Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-02 09:12:40 +01:00
Code Issues Releases Activity

[adultswim] Fix Extraction(closes #8640)(closes #10950)(closes closes #11042)(closes #12121)

Browse Source 
- add support for adobe pass authentication
- add support for live streams
- add support for show pages
This commit is contained in:
Remita Amine 2017-05-08 15:01:10 +01:00
parent 04c09f1961
commit 3b859145c2
1 changed files with 106 additions and 179 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

285
youtube_dl/extractor/adultswim.py
View File

@ -5,91 +5,52 @@
from .turner import TurnerBaseIE from .turner import TurnerBaseIE
from ..utils import ( from ..utils import (
ExtractorError,
int_or_none, int_or_none,
strip_or_none,
) )
class AdultSwimIE(TurnerBaseIE): class AdultSwimIE(TurnerBaseIE):
_VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?' _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<show_path>[^/?#]+)(?:/(?P<episode_path>[^/?#]+))?'
_TESTS = [{ _TESTS = [{
'url': 'http://adultswim.com/videos/rick-and-morty/pilot', 'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
'playlist': [
{
'md5': '247572debc75c7652f253c8daa51a14d',
'info_dict': {
'id': 'rQxZvXQ4ROaSOqq-or2Mow-0',
'ext': 'flv',
'title': 'Rick and Morty - Pilot Part 1',
'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
},
},
{
'md5': '77b0e037a4b20ec6b98671c4c379f48d',
'info_dict': {
'id': 'rQxZvXQ4ROaSOqq-or2Mow-3',
'ext': 'flv',
'title': 'Rick and Morty - Pilot Part 4',
'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
},
},
],
'info_dict': { 'info_dict': {
'id': 'rQxZvXQ4ROaSOqq-or2Mow', 'id': 'rQxZvXQ4ROaSOqq-or2Mow',
'ext': 'mp4',
'title': 'Rick and Morty - Pilot', 'title': 'Rick and Morty - Pilot',
'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. " 'description': 'Rick moves in with his daughter\'s family and establishes himself as a bad influence on his grandson, Morty.',
}, 'timestamp': 1493267400,
'skip': 'This video is only available for registered users', 'upload_date': '20170427',
}, {
'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
'playlist': [
{
'md5': '2eb5c06d0f9a1539da3718d897f13ec5',
'info_dict': {
'id': '-t8CamQlQ2aYZ49ItZCFog-0',
'ext': 'flv',
'title': 'American Dad - Putting Francine Out of Business',
'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
},
}
],
'info_dict': {
'id': '-t8CamQlQ2aYZ49ItZCFog',
'title': 'American Dad - Putting Francine Out of Business',
'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
},
}, {
'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
'playlist': [
{
'md5': '3e346a2ab0087d687a05e1e7f3b3e529',
'info_dict': {
'id': 'sY3cMUR_TbuE4YmdjzbIcQ-0',
'ext': 'mp4',
'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
'description': 'Dr. Brule reports live from Wine Country with a special report on wines. \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
},
}
],
'info_dict': {
'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
'description': 'Dr. Brule reports live from Wine Country with a special report on wines. \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
}, },
'params': { 'params': {
# m3u8 download # m3u8 download
'skip_download': True, 'skip_download': True,
} },
'expected_warnings': ['Unable to download f4m manifest'],
}, {
'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
'info_dict': {
'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
'ext': 'mp4',
'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
'description': 'Dr. Brule reports live from Wine Country with a special report on wines. \nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.',
'upload_date': '20080124',
'timestamp': 1201150800,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, { }, {
# heroMetadata.trailer
'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/', 'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
'info_dict': { 'info_dict': {
'id': 'I0LQFQkaSUaFp8PnAWHhoQ', 'id': 'I0LQFQkaSUaFp8PnAWHhoQ',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Decker - Inside Decker: A New Hero', 'title': 'Decker - Inside Decker: A New Hero',
