u'Invalid URL: %s' % url) + playlist_id = mobj.group('id') + + webpage = self._download_webpage(url, playlist_id) + + m = re.search(r"new TRAX.Mix\((.*?)\);\n*\s*TRAX.initSearchAutocomplete\('#search'\);", webpage, flags=re.DOTALL) + if not m: + raise ExtractorError(u'Cannot find trax information') + json_like = m.group(1) + data = json.loads(json_like) + + session = str(random.randint(0, 1000000000)) + mix_id = data['id'] + track_count = data['tracks_count'] + first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id) + next_url = first_url + res = [] + for i in itertools.count(): + api_json = self._download_webpage(next_url, playlist_id, + note=u'Downloading song information %s/%s' % (str(i+1), track_count), + errnote=u'Failed to download song information') + api_data = json.loads(api_json) + track_data = api_data[u'set']['track'] + info = { + 'id': track_data['id'], + 'url': track_data['track_file_stream_url'], + 'title': track_data['performer'] + u' - ' + track_data['name'], + 'raw_title': track_data['name'], + 'uploader_id': data['user']['login'], + 'ext': 'm4a', + } + res.append(info) + if api_data['set']['at_last_track']: + break + next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id']) + return res + +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(), + YouJizzIE(), + PornotubeIE(), + YouPornIE(), + GooglePlusIE(), + ArteTvIE(), + NBAIE(), + JustinTVIE(), + FunnyOrDieIE(), + TweetReelIE(), + SteamIE(), + UstreamIE(), + RBMARadioIE(), + EightTracksIE(), + GenericIE() + ] + +