From 4f8095235321632ac2785dda2f038bc2aedba4d9 Mon Sep 17 00:00:00 2001 From: pukkandan Date: Wed, 27 Apr 2022 08:24:25 +0530 Subject: [PATCH] [cleanup] Delete unused extractors --- yt_dlp/extractor/blinkx.py | 84 ---------- yt_dlp/extractor/discoveryvr.py | 56 ------- yt_dlp/extractor/everyonesmixtape.py | 73 --------- yt_dlp/extractor/fxnetworks.py | 74 --------- yt_dlp/extractor/kanalplay.py | 92 ----------- yt_dlp/extractor/noco.py | 225 --------------------------- yt_dlp/extractor/spiegeltv.py | 15 -- yt_dlp/extractor/tastytrade.py | 41 ----- yt_dlp/extractor/tudou.py | 45 ------ yt_dlp/extractor/vidzi.py | 65 -------- 10 files changed, 770 deletions(-) delete mode 100644 yt_dlp/extractor/blinkx.py delete mode 100644 yt_dlp/extractor/discoveryvr.py delete mode 100644 yt_dlp/extractor/everyonesmixtape.py delete mode 100644 yt_dlp/extractor/fxnetworks.py delete mode 100644 yt_dlp/extractor/kanalplay.py delete mode 100644 yt_dlp/extractor/noco.py delete mode 100644 yt_dlp/extractor/spiegeltv.py delete mode 100644 yt_dlp/extractor/tastytrade.py delete mode 100644 yt_dlp/extractor/tudou.py delete mode 100644 yt_dlp/extractor/vidzi.py diff --git a/yt_dlp/extractor/blinkx.py b/yt_dlp/extractor/blinkx.py deleted file mode 100644 index 80531ccad..000000000 --- a/yt_dlp/extractor/blinkx.py +++ /dev/null @@ -1,84 +0,0 @@ -import json - -from .common import InfoExtractor -from ..utils import ( - remove_start, - int_or_none, -) - - -class BlinkxIE(InfoExtractor): - _VALID_URL = r'(?:https?://(?:www\.)blinkx\.com/#?ce/|blinkx:)(?P[^?]+)' - IE_NAME = 'blinkx' - - _TEST = { - 'url': 'http://www.blinkx.com/ce/Da0Gw3xc5ucpNduzLuDDlv4WC9PuI4fDi1-t6Y3LyfdY2SZS5Urbvn-UPJvrvbo8LTKTc67Wu2rPKSQDJyZeeORCR8bYkhs8lI7eqddznH2ofh5WEEdjYXnoRtj7ByQwt7atMErmXIeYKPsSDuMAAqJDlQZ-3Ff4HJVeH_s3Gh8oQ', - 'md5': '337cf7a344663ec79bf93a526a2e06c7', - 'info_dict': { - 'id': 'Da0Gw3xc', - 'ext': 'mp4', - 'title': 'No Daily Show for John Oliver; HBO Show Renewed - IGN News', - 'uploader': 'IGN News', - 'upload_date': '20150217', - 'timestamp': 1424215740, - 'description': 'HBO has renewed Last Week Tonight With John Oliver for two more seasons.', - 'duration': 47.743333, - }, - } - - def _real_extract(self, url): - video_id = self._match_id(url) - display_id = video_id[:8] - - api_url = ('https://apib4.blinkx.com/api.php?action=play_video&' - + 'video=%s' % video_id) - data_json = self._download_webpage(api_url, display_id) - data = json.loads(data_json)['api']['results'][0] - duration = None - thumbnails = [] - formats = [] - for m in data['media']: - if m['type'] == 'jpg': - thumbnails.append({ - 'url': m['link'], - 'width': int(m['w']), - 'height': int(m['h']), - }) - elif m['type'] == 'original': - duration = float(m['d']) - elif m['type'] == 'youtube': - yt_id = m['link'] - self.to_screen('Youtube video detected: %s' % yt_id) - return self.url_result(yt_id, 'Youtube', video_id=yt_id) - elif m['type'] in ('flv', 'mp4'): - vcodec = remove_start(m['vcodec'], 'ff') - acodec = remove_start(m['acodec'], 'ff') - vbr = int_or_none(m.get('vbr') or m.get('vbitrate'), 1000) - abr = int_or_none(m.get('abr') or m.get('abitrate'), 1000) - tbr = vbr + abr if vbr and abr else None - format_id = '%s-%sk-%s' % (vcodec, tbr, m['w']) - formats.append({ - 'format_id': format_id, - 'url': m['link'], - 'vcodec': vcodec, - 'acodec': acodec, - 'abr': abr, - 'vbr': vbr, - 'tbr': tbr, - 'width': int_or_none(m.get('w')), - 'height': int_or_none(m.get('h')), - }) - - self._sort_formats(formats) - - return { - 'id': display_id, - 'fullid': video_id, - 'title': data['title'], - 'formats': formats, - 