'description': 'md5:c916df071d425d62d70c86d4399d3ee0', 'description': 'The guys recap the conclusion of the season. They announce a new hero, take a peek into the Victorville Film Archive and welcome back the talented James Dean.',
'duration': 249.008, 'timestamp': 1469480460,
'upload_date': '20160725',
}, },
'params': { 'params': {
# m3u8 download # m3u8 download
@ -97,136 +58,102 @@ class AdultSwimIE(TurnerBaseIE):
}, },
'expected_warnings': ['Unable to download f4m manifest'], 'expected_warnings': ['Unable to download f4m manifest'],
}, { }, {
'url': 'http://www.adultswim.com/videos/toonami/friday-october-14th-2016/', 'url': 'http://www.adultswim.com/videos/attack-on-titan',
'info_dict': { 'info_dict': {
'id': 'eYiLsKVgQ6qTC6agD67Sig', 'id': 'b7A69dzfRzuaXIECdxW8XQ',
'title': 'Toonami - Friday, October 14th, 2016', 'title': 'Attack on Titan',
'description': 'md5:99892c96ffc85e159a428de85c30acde', 'description': 'md5:6c8e003ea0777b47013e894767f5e114',
},
'playlist_mincount': 12,
}, {
'url': 'http://www.adultswim.com/videos/streams/williams-stream',
'info_dict': {
'id': 'd8DEBj7QRfetLsRgFnGEyg',
'ext': 'mp4',
'title': r're:^Williams Stream \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'description': 'original programming',
}, },
'playlist': [{
'md5': '',
'info_dict': {
'id': 'eYiLsKVgQ6qTC6agD67Sig',
'ext': 'mp4',
'title': 'Toonami - Friday, October 14th, 2016',
'description': 'md5:99892c96ffc85e159a428de85c30acde',
},
}],
'params': { 'params': {
# m3u8 download # m3u8 download
'skip_download': True, 'skip_download': True,
}, },
'expected_warnings': ['Unable to download f4m manifest'],
}] }]
@staticmethod
def find_video_info(collection, slug):
for video in collection.get('videos'):
if video.get('slug') == slug:
return video
@staticmethod
def find_collection_by_linkURL(collections, linkURL):
for collection in collections:
if collection.get('linkURL') == linkURL:
return collection
@staticmethod
def find_collection_containing_video(collections, slug):
for collection in collections:
for video in collection.get('videos'):
if video.get('slug') == slug:
return collection, video
return None, None
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) show_path, episode_path = re.match(self._VALID_URL, url).groups()
show_path = mobj.group('show_path') display_id = episode_path or show_path
episode_path = mobj.group('episode_path') webpage = self._download_webpage(url, display_id)
is_playlist = True if mobj.group('is_playlist') else False initial_data = self._parse_json(self._search_regex(
r'AS_INITIAL_DATA(?:__)?\s*=\s*({.+?});',
webpage, 'initial data'), display_id)
webpage = self._download_webpage(url, episode_path) is_stream = show_path == 'streams'
if is_stream:
if not episode_path:
episode_path = 'live-stream'
# Extract the value of `bootstrappedData` from the Javascript in the page. video_data = next(stream for stream_path, stream in initial_data['streams'].items() if stream_path == episode_path)
bootstrapped_data = self._parse_json(self._search_regex( video_id = video_data.get('stream')
r'var bootstrappedData = ({.*});', webpage, 'bootstraped data'), episode_path)
# Downloading videos from a /videos/playlist/ URL needs to be handled differently. if not video_id:
# NOTE: We are only downloading one video (the current one) not the playlist entries = []
if is_playlist: for episode in video_data.get('archiveEpisodes', []):
collections = bootstrapped_data['playlists']['collections'] episode_url = episode.get('url')
collection = self.find_collection_by_linkURL(collections, show_path) if not episode_url:
video_info = self.find_video_info(collection, episode_path) continue
entries.append(self.url_result(
show_title = video_info['showTitle'] episode_url, 'AdultSwim', episode.get('id')))
segment_ids = [video_info['videoPlaybackID']] return self.playlist_result(
entries, video_data.get('id'), video_data.get('title'),
strip_or_none(video_data.get('description')))
else: else:
collections = bootstrapped_data['show']['collections'] show_data = initial_data['show']
collection, video_info = self.find_collection_containing_video(collections, episode_path)
