From 40d43e940cdf94c22e4ec9fe3a8b2ca2a9589115 Mon Sep 17 00:00:00 2001 From: Alex Seiler Date: Mon, 23 Oct 2017 21:15:48 +0200 Subject: [PATCH] [ellentube] Fix broken extractor (closes #14407) --- youtube_dl/extractor/ellentube.py | 114 +++++++++++++++++++++++++++++ youtube_dl/extractor/ellentv.py | 101 ------------------------- youtube_dl/extractor/extractors.py | 6 +- 3 files changed, 117 insertions(+), 104 deletions(-) create mode 100644 youtube_dl/extractor/ellentube.py delete mode 100644 youtube_dl/extractor/ellentv.py diff --git a/youtube_dl/extractor/ellentube.py b/youtube_dl/extractor/ellentube.py new file mode 100644 index 000000000..64276591e --- /dev/null +++ b/youtube_dl/extractor/ellentube.py @@ -0,0 +1,114 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + urljoin, +) + + +class EllenTubeBaseIE(InfoExtractor): + API_URL = 'https://api-prod.ellentube.com/' + + def _extract_from_video_id(self, video_id, display_id=None): + video_data = self._download_json( + urljoin(self.API_URL, 'ellenapi/api/item/%s' % video_id), video_id) + title = video_data['title'] + description = video_data.get('description') + publish_time = int_or_none(video_data.get('publishTime')) + thumbnail = video_data.get('thumbnail') + + formats = [] + duration = None + for entry in video_data.get('media'): + if entry.get('id') == 'm3u8': + formats = self._extract_m3u8_formats(entry.get( + 'url'), video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls') + duration = int_or_none(entry.get('duration')) + break + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'display_id': display_id, + 'duration': duration, + 'thumbnail': thumbnail, + 'timestamp': publish_time, + 'formats': formats, + } + + def _extract_video_ids_from_api_search(self, api_search, display_id): + feed_data = self._download_json( + urljoin(self.API_URL, 'ellenapi/api/feed/?%s' % api_search), display_id) + return [entry.get('id') for entry in feed_data if entry.get('type') == 'VIDEO'] + + +class EllenTubeVideoIE(EllenTubeBaseIE): + _VALID_URL = r'https?://(?:www\.)?ellentube\.com/video/(?P.+)\.html' + + _TEST = { + 'url': 'https://www.ellentube.com/video/ellen-meets-las-vegas-survivors-jesus-campos-and-stephen-schuck.html', + 'md5': '2fabc277131bddafdd120e0fc0f974c9', + 'info_dict': { + 'id': '0822171c-3829-43bf-b99f-d77358ae75e3', + 'ext': 'mp4', + 'title': 'Ellen Meets Las Vegas Survivors Jesus Campos and Stephen Schuck', + 'description': 'md5:76e3355e2242a78ad9e3858e5616923f', + 'display_id': 'ellen-meets-las-vegas-survivors-jesus-campos-and-stephen-schuck', + 'duration': 514, + 'timestamp': 1508505120000, + 'thumbnail': 'https://warnerbros-h.assetsadobe.com/is/image/content/dam/ellen/videos/episodes/season15/32/video--2728751654987218111', + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id_regex = r'data-config.+([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})' + video_id = self._search_regex(video_id_regex, webpage, 'video id') + return self._extract_from_video_id(video_id, display_id) + + +class EllenTubePlaylistIE(EllenTubeBaseIE): + _VALID_URL = r'https?://(?:www\.)?ellentube\.com/(?:episode|studios)/(?P.+)\.html' + + _TESTS = [{ + 'url': 'https://www.ellentube.com/episode/dax-shepard-jordan-fisher-haim.html', + 'info_dict': { + 'id': 'dax-shepard-jordan-fisher-haim', + 'title': 'Dax Shepard, \'DWTS\' Team Jordan Fisher & Lindsay Arnold, HAIM', + }, + 'playlist_count': 6, + }, { + 'url': 'https://www.ellentube.com/studios/macey-goes-rving0.html', + 'info_dict': { + 'id': 'macey-goes-rving0', + 'title': 'Macey Goes RVing', + }, + 'playlist_mincount': 3, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + playlist_data = self._html_search_regex( + r'', webpage, 'episode data') + playlist_title = self._search_regex( + r'title"\s*:\s*"(.