'uploader': data.get('channel_name'), - 'timestamp': data.get('pubdate_epoch'), - 'description': data.get('description'), - 'thumbnails': thumbnails, - 'duration': duration, - } diff --git a/yt_dlp/extractor/discoveryvr.py b/yt_dlp/extractor/discoveryvr.py deleted file mode 100644 index a021d986e..000000000 --- a/yt_dlp/extractor/discoveryvr.py +++ /dev/null @@ -1,56 +0,0 @@ -from .common import InfoExtractor -from ..utils import parse_duration - - -class DiscoveryVRIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?discoveryvr\.com/watch/(?P[^/?#]+)' - _TEST = { - 'url': 'http://www.discoveryvr.com/watch/discovery-vr-an-introduction', - 'md5': '32b1929798c464a54356378b7912eca4', - 'info_dict': { - 'id': 'discovery-vr-an-introduction', - 'ext': 'mp4', - 'title': 'Discovery VR - An Introduction', - 'description': 'md5:80d418a10efb8899d9403e61d8790f06', - } - } - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - - bootstrap_data = self._search_regex( - r'root\.DVR\.bootstrapData\s+=\s+"({.+?})";', - webpage, 'bootstrap data') - bootstrap_data = self._parse_json( - bootstrap_data.encode('utf-8').decode('unicode_escape'), - display_id) - videos = self._parse_json(bootstrap_data['videos'], display_id)['allVideos'] - video_data = next(video for video in videos if video.get('slug') == display_id) - - series = video_data.get('showTitle') - title = episode = video_data.get('title') or series - if series and series != title: - title = '%s - %s' % (series, title) - - formats = [] - for f, format_id in (('cdnUriM3U8', 'mobi'), ('webVideoUrlSd', 'sd'), ('webVideoUrlHd', 'hd')): - f_url = video_data.get(f) - if not f_url: - continue - formats.append({ - 'format_id': format_id, - 'url': f_url, - }) - - return { - 'id': display_id, - 'display_id': display_id, - 'title': title, - 'description': video_data.get('description'), - 'thumbnail': video_data.get('thumbnail'), - 'duration': parse_duration(video_data.get('runTime')), - 'formats': formats, - 'episode': episode, - 'series': series, - } diff --git a/yt_dlp/extractor/everyonesmixtape.py b/yt_dlp/extractor/everyonesmixtape.py deleted file mode 100644 index d26ff8ad3..000000000 --- a/yt_dlp/extractor/everyonesmixtape.py +++ /dev/null @@ -1,73 +0,0 @@ -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - sanitized_Request, -) - - -class EveryonesMixtapeIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?everyonesmixtape\.com/#/mix/(?P[0-9a-zA-Z]+)(?:/(?P[0-9]))?$' - - _TESTS = [{ - 'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi/5', - 'info_dict': { - 'id': '5bfseWNmlds', - 'ext': 'mp4', - 'title': "Passion Pit - \"Sleepyhead\" (Official Music Video)", - 'uploader': 'FKR.TV', - 'uploader_id': 'frenchkissrecords', - 'description': "Music video for \"Sleepyhead\" from Passion Pit's debut EP Chunk Of Change.\nBuy on iTunes: https://itunes.apple.com/us/album/chunk-of-change-ep/id300087641\n\nDirected by The Wilderness.\n\nhttp://www.passionpitmusic.com\nhttp://www.frenchkissrecords.com", - 'upload_date': '20081015' - }, - 'params': { - 'skip_download': True, # This is simply YouTube - } - }, { - 'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi', - 'info_dict': { - 'id': 'm7m0jJAbMQi', - 'title': 'Driving', - }, - 'playlist_count': 24 - }] - - def _real_extract(self, url): - mobj = self._match_valid_url(url) - playlist_id = mobj.group('id') - - pllist_url = 'http://everyonesmixtape.com/mixtape.php?a=getMixes&u=-1&linked=%s&explore=' % playlist_id - pllist_req = sanitized_Request(pllist_url) - pllist_req.add_header('X-Requested-With', 'XMLHttpRequest') - - playlist_list = self._download_json( - pllist_req, playlist_id, note='Downloading playlist metadata') - try: - playlist_no = next(playlist['id'] - for playlist in playlist_list - if playlist['code'] == playlist_id) - except StopIteration: - raise ExtractorError('Playlist id not found') - - pl_url = 'http://everyonesmixtape.com/mixtape.php?a=getMix&id=%s&userId=null&code=' % playlist_no - pl_req = sanitized_Request(pl_url) - pl_req.add_header('X-Requested-With', 'XMLHttpRequest') - playlist = self._download_json( - pl_req, playlist_id, note='Downloading playlist info') - - entries = [{ - '_type': 'url', - 'url': t['url'], - 'title': t['title'], - } for t in playlist['tracks']] - - if mobj.group('songnr'): - songnr = int(mobj.group('songnr')) - 1 - return entries[songnr] - - playlist_title = playlist['mixData']['name'] - return { - '_type': 'playlist', - 'id': playlist_id, - 'title': playlist_title, - 'entries': entries, - } diff --git a/yt_dlp/extractor/fxnetworks.py b/yt_dlp/extractor/fxnetworks.py deleted file mode 100644 index 370b0a597..000000000 --- a/yt_dlp/extractor/fxnetworks.py +++ /dev/null @@ -1,74 +0,0 @@ -from .adobepass import AdobePassIE -from ..utils import ( - extract_attributes, - int_or_none, - parse_age_limit, - smuggle_url, - update_url_query, -) - - -class FXNetworksIE(AdobePassIE): - _VALID_URL = r'https?://(?:www\.)?(?:fxnetworks|simpsonsworld)\.com/video/(?P\d+)' - _TESTS = [{ - 'url': 'http://www.fxnetworks.com/video/1032565827847', - 'md5': '8d99b97b4aa7a202f55b6ed47ea7e703', - 'info_dict': { - 'id': 'dRzwHC_MMqIv', - 'ext': 'mp4', - 'title': 'First Look: Better Things - Season 2', - 'description': 'Because real life is like a fart. Watch this FIRST LOOK to see what inspired the new season of Better Things.', - 'age_limit': 14, - 'uploader': 'NEWA-FNG-FX', - 'upload_date': '20170825', - 'timestamp': 1503686274, - 'episode_number': 0, - 'season_number': 2, - 'series': 'Better Things', - }, - 'add_ie': ['ThePlatform'], - }, { - 'url': 'http://www.simpsonsworld.com/video/716094019682', - 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - if 'The content you are trying to access is not available in your region.' in webpage: - self.raise_geo_restricted() - video_data = extract_attributes(self._search_regex( - r'()', webpage, 'video data')) - player_type = self._search_regex(r'playerType\s*=\s*[\'"]([^\'"]+)', webpage, 'player type', default=None) - release_url = video_data['rel'] - title = video_data['data-title'] - rating = video_data.get('data-rating') - query = { - 'mbr': 'true', - } - if player_type == 'movies': - query.update({ - 'manifest': 'm3u', - }) - else: - query.update({ - 'switch': 'http', - }) - if video_data.get('data-req-auth') == '1': - resource = self._get_mvpd_resource( - video_data['data-channel'], title, - video_data.get('data-guid'), rating) - query['auth'] = self._extract_mvpd_auth(url, video_id, 'fx', resource) - - return { - '_type': 'url_transparent', - 'id': video_id, - 'title': title, - 'url': smuggle_url(update_url_query(release_url, query), {'force_smil_url': True}), - 'series': video_data.get('data-show-title'), - 'episode_number': int_or_none(video_data.get('data-episode')), - 'season_number': int_or_none(video_data.get('data-season')), - 'thumbnail': video_data.get('data-large-thumb'), - 'age_limit': parse_age_limit(rating), - 'ie_key': 'ThePlatform', - } diff --git a/yt_dlp/extractor/kanalplay.py b/yt_dlp/extractor/kanalplay.py deleted file mode 100644 index ef74014c0..000000000 --- a/yt_dlp/extractor/kanalplay.py +++ /dev/null @@ -1,92 +0,0 @@ -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - float_or_none, - srt_subtitles_timecode, -) - - -class KanalPlayIE(InfoExtractor): - IE_DESC = 'Kanal 5/9/11 Play' - _VALID_URL = r'https?://(?:www\.)