# Video wasn't found in the collections, let's try `slugged_video`.
if video_info is None:
if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
video_info = bootstrapped_data['slugged_video']
if not video_info:
video_info = bootstrapped_data.get(
'heroMetadata', {}).get('trailer', {}).get('video')
if not video_info:
video_info = bootstrapped_data.get('onlineOriginals', [None])[0]
if not video_info:
raise ExtractorError('Unable to find video info')
show = bootstrapped_data['show'] if not episode_path:
show_title = show['title'] entries = []
stream = video_info.get('stream') for video in show_data.get('videos', []):
if stream and stream.get('videoPlaybackID'): slug = video.get('slug')
segment_ids = [stream['videoPlaybackID']] if not slug:
elif video_info.get('clips'): continue
segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']] entries.append(self.url_result(
elif video_info.get('videoPlaybackID'): 'http://adultswim.com/videos/%s/%s' % (show_path, slug),
segment_ids = [video_info['videoPlaybackID']] 'AdultSwim', video.get('id')))
elif video_info.get('id'): return self.playlist_result(
segment_ids = [video_info['id']] entries, show_data.get('id'), show_data.get('title'),
else: strip_or_none(show_data.get('metadata', {}).get('description')))
if video_info.get('auth') is True:
raise ExtractorError(
'This video is only available via cable service provider subscription that'
' is not currently supported. You may want to use --cookies.', expected=True)
else:
raise ExtractorError('Unable to find stream or clips')
episode_id = video_info['id'] video_data = show_data['sluggedVideo']
episode_title = video_info['title'] video_id = video_data['id']
episode_description = video_info.get('description')
episode_duration = int_or_none(video_info.get('duration'))
view_count = int_or_none(video_info.get('views'))
entries = [] info = self._extract_cvp_info(
for part_num, segment_id in enumerate(segment_ids): 'http://www.adultswim.com/videos/api/v0/assets?id=' + video_id,
segement_info = self._extract_cvp_info( video_id, {
'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id, 'secure': {
segment_id, { 'media_src': 'http://androidhls-secure.cdn.turner.com/adultswim/big',
'secure': { 'tokenizer_src': 'http://www.adultswim.com/astv/mvpd/processors/services/token_ipadAdobe.do',
'media_src': 'http://androidhls-secure.cdn.turner.com/adultswim/big', },
'tokenizer_src': 'http://www.adultswim.com/astv/mvpd/processors/services/token_ipadAdobe.do', }, {
}, 'url': url,
}) 'site_name': 'AdultSwim',
segment_title = '%s - %s' % (show_title, episode_title) 'auth_required': video_data.get('auth'),
if len(segment_ids) > 1:
segment_title += ' Part %d' % (part_num + 1)
segement_info.update({
'id': segment_id,
'title': segment_title,
'description': episode_description,
}) })
entries.append(segement_info)
return { info.update({
'_type': 'playlist', 'id': video_id,
'id': episode_id, 'display_id': display_id,
'display_id': episode_path, 'description': info.get('description') or strip_or_none(video_data.get('description')),
'entries': entries, })
'title': '%s - %s' % (show_title, episode_title), if not is_stream:
'description': episode_description, info.update({
'duration': episode_duration, 'duration': info.get('duration') or int_or_none(video_data.get('duration')),
'view_count': view_count, 'timestamp': info.get('timestamp') or int_or_none(video_data.get('launch_date')),
} 'season_number': info.get('season_number') or int_or_none(video_data.get('season_number')),
'episode': info['title'],
'episode_number': info.get('episode_number') or int_or_none(video_data.get('episode_number')),
})
info['series'] = video_data.get('collection_title') or info.get('series')
if info['series'] and info['series'] != info['title']:
info['title'] = '%s - %s' % (info['series'], info['title'])
return info