from __future__ import unicode_literals
import re
-import json
-from .common import InfoExtractor
+from .turner import TurnerBaseIE
from ..utils import (
- ExtractorError,
- xpath_text,
- float_or_none,
+ int_or_none,
+ strip_or_none,
+ url_or_none,
)
-class AdultSwimIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?'
+class AdultSwimIE(TurnerBaseIE):
+ _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',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ 'expected_warnings': ['Unable to download f4m manifest'],
}, {
- '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].'
- },
- }
- ],
+ 'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
'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].'
+ '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,
+ },
+ }, {
+ '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': '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
+ 'skip_download': True,
+ },
+ 'expected_warnings': ['Unable to download f4m manifest'],
+ }, {
+ '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': 'd8DEBj7QRfetLsRgFnGEyg',
+ 'ext': 'mp4',
+ 'title': r're:^Williams Stream \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
+ 'description': 'original programming',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
},
}]
- @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
-
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.
- bootstrappedDataJS = self._search_regex(r'var bootstrappedData = ({.*});', webpage, episode_path)
-
- try:
- bootstrappedData = json.loads(bootstrappedDataJS)
- except ValueError as ve:
- errmsg = '%s: Failed to parse JSON ' % episode_path
- raise ExtractorError(errmsg, cause=ve)
-
- # 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 = bootstrappedData['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 = url_or_none(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 = bootstrappedData['show']['collections']
- collection, video_info = self.find_collection_containing_video(collections, episode_path)
-
- show = bootstrappedData['show']
- show_title = show['title']
- segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
-
- episode_id = video_info['id']
- episode_title = video_info['title']
- episode_description = video_info['description']
- episode_duration = video_info.get('duration')
-
- entries = []
- for part_num, segment_id in enumerate(segment_ids):
- segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=mobile' % segment_id
-
- segment_title = '%s - %s' % (show_title, episode_title)
- if len(segment_ids) > 1:
- segment_title += ' Part %d' % (part_num + 1)
-
- idoc = self._download_xml(
- segment_url, segment_title,
- 'Downloading segment information', 'Unable to download segment information')
-
- segment_duration = float_or_none(
- xpath_text(idoc, './/trt', 'segment duration').strip())
-
- formats = []
- file_els = idoc.findall('.//files/file')
-
- for file_el in file_els:
- bitrate = file_el.attrib.get('bitrate')
- ftype = file_el.attrib.get('type')
-
- formats.append({
- 'format_id': '%s_%s' % (bitrate, ftype),
- 'url': file_el.text.strip(),
- # The bitrate may not be a number (for example: 'iphone')
- 'tbr': int(bitrate) if bitrate.isdigit() else None,
- 'quality': 1 if ftype == 'hd' else -1
- })
-
- self._sort_formats(formats)
+ 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?platform=desktop&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.append({
- 'id': segment_id,
- 'title': segment_title,
- 'formats': formats,
- 'duration': segment_duration,
- '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')),
})
- 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
- }
+ 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
Rapsys Git / youtubedl / blobdiff