?kanal(?P5|9|11)play\.se/(?:#!/)?(?:play/)?program/\d+/video/(?P\d+)' - _TESTS = [{ - 'url': 'http://www.kanal5play.se/#!/play/program/3060212363/video/3270012277', - 'info_dict': { - 'id': '3270012277', - 'ext': 'flv', - 'title': 'Saknar både dusch och avlopp', - 'description': 'md5:6023a95832a06059832ae93bc3c7efb7', - 'duration': 2636.36, - }, - 'params': { - # rtmp download - 'skip_download': True, - } - }, { - 'url': 'http://www.kanal9play.se/#!/play/program/335032/video/246042', - 'only_matching': True, - }, { - 'url': 'http://www.kanal11play.se/#!/play/program/232835958/video/367135199', - 'only_matching': True, - }] - - def _fix_subtitles(self, subs): - return '\r\n\r\n'.join( - '%s\r\n%s --> %s\r\n%s' - % ( - num, - srt_subtitles_timecode(item['startMillis'] / 1000.0), - srt_subtitles_timecode(item['endMillis'] / 1000.0), - item['text'], - ) for num, item in enumerate(subs, 1)) - - def _get_subtitles(self, channel_id, video_id): - subs = self._download_json( - 'http://www.kanal%splay.se/api/subtitles/%s' % (channel_id, video_id), - video_id, 'Downloading subtitles JSON', fatal=False) - return {'sv': [{'ext': 'srt', 'data': self._fix_subtitles(subs)}]} if subs else {} - - def _real_extract(self, url): - mobj = self._match_valid_url(url) - video_id = mobj.group('id') - channel_id = mobj.group('channel_id') - - video = self._download_json( - 'http://www.kanal%splay.se/api/getVideo?format=FLASH&videoId=%s' % (channel_id, video_id), - video_id) - - reasons_for_no_streams = video.get('reasonsForNoStreams') - if reasons_for_no_streams: - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, '\n'.join(reasons_for_no_streams)), - expected=True) - - title = video['title'] - description = video.get('description') - duration = float_or_none(video.get('length'), 1000) - thumbnail = video.get('posterUrl') - - stream_base_url = video['streamBaseUrl'] - - formats = [{ - 'url': stream_base_url, - 'play_path': stream['source'], - 'ext': 'flv', - 'tbr': float_or_none(stream.get('bitrate'), 1000), - 'rtmp_real_time': True, - } for stream in video['streams']] - self._sort_formats(formats) - - subtitles = {} - if video.get('hasSubtitle'): - subtitles = self.extract_subtitles(channel_id, video_id) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'formats': formats, - 'subtitles': subtitles, - } diff --git a/yt_dlp/extractor/noco.py b/yt_dlp/extractor/noco.py deleted file mode 100644 index 583d399cc..000000000 --- a/yt_dlp/extractor/noco.py +++ /dev/null @@ -1,225 +0,0 @@ -import re -import time -import hashlib - -from .common import InfoExtractor -from ..compat import ( - compat_str, -) -from ..utils import ( - clean_html, - ExtractorError, - int_or_none, - float_or_none, - parse_iso8601, - parse_qs, - sanitized_Request, - urlencode_postdata, -) - - -class NocoIE(InfoExtractor): - _VALID_URL = r'https?://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P\d+)' - _LOGIN_URL = 'https://noco.tv/do.php' - _API_URL_TEMPLATE = 'https://api.noco.tv/1.1/%s?ts=%s&tk=%s' - _SUB_LANG_TEMPLATE = '&sub_lang=%s' - _NETRC_MACHINE = 'noco' - - _TESTS = [ - { - 'url': 'http://noco.tv/emission/11538/nolife/ami-ami-idol-hello-france/', - 'md5': '0a993f0058ddbcd902630b2047ef710e', - 'info_dict': { - 'id': '11538', - 'ext': 'mp4', - 'title': 'Ami Ami Idol - Hello! France', - 'description': 'md5:4eaab46ab68fa4197a317a88a53d3b86', - 'upload_date': '20140412', - 'uploader': 'Nolife', - 'uploader_id': 'NOL', - 'duration': 