aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/adultswim.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/adultswim.py')
-rw-r--r--youtube_dl/extractor/adultswim.py281
1 files changed, 104 insertions, 177 deletions
diff --git a/youtube_dl/extractor/adultswim.py b/youtube_dl/extractor/adultswim.py
index 989505c82..9c37ea33c 100644
--- a/youtube_dl/extractor/adultswim.py
+++ b/youtube_dl/extractor/adultswim.py
@@ -5,91 +5,52 @@ import re
from .turner import TurnerBaseIE
from ..utils import (
- ExtractorError,
int_or_none,
+ strip_or_none,
)
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 = [{
'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': {
'id': 'rQxZvXQ4ROaSOqq-or2Mow',
+ 'ext': 'mp4',
'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,
+ 'upload_date': '20170427',
},
- 'skip': 'This video is only available for registered users',
- }, {
- '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].'
+ 'params': {
+ # m3u8 download
+ '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/',
- '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',
+ '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',
+ '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/',
'info_dict': {
'id': 'I0LQFQkaSUaFp8PnAWHhoQ',
'ext': 'mp4',
'title': 'Decker - Inside Decker: A New Hero',
- 'description': 'md5:c916df071d425d62d70c86d4399d3ee0',
- 'duration': 249.008,
+ '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.',
+ 'timestamp': 1469480460,
+ 'upload_date': '20160725',
},
'params': {
# m3u8 download
@@ -97,136 +58,102 @@ class AdultSwimIE(TurnerBaseIE):
},
'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': {
+ 'id': 'b7A69dzfRzuaXIECdxW8XQ',
+ 'title': 'Attack on Titan',
+ 'description': 'md5:6c8e003ea0777b47013e894767f5e114',
+ },
+ 'playlist_mincount': 12,
+ }, {
+ 'url': 'http://www.adultswim.com/videos/streams/williams-stream',
'info_dict': {
- 'id': 'eYiLsKVgQ6qTC6agD67Sig',
- 'title': 'Toonami - Friday, October 14th, 2016',
- 'description': 'md5:99892c96ffc85e159a428de85c30acde',
+ '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': {
# m3u8 download
'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):
- mobj = re.match(self._VALID_URL, url)
- show_path = mobj.group('show_path')
- episode_path = mobj.group('episode_path')
- is_playlist = True if mobj.group('is_playlist') else False
-
- webpage = self._download_webpage(url, episode_path)
-
- # Extract the value of `bootstrappedData` from the Javascript in the page.
- bootstrapped_data = self._parse_json(self._search_regex(
- r'var bootstrappedData = ({.*});', webpage, 'bootstraped data'), episode_path)
-
- # Downloading videos from a /videos/playlist/ URL needs to be handled differently.
- # NOTE: We are only downloading one video (the current one) not the playlist
- if is_playlist:
- collections = bootstrapped_data['playlists']['collections']
- collection = self.find_collection_by_linkURL(collections, show_path)
- video_info = self.find_video_info(collection, episode_path)
-
- show_title = video_info['showTitle']
- segment_ids = [video_info['videoPlaybackID']]
+ show_path, episode_path = re.match(self._VALID_URL, url).groups()
+ display_id = episode_path or show_path
+ webpage = self._download_webpage(url, display_id)
+ initial_data = self._parse_json(self._search_regex(
+ r'AS_INITIAL_DATA(?:__)?\s*=\s*({.+?});',
+ webpage, 'initial data'), display_id)
+
+ is_stream = show_path == 'streams'
+ if is_stream:
+ if not episode_path:
+ episode_path = 'live-stream'
+
+ video_data = next(stream for stream_path, stream in initial_data['streams'].items() if stream_path == episode_path)
+ video_id = video_data.get('stream')
+
+ if not video_id:
+ entries = []
+ for episode in video_data.get('archiveEpisodes', []):
+ episode_url = episode.get('url')
+ if not episode_url:
+ continue
+ entries.append(self.url_result(
+ episode_url, 'AdultSwim', episode.get('id')))
+ return self.playlist_result(
+ entries, video_data.get('id'), video_data.get('title'),
+ strip_or_none(video_data.get('description')))
else:
- collections = bootstrapped_data['show']['collections']
- 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']
- show_title = show['title']
- stream = video_info.get('stream')
- if stream and stream.get('videoPlaybackID'):
- segment_ids = [stream['videoPlaybackID']]
- elif video_info.get('clips'):
- segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
- elif video_info.get('videoPlaybackID'):
- segment_ids = [video_info['videoPlaybackID']]
- elif video_info.get('id'):
- segment_ids = [video_info['id']]
- else:
- 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']
- episode_title = video_info['title']
- episode_description = video_info.get('description')
- episode_duration = int_or_none(video_info.get('duration'))
- view_count = int_or_none(video_info.get('views'))
+ show_data = initial_data['show']
+
+ if not episode_path:
+ entries = []
+ for video in show_data.get('videos', []):
+ slug = video.get('slug')
+ if not slug:
+ continue
+ entries.append(self.url_result(
+ 'http://adultswim.com/videos/%s/%s' % (show_path, slug),
+ 'AdultSwim', video.get('id')))
+ return self.playlist_result(
+ entries, show_data.get('id'), show_data.get('title'),
+ strip_or_none(show_data.get('metadata', {}).get('description')))
+
+ video_data = show_data['sluggedVideo']
+ video_id = video_data['id']
+
+ info = self._extract_cvp_info(
+ 'http://www.adultswim.com/videos/api/v0/assets?id=' + video_id,
+ video_id, {
+ 'secure': {
+ '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',
+ 'auth_required': video_data.get('auth'),
+ })
- entries = []
- for part_num, segment_id in enumerate(segment_ids):
- segement_info = self._extract_cvp_info(
- 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id,
- segment_id, {
- 'secure': {
- 'media_src': 'http://androidhls-secure.cdn.turner.com/adultswim/big',
- 'tokenizer_src': 'http://www.adultswim.com/astv/mvpd/processors/services/token_ipadAdobe.do',
- },
- })
- segment_title = '%s - %s' % (show_title, episode_title)
- if len(segment_ids) > 1:
- segment_title += ' Part %d' % (part_num + 1)
- segement_info.update({
- 'id': segment_id,
- 'title': segment_title,
- 'description': episode_description,
+ info.update({
+ 'id': video_id,
+ 'display_id': display_id,
+ 'description': info.get('description') or strip_or_none(video_data.get('description')),
+ })
+ if not is_stream:
+ info.update({
+ 'duration': info.get('duration') or int_or_none(video_data.get('duration')),
+ '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')),
})
- entries.append(segement_info)
- return {
- '_type': 'playlist',
- 'id': episode_id,
- 'display_id': episode_path,
- 'entries': entries,
- 'title': '%s - %s' % (show_title, episode_title),
- 'description': episode_description,
- 'duration': episode_duration,
- 'view_count': view_count,
- }
+ 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