2 from __future__ import unicode_literals
6 from .common import InfoExtractor
15 class AdultSwimIE(InfoExtractor):
16 _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?'
19 'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
22 'md5': '247572debc75c7652f253c8daa51a14d',
24 'id': 'rQxZvXQ4ROaSOqq-or2Mow-0',
26 'title': 'Rick and Morty - Pilot Part 1',
27 'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
31 'md5': '77b0e037a4b20ec6b98671c4c379f48d',
33 'id': 'rQxZvXQ4ROaSOqq-or2Mow-3',
35 'title': 'Rick and Morty - Pilot Part 4',
36 'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
41 'id': 'rQxZvXQ4ROaSOqq-or2Mow',
42 'title': 'Rick and Morty - Pilot',
43 'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
45 'skip': 'This video is only available for registered users',
47 'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
50 'md5': '2eb5c06d0f9a1539da3718d897f13ec5',
52 'id': '-t8CamQlQ2aYZ49ItZCFog-0',
54 'title': 'American Dad - Putting Francine Out of Business',
55 'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
60 'id': '-t8CamQlQ2aYZ49ItZCFog',
61 'title': 'American Dad - Putting Francine Out of Business',
62 'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
65 'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
68 'md5': '3e346a2ab0087d687a05e1e7f3b3e529',
70 'id': 'sY3cMUR_TbuE4YmdjzbIcQ-0',
72 'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
73 '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',
78 'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
79 'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
80 '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',
84 'skip_download': True,
87 # heroMetadata.trailer
88 'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
89 'md5': '33e9a5d8f646523ce0868ecfb0eed77d',
91 'id': 'I0LQFQkaSUaFp8PnAWHhoQ',
93 'title': 'Decker - Inside Decker: A New Hero',
94 'description': 'md5:c916df071d425d62d70c86d4399d3ee0',
99 'skip_download': True,
104 def find_video_info(collection, slug):
105 for video in collection.get('videos'):
106 if video.get('slug') == slug:
110 def find_collection_by_linkURL(collections, linkURL):
111 for collection in collections:
112 if collection.get('linkURL') == linkURL:
116 def find_collection_containing_video(collections, slug):
117 for collection in collections:
118 for video in collection.get('videos'):
119 if video.get('slug') == slug:
120 return collection, video
123 def _real_extract(self, url):
124 mobj = re.match(self._VALID_URL, url)
125 show_path = mobj.group('show_path')
126 episode_path = mobj.group('episode_path')
127 is_playlist = True if mobj.group('is_playlist') else False
129 webpage = self._download_webpage(url, episode_path)
131 # Extract the value of `bootstrappedData` from the Javascript in the page.
132 bootstrapped_data = self._parse_json(self._search_regex(
133 r'var bootstrappedData = ({.*});', webpage, 'bootstraped data'), episode_path)
135 # Downloading videos from a /videos/playlist/ URL needs to be handled differently.
136 # NOTE: We are only downloading one video (the current one) not the playlist
138 collections = bootstrapped_data['playlists']['collections']
139 collection = self.find_collection_by_linkURL(collections, show_path)
140 video_info = self.find_video_info(collection, episode_path)
142 show_title = video_info['showTitle']
143 segment_ids = [video_info['videoPlaybackID']]
145 collections = bootstrapped_data['show']['collections']
146 collection, video_info = self.find_collection_containing_video(collections, episode_path)
147 # Video wasn't found in the collections, let's try `slugged_video`.
148 if video_info is None:
149 if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
150 video_info = bootstrapped_data['slugged_video']
152 video_info = bootstrapped_data.get('heroMetadata', {}).get('trailer').get('video')
154 raise ExtractorError('Unable to find video info')
156 show = bootstrapped_data['show']
157 show_title = show['title']
158 stream = video_info.get('stream')
159 if stream and stream.get('videoPlaybackID'):
160 segment_ids = [stream['videoPlaybackID']]
161 elif video_info.get('clips'):
162 segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
163 elif video_info.get('videoPlaybackID'):
164 segment_ids = [video_info['videoPlaybackID']]
166 raise ExtractorError(
167 'This video is only available via cable service provider subscription that'
168 ' is not currently supported. You may want to use --cookies.'
169 if video_info.get('auth') is True else 'Unable to find stream or clips',
172 episode_id = video_info['id']
173 episode_title = video_info['title']
174 episode_description = video_info['description']
175 episode_duration = video_info.get('duration')
178 for part_num, segment_id in enumerate(segment_ids):
179 segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id
181 segment_title = '%s - %s' % (show_title, episode_title)
182 if len(segment_ids) > 1:
183 segment_title += ' Part %d' % (part_num + 1)
185 idoc = self._download_xml(
186 segment_url, segment_title,
187 'Downloading segment information', 'Unable to download segment information')
189 segment_duration = float_or_none(
190 xpath_text(idoc, './/trt', 'segment duration').strip())
193 file_els = idoc.findall('.//files/file') or idoc.findall('./files/file')
197 for file_el in file_els:
198 media_url = file_el.text
199 if not media_url or determine_ext(media_url) == 'f4m':
201 if file_el.text not in unique_urls:
202 unique_urls.append(file_el.text)
203 unique_file_els.append(file_el)
205 for file_el in unique_file_els:
206 bitrate = file_el.attrib.get('bitrate')
207 ftype = file_el.attrib.get('type')
208 media_url = file_el.text
209 if determine_ext(media_url) == 'm3u8':
210 formats.extend(self._extract_m3u8_formats(
211 media_url, segment_title, 'mp4', preference=0,
212 m3u8_id='hls', fatal=False))
215 'format_id': '%s_%s' % (bitrate, ftype),
216 'url': file_el.text.strip(),
217 # The bitrate may not be a number (for example: 'iphone')
218 'tbr': int(bitrate) if bitrate.isdigit() else None,
221 self._sort_formats(formats)
225 'title': segment_title,
227 'duration': segment_duration,
228 'description': episode_description
234 'display_id': episode_path,
236 'title': '%s - %s' % (show_title, episode_title),
237 'description': episode_description,
238 'duration': episode_duration