2851.2, - }, - 'skip': 'Requires noco account', - }, - { - 'url': 'http://noco.tv/emission/12610/lbl42/the-guild/s01e01-wake-up-call', - 'md5': 'c190f1f48e313c55838f1f412225934d', - 'info_dict': { - 'id': '12610', - 'ext': 'mp4', - 'title': 'The Guild #1 - Wake-Up Call', - 'timestamp': 1403863200, - 'upload_date': '20140627', - 'uploader': 'LBL42', - 'uploader_id': 'LBL', - 'duration': 233.023, - }, - 'skip': 'Requires noco account', - } - ] - - def _perform_login(self, username, password): - login = self._download_json( - self._LOGIN_URL, None, 'Logging in', - data=urlencode_postdata({ - 'a': 'login', - 'cookie': '1', - 'username': username, - 'password': password, - }), - headers={ - 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', - }) - - if 'erreur' in login: - raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True) - - @staticmethod - def _ts(): - return int(time.time() * 1000) - - def _call_api(self, path, video_id, note, sub_lang=None): - ts = compat_str(self._ts() + self._ts_offset) - tk = hashlib.md5((hashlib.md5(ts.encode('ascii')).hexdigest() + '#8S?uCraTedap6a').encode('ascii')).hexdigest() - url = self._API_URL_TEMPLATE % (path, ts, tk) - if sub_lang: - url += self._SUB_LANG_TEMPLATE % sub_lang - - request = sanitized_Request(url) - request.add_header('Referer', self._referer) - - resp = self._download_json(request, video_id, note) - - if isinstance(resp, dict) and resp.get('error'): - self._raise_error(resp['error'], resp['description']) - - return resp - - def _raise_error(self, error, description): - raise ExtractorError( - '%s returned error: %s - %s' % (self.IE_NAME, error, description), - expected=True) - - def _real_extract(self, url): - video_id = self._match_id(url) - - # Timestamp adjustment offset between server time and local time - # must be calculated in order to use timestamps closest to server's - # in all API requests (see https://github.com/ytdl-org/youtube-dl/issues/7864) - webpage = self._download_webpage(url, video_id) - - player_url = self._search_regex( - r'(["\'])(?Phttps?://noco\.tv/(?:[^/]+/)+NocoPlayer.+?\.swf.*?)\1', - webpage, 'noco player', group='player', - default='http://noco.tv/cdata/js/player/NocoPlayer-v1.2.40.swf') - - qs = parse_qs(player_url) - ts = int_or_none(qs.get('ts', [None])[0]) - self._ts_offset = ts - self._ts() if ts else 0 - self._referer = player_url - - medias = self._call_api( - 'shows/%s/medias' % video_id, - video_id, 'Downloading video JSON') - - show = self._call_api( - 'shows/by_id/%s' % video_id, - video_id, 'Downloading show JSON')[0] - - options = self._call_api( - 'users/init', video_id, - 'Downloading user options JSON')['options'] - audio_lang_pref = options.get('audio_language') or options.get('language', 'fr') - - if audio_lang_pref == 'original': - audio_lang_pref = show['original_lang'] - if len(medias) == 1: - audio_lang_pref = list(medias.keys())[0] - elif audio_lang_pref not in medias: - audio_lang_pref = 'fr' - - qualities = self._call_api( - 'qualities', - video_id, 'Downloading qualities JSON') - - formats = [] - - for audio_lang, audio_lang_dict in medias.items(): - preference = 1 if audio_lang == audio_lang_pref else 0 - for sub_lang, lang_dict in audio_lang_dict['video_list'].items(): - for format_id, fmt in lang_dict['quality_list'].items(): - format_id_extended = 'audio-%s_sub-%s_%s' % (audio_lang, sub_lang, format_id) - - video = self._call_api( - 'shows/%s/video/%s/%s' % (video_id, format_id.lower(), audio_lang), - video_id, 'Downloading %s video JSON' % format_id_extended, - sub_lang if sub_lang != 'none' else None) - - file_url = video['file'] - if not file_url: - continue - - if file_url in ['forbidden', 'not found']: - popmessage = video['popmessage'] - self._raise_error(popmessage['title'], popmessage['message']) - - formats.append({ - 'url': file_url, - 'format_id': format_id_extended, - 'width': int_or_none(fmt.get('res_width')), - 'height': int_or_none(fmt.get('res_lines')), - 'abr': int_or_none(fmt.get('audiobitrate'), 1000), - 'vbr': int_or_none(fmt.get('videobitrate'), 1000), - 'filesize': int_or_none(fmt.get('filesize')), - 'format_note': qualities[format_id].get('quality_name'), - 'quality': qualities[format_id].get('priority'), - 'language_preference': preference, - }) - - self._sort_formats(formats) - - timestamp = parse_iso8601(show.get('online_date_start_utc'), ' ') - - if timestamp is not None and timestamp < 0: - timestamp = None - - uploader = show.get('partner_name') - uploader_id = show.get('partner_key') - duration = float_or_none(show.get('duration_ms'), 1000) - - thumbnails = [] - for thumbnail_key, thumbnail_url in show.items(): - m = re.search(r'^screenshot_(?P\d+)x(?P\d+)$', thumbnail_key) - if not m: - continue - thumbnails.append({ - 'url': thumbnail_url, - 'width': int(m.group('width')), - 'height': int(m.group('height')), - }) - - episode = show.get('show_TT') or show.get('show_OT') - family = show.get('family_TT') or show.get('family_OT') - episode_number = show.get('episode_number') - - title = '' - if family: - title += family - if episode_number: - title += ' #' + compat_str(episode_number) - if episode: - title += ' - ' + compat_str(episode) - - description = show.get('show_resume') or show.get('family_resume') - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnails': thumbnails, - 'timestamp': timestamp, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'duration': duration, - 'formats': formats, - } diff --git a/yt_dlp/extractor/spiegeltv.py b/yt_dlp/extractor/spiegeltv.py deleted file mode 100644 index 69942334e..000000000 --- a/yt_dlp/extractor/spiegeltv.py +++ /dev/null @@ -1,15 +0,0 @@ -from .common import InfoExtractor -from .nexx import NexxIE - - -class SpiegeltvIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/videos/(?P\d+)' - _TEST = { - 'url': 'http://www.spiegel.tv/videos/161681-flug-mh370/', - 'only_matching': True, - } - - def _real_extract(self, url): - return self.url_result( - 'https://api.nexx.cloud/v3/748/videos/byid/%s' - % self._match_id(url), ie=NexxIE.ie_key()) diff --git a/yt_dlp/extractor/tastytrade.py b/yt_dlp/extractor/tastytrade.py deleted file mode 100644 index bb26926e8..000000000 --- a/yt_dlp/extractor/tastytrade.py +++ /dev/null @@ -1,41 +0,0 @@ -from .common import InfoExtractor -from .ooyala import OoyalaIE - - -class TastyTradeIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tastytrade\.com/tt/shows/[^/]+/episodes/(?P[^/?#&]+)' - - _TESTS = [{ - 'url': 'https://www.tastytrade.com/tt/shows/market-measures/episodes/correlation-in-short-volatility-06-28-2017', - 'info_dict': { - 'id': 'F3bnlzbToeI6pLEfRyrlfooIILUjz4nM', - 'ext': 'mp4', - 'title': 'A History of Teaming', - 'description': 'md5:2a9033db8da81f2edffa4c99888140b3', - 'duration': 422.255, - }, - 'params': { - 'skip_download': True, - }, - 'add_ie': ['Ooyala'], - }, { - 'url': 'https://www.tastytrade.com/tt/shows/daily-dose/episodes/daily-dose-06-30-2017', - 'only_matching': True, - }] - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - - ooyala_code = self._search_regex( - r'data-media-id=(["\'])(?P(?:(?!\1).)