+?)"', playlist_data, 'playlist title') + entries = [self._extract_from_video_id(m.group('vid')) for m in re.finditer( + r'pid=(?P[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})', playlist_data)] + if not entries: + api_search = self._search_regex( + r'filter"\s*:\s*"(.+?)"', playlist_data, 'api search') + video_ids = self._extract_video_ids_from_api_search( + api_search, display_id) + entries = [self._extract_from_video_id( + vid, display_id) for vid in video_ids] + + return self.playlist_result(entries, display_id, playlist_title) diff --git a/youtube_dl/extractor/ellentv.py b/youtube_dl/extractor/ellentv.py deleted file mode 100644 index e0a13dd76..000000000 --- a/youtube_dl/extractor/ellentv.py +++ /dev/null @@ -1,101 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from .kaltura import KalturaIE -from ..utils import NO_DEFAULT - - -class EllenTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P[a-z0-9_-]+)' - _TESTS = [{ - 'url': 'http://www.ellentv.com/videos/0-ipq1gsai/', - 'md5': '4294cf98bc165f218aaa0b89e0fd8042', - 'info_dict': { - 'id': '0_ipq1gsai', - 'ext': 'mov', - 'title': 'Fast Fingers of Fate', - 'description': 'md5:3539013ddcbfa64b2a6d1b38d910868a', - 'timestamp': 1428035648, - 'upload_date': '20150403', - 'uploader_id': 'batchUser', - }, - }, { - # not available via http://widgets.ellentube.com/ - 'url': 'http://www.ellentv.com/videos/1-szkgu2m2/', - 'info_dict': { - 'id': '1_szkgu2m2', - 'ext': 'flv', - 'title': "Ellen's Amazingly Talented Audience", - 'description': 'md5:86ff1e376ff0d717d7171590e273f0a5', - 'timestamp': 1255140900, - 'upload_date': '20091010', - 'uploader_id': 'ellenkaltura@gmail.com', - }, - 'params': { - 'skip_download': True, - }, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - URLS = ('http://widgets.ellentube.com/videos/%s' % video_id, url) - - for num, url_ in enumerate(URLS, 1): - webpage = self._download_webpage( - url_, video_id, fatal=num == len(URLS)) - - default = NO_DEFAULT if num == len(URLS) else None - - partner_id = self._search_regex( - r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id', - default=default) - - kaltura_id = self._search_regex( - [r'id="kaltura_player_([^"]+)"', - r"_wb_entry_id\s*:\s*'([^']+)", - r'data-kaltura-entry-id="([^"]+)'], - webpage, 'kaltura id', default=default) - - if partner_id and kaltura_id: - break - - return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), KalturaIE.ie_key()) - - -class EllenTVClipsIE(InfoExtractor): - IE_NAME = 'EllenTV:clips' - _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P[a-z0-9_-]+)' - _TEST = { - 'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/', - 'info_dict': { - 'id': 'meryl-streep-vanessa-hudgens', - 'title': 'Meryl Streep, Vanessa Hudgens', - }, - 'playlist_mincount': 5, - } - - def _real_extract(self, url): - playlist_id = self._match_id(url) - - webpage = self._download_webpage(url, playlist_id) - playlist = self._extract_playlist(webpage, playlist_id) - - return { - '_type': 'playlist', - 'id': playlist_id, - 'title': self._og_search_title(webpage), - 'entries': self._extract_entries(playlist) - } - - def _extract_playlist(self, webpage, playlist_id): - json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json') - return self._parse_json('[{' + json_string + '}]', playlist_id) - - def _extract_entries(self, playlist): - return [ - self.url_result( - 'kaltura:%s:%s' % (item['kaltura_partner_id'], item['kaltura_entry_id']), - KalturaIE.ie_key(), video_id=item['kaltura_entry_id']) - for item in playlist] diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 09b20a39a..cb92475c7 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -308,9 +308,9 @@ from .ehow import EHowIE from .eighttracks import EightTracksIE from .einthusan import EinthusanIE from .eitb import EitbIE -from .ellentv import ( - EllenTVIE, - EllenTVClipsIE, +from .ellentube import ( + EllenTubePlaylistIE, + EllenTubeVideoIE, ) from .elpais import ElPaisIE from .embedly import EmbedlyIE