summaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
authorSergey M․ <[email protected]>2017-09-10 22:08:32 +0700
committerSergey M․ <[email protected]>2017-09-10 22:08:32 +0700
commitbf6ec2fea9087235c14df2a079620fcc2c17b5eb (patch)
tree06c679cd57af0872554d855f4444706f8999c1f8
parentc3dd44e08577c2ae0d08951037db5d1db7a321c3 (diff)
downloadyoutube-dl-bf6ec2fea9087235c14df2a079620fcc2c17b5eb.tar.gz
youtube-dl-bf6ec2fea9087235c14df2a079620fcc2c17b5eb.zip
[fox] Fix extraction (#14147)
-rw-r--r--youtube_dl/extractor/fox.py125
1 files changed, 84 insertions, 41 deletions
diff --git a/youtube_dl/extractor/fox.py b/youtube_dl/extractor/fox.py
index 159fdf9c4..facc665f6 100644
--- a/youtube_dl/extractor/fox.py
+++ b/youtube_dl/extractor/fox.py
@@ -3,56 +3,99 @@ from __future__ import unicode_literals
from .adobepass import AdobePassIE
from ..utils import (
- smuggle_url,
- update_url_query,
+ int_or_none,
+ parse_age_limit,
+ parse_duration,
+ try_get,
+ unified_timestamp,
)
class FOXIE(AdobePassIE):
- _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[0-9]+)'
- _TEST = {
- 'url': 'http://www.fox.com/watch/255180355939/7684182528',
+ _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[\da-fA-F]+)'
+ _TESTS = [{
+ # clip
+ 'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/',
'md5': 'ebd296fcc41dd4b19f8115d8461a3165',
'info_dict': {
- 'id': '255180355939',
+ 'id': '4b765a60490325103ea69888fb2bd4e8',
'ext': 'mp4',
- 'title': 'Official Trailer: Gotham',
- 'description': 'Tracing the rise of the great DC Comics Super-Villains and vigilantes, Gotham reveals an entirely new chapter that has never been told.',
- 'duration': 129,
- 'timestamp': 1400020798,
- 'upload_date': '20140513',
- 'uploader': 'NEWA-FNG-FOXCOM',
+ 'title': 'Aftermath: Bruce Wayne Develops Into The Dark Knight',
+ 'description': 'md5:549cd9c70d413adb32ce2a779b53b486',
+ 'duration': 102,
+ 'timestamp': 1504291893,
+ 'upload_date': '20170901',
+ 'creator': 'FOX',
+ 'series': 'Gotham',
},
- 'add_ie': ['ThePlatform'],
- }
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
+ # episode, geo-restricted
+ 'url': 'https://www.fox.com/watch/087036ca7f33c8eb79b08152b4dd75c1/',
+ 'only_matching': True,
+ }, {
+ # episode, geo-restricted, tv provided required
+ 'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
-
- settings = self._parse_json(self._search_regex(
- r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
- webpage, 'drupal settings'), video_id)
- fox_pdk_player = settings['fox_pdk_player']
- release_url = fox_pdk_player['release_url']
- query = {
- 'mbr': 'true',
- 'switch': 'http'
- }
- if fox_pdk_player.get('access') == 'locked':
- ap_p = settings['foxAdobePassProvider']
- rating = ap_p.get('videoRating')
- if rating == 'n/a':
- rating = None
- resource = self._get_mvpd_resource('fbc-fox', None, ap_p['videoGUID'], rating)
- query['auth'] = self._extract_mvpd_auth(url, video_id, 'fbc-fox', resource)
-
- info = self._search_json_ld(webpage, video_id, fatal=False)
- info.update({
- '_type': 'url_transparent',
- 'ie_key': 'ThePlatform',
- 'url': smuggle_url(update_url_query(release_url, query), {'force_smil_url': True}),
- 'id': video_id,
- })
- return info
+ video = self._download_json(
+ 'https://api.fox.com/fbc-content/v1_4/video/%s' % video_id,
+ video_id, headers={
+ 'apikey': 'abdcbed02c124d393b39e818a4312055',
+ 'Content-Type': 'application/json',
+ 'Referer': url,
+ })
+
+ title = video['name']
+
+ m3u8_url = self._download_json(
+ video['videoRelease']['url'], video_id)['playURL']
+
+ formats = self._extract_m3u8_formats(
+ m3u8_url, video_id, 'mp4',
+ entry_protocol='m3u8_native', m3u8_id='hls')
+ self._sort_formats(formats)
+
+ description = video.get('description')
+ duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
+ video.get('duration')) or parse_duration(video.get('duration'))
+ timestamp = unified_timestamp(video.get('datePublished'))
+ age_limit = parse_age_limit(video.get('contentRating'))
+
+ data = try_get(
+ video, lambda x: x['trackingData']['properties'], dict) or {}
+
+ creator = data.get('brand') or data.get('network') or video.get('network')
+
+ series = video.get('seriesName') or data.get(
+ 'seriesName') or data.get('show')
+ season_number = int_or_none(video.get('seasonNumber'))
+ episode = video.get('name')
+ episode_number = int_or_none(video.get('episodeNumber'))
+ release_year = int_or_none(video.get('releaseYear'))
+
+ if data.get('authRequired'):
+ # TODO: AP
+ pass
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': description,
+ 'duration': duration,
+ 'timestamp': timestamp,
+ 'age_limit': age_limit,
+ 'creator': creator,
+ 'series': series,
+ 'season_number': season_number,
+ 'episode': episode,
+ 'episode_number': episode_number,
+ 'release_year': release_year,
+ 'formats': formats,
+ }