+)\1', - webpage, 'ooyala code', group='code') - - info = self._search_json_ld(webpage, display_id, fatal=False) - info.update({ - '_type': 'url_transparent', - 'ie_key': OoyalaIE.ie_key(), - 'url': 'ooyala:%s' % ooyala_code, - 'display_id': display_id, - }) - return info diff --git a/yt_dlp/extractor/tudou.py b/yt_dlp/extractor/tudou.py deleted file mode 100644 index 69774ee38..000000000 --- a/yt_dlp/extractor/tudou.py +++ /dev/null @@ -1,45 +0,0 @@ -from .common import InfoExtractor - - -class TudouPlaylistIE(InfoExtractor): - IE_NAME = 'tudou:playlist' - _VALID_URL = r'https?://(?:www\.)?tudou\.com/listplay/(?P[\w-]{11})\.html' - _TESTS = [{ - 'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo.html', - 'info_dict': { - 'id': 'zzdE77v6Mmo', - }, - 'playlist_mincount': 209, - }] - - def _real_extract(self, url): - playlist_id = self._match_id(url) - playlist_data = self._download_json( - 'http://www.tudou.com/tvp/plist.action?lcode=%s' % playlist_id, playlist_id) - entries = [self.url_result( - 'http://www.tudou.com/programs/view/%s' % item['icode'], - 'Tudou', item['icode'], - item['kw']) for item in playlist_data['items']] - return self.playlist_result(entries, playlist_id) - - -class TudouAlbumIE(InfoExtractor): - IE_NAME = 'tudou:album' - _VALID_URL = r'https?://(?:www\.)?tudou\.com/album(?:cover|play)/(?P[\w-]{11})' - _TESTS = [{ - 'url': 'http://www.tudou.com/albumplay/v5qckFJvNJg.html', - 'info_dict': { - 'id': 'v5qckFJvNJg', - }, - 'playlist_mincount': 45, - }] - - def _real_extract(self, url): - album_id = self._match_id(url) - album_data = self._download_json( - 'http://www.tudou.com/tvp/alist.action?acode=%s' % album_id, album_id) - entries = [self.url_result( - 'http://www.tudou.com/programs/view/%s' % item['icode'], - 'Tudou', item['icode'], - item['kw']) for item in album_data['items']] - return self.playlist_result(entries, album_id) diff --git a/yt_dlp/extractor/vidzi.py b/yt_dlp/extractor/vidzi.py deleted file mode 100644 index efa9be116..000000000 --- a/yt_dlp/extractor/vidzi.py +++ /dev/null @@ -1,65 +0,0 @@ -import re - -from .common import InfoExtractor -from ..utils import ( - decode_packed_codes, - js_to_json, - NO_DEFAULT, - PACKED_CODES_RE, -) - - -class VidziIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?vidzi\.(?:tv|cc|si|nu)/(?:embed-)?(?P[0-9a-zA-Z]+)' - _TESTS = [{ - 'url': 'http://vidzi.tv/cghql9yq6emu.html', - 'md5': '4f16c71ca0c8c8635ab6932b5f3f1660', - 'info_dict': { - 'id': 'cghql9yq6emu', - 'ext': 'mp4', - 'title': 'youtube-dl test video 1\\\\2\'3/4<5\\\\6ä7↭', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }, { - 'url': 'http://vidzi.tv/embed-4z2yb0rzphe9-600x338.html', - 'only_matching': True, - }, { - 'url': 'http://vidzi.cc/cghql9yq6emu.html', - 'only_matching': True, - }, { - 'url': 'https://vidzi.si/rph9gztxj1et.html', - 'only_matching': True, - }, { - 'url': 'http://vidzi.nu/cghql9yq6emu.html', - 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage( - 'http://vidzi.tv/%s' % video_id, video_id) - title = self._html_search_regex( - r'(?s)

(.*?)

', webpage, 'title') - - codes = [webpage] - codes.extend([ - decode_packed_codes(mobj.group(0)).replace('\\\'', '\'') - for mobj in re.finditer(PACKED_CODES_RE, webpage)]) - for num, code in enumerate(codes, 1): - jwplayer_data = self._parse_json( - self._search_regex( - r'setup\(([^)]+)\)', code, 'jwplayer data', - default=NO_DEFAULT if num == len(codes) else '{}'), - video_id, transform_source=lambda s: js_to_json( - re.sub(r'\s*\+\s*window\[.+?\]', '', s))) - if jwplayer_data: - break - - info_dict = self._parse_jwplayer_data(jwplayer_data, video_id, require_title=False) - info_dict['title'] = title - - return info_dict