From 006374e3aebc3be3f20b7e812c987cdf15b3ae35 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 17 Nov 2018 23:59:20 +0700 Subject: [PATCH] [wwe] Fix issues, extract subtitles and add support for playlists (closes #14781, closes #17450) --- youtube_dl/extractor/wwe.py | 138 +++++++++++++++++++++++++++++------- 1 file changed, 111 insertions(+), 27 deletions(-) diff --git a/youtube_dl/extractor/wwe.py b/youtube_dl/extractor/wwe.py index c471a79f5e..bebc77bb54 100644 --- a/youtube_dl/extractor/wwe.py +++ b/youtube_dl/extractor/wwe.py @@ -1,20 +1,75 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..compat import compat_str -from ..utils import urljoin +from ..utils import ( + try_get, + unescapeHTML, + url_or_none, + urljoin, +) -class WWEIE(InfoExtractor): - _VALID_URL = r'https?://(?:\w+\.)?wwe.com/(?:.*/)?videos/(?P[\w-]+)' +class WWEBaseIE(InfoExtractor): + _SUBTITLE_LANGS = { + 'English': 'en', + 'Deutsch': 'de', + } + + def _extract_entry(self, data, url, video_id=None): + video_id = compat_str(video_id or data['nid']) + title = data['title'] + + formats = self._extract_m3u8_formats( + data['file'], video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + + description = data.get('description') + thumbnail = urljoin(url, data.get('image')) + series = data.get('show_name') + episode = data.get('episode_name') + + subtitles = {} + tracks = data.get('tracks') + if isinstance(tracks, list): + for track in tracks: + if not isinstance(track, dict): + continue + if track.get('kind') != 'captions': + continue + track_file = url_or_none(track.get('file')) + if not track_file: + continue + label = track.get('label') + lang = self._SUBTITLE_LANGS.get(label, label) or 'en' + subtitles.setdefault(lang, []).append({ + 'url': track_file, + }) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'series': series, + 'episode': episode, + 'formats': formats, + 'subtitles': subtitles, + } + + +class WWEIE(WWEBaseIE): + _VALID_URL = r'https?://(?:[^/]+\.)?wwe\.com/(?:[^/]+/)*videos/(?P[^/?#&]+)' _TESTS = [{ 'url': 'https://www.wwe.com/videos/daniel-bryan-vs-andrade-cien-almas-smackdown-live-sept-4-2018', - 'md5': '30cbc824b51f4010ea885bfcaec76972', + 'md5': '92811c6a14bfc206f7a6a9c5d9140184', 'info_dict': { 'id': '40048199', 'ext': 'mp4', 'title': 'Daniel Bryan vs. Andrade "Cien" Almas: SmackDown LIVE, Sept. 4, 2018', - 'description': 'Still fuming after he and his wife Brie Bella were attacked by The Miz and Maryse last week, Daniel Bryan takes care of some unfinished business with Andrade "Cien" Almas.', + 'description': 'md5:2d7424dbc6755c61a0e649d2a8677f67', 'thumbnail': r're:^https?://.*\.jpg$', } }, { @@ -26,31 +81,60 @@ def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - drupal_settings = self._parse_json( + landing = self._parse_json( self._html_search_regex( - r'(?s)Drupal\.settings\s*,\s*({.+?})\);', + r'(?s)Drupal\.settings\s*,\s*({.+?})\s*\)\s*;', webpage, 'drupal settings'), - display_id) + display_id)['WWEVideoLanding'] - player = drupal_settings['WWEVideoLanding']['initialVideo'] - metadata = player['playlist'][0] + data = landing['initialVideo']['playlist'][0] + video_id = landing.get('initialVideoId') - id = compat_str(metadata['nid']) - title = metadata.get('title') or self._og_search_title(webpage) - video_url = 'https:' + metadata['file'] - thumbnail = None - if metadata.get('image') is not None: - thumbnail = urljoin(url, metadata.get('image')) - description = metadata.get('description') + info = self._extract_entry(data, url, video_id) + info['display_id'] = display_id + return info - formats = self._extract_m3u8_formats(video_url, id, 'mp4') - return { - 'id': id, - 'title': title, - 'formats': formats, - 'url': video_url, - 'display_id': display_id, - 'thumbnail': thumbnail, - 'description': description, - } +class WWEPlaylistIE(WWEBaseIE): + _VALID_URL = r'https?://(?:[^/]+\.)?wwe\.com/(?:[^/]+/)*(?P[^/?#&]+)' + _TESTS = [{ + 'url': 'https://www.wwe.com/shows/raw/2018-11-12', + 'info_dict': { + 'id': '2018-11-12', + }, + 'playlist_mincount': 11, + }, { + 'url': 'http://www.wwe.com/article/walk-the-prank-wwe-edition', + 'only_matching': True, + }, { + 'url': 'https://www.wwe.com/shows/wwenxt/article/matt-riddle-interview', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + return False if WWEIE.suitable(url) else super(WWEPlaylistIE, cls).suitable(url) + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + entries = [] + for mobj in re.finditer( + r'data-video\s*=\s*(["\'])(?P{.+?})\1', webpage): + video = self._parse_json( + mobj.group('data'), display_id, transform_source=unescapeHTML, + fatal=False) + if not video: + continue + data = try_get(video, lambda x: x['playlist'][0], dict) + if not data: + continue + try: + entry = self._extract_entry(data, url) + except Exception: + continue + entry['extractor_key'] = WWEIE.ie_key() + entries.append(entry) + + return self.playlist_result(entries, display_id)