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. "
46 'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
49 'md5': '2eb5c06d0f9a1539da3718d897f13ec5',
51 'id': '-t8CamQlQ2aYZ49ItZCFog-0',
53 'title': 'American Dad - Putting Francine Out of Business',
54 'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
59 'id': '-t8CamQlQ2aYZ49ItZCFog',
60 'title': 'American Dad - Putting Francine Out of Business',
61 'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
64 'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
67 'md5': '3e346a2ab0087d687a05e1e7f3b3e529',
69 'id': 'sY3cMUR_TbuE4YmdjzbIcQ-0',
71 'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
72 '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',
77 'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
78 'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
79 '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 def find_video_info(collection, slug):
85 for video in collection.get('videos'):
86 if video.get('slug') == slug:
90 def find_collection_by_linkURL(collections, linkURL):
91 for collection in collections:
92 if collection.get('linkURL') == linkURL:
96 def find_collection_containing_video(collections, slug):
97 for collection in collections:
98 for video in collection.get('videos'):
99 if video.get('slug') == slug:
100 return collection, video
103 def _real_extract(self, url):
104 mobj = re.match(self._VALID_URL, url)
105 show_path = mobj.group('show_path')
106 episode_path = mobj.group('episode_path')
107 is_playlist = True if mobj.group('is_playlist') else False
109 webpage = self._download_webpage(url, episode_path)
111 # Extract the value of `bootstrappedData` from the Javascript in the page.
112 bootstrapped_data = self._parse_json(self._search_regex(
113 r'var bootstrappedData = ({.*});', webpage, 'bootstraped data'), episode_path)
115 # Downloading videos from a /videos/playlist/ URL needs to be handled differently.
116 # NOTE: We are only downloading one video (the current one) not the playlist
118 collections = bootstrapped_data['playlists']['collections']
119 collection = self.find_collection_by_linkURL(collections, show_path)
120 video_info = self.find_video_info(collection, episode_path)
122 show_title = video_info['showTitle']
123 segment_ids = [video_info['videoPlaybackID']]
125 collections = bootstrapped_data['show']['collections']
126 collection, video_info = self.find_collection_containing_video(collections, episode_path)
127 # Video wasn't found in the collections, let's try `slugged_video`.
128 if video_info is None:
129 if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
130 video_info = bootstrapped_data['slugged_video']
132 raise ExtractorError('Unable to find video info')
134 show = bootstrapped_data['show']
135 show_title = show['title']
136 stream = video_info.get('stream')
137 clips = [stream] if stream else video_info['clips']
138 segment_ids = [clip['videoPlaybackID'] for clip in clips]
140 episode_id = video_info['id']
141 episode_title = video_info['title']
142 episode_description = video_info['description']
143 episode_duration = video_info.get('duration')
146 for part_num, segment_id in enumerate(segment_ids):
147 segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id
149 segment_title = '%s - %s' % (show_title, episode_title)
150 if len(segment_ids) > 1:
151 segment_title += ' Part %d' % (part_num + 1)
153 idoc = self._download_xml(
154 segment_url, segment_title,
155 'Downloading segment information', 'Unable to download segment information')
157 segment_duration = float_or_none(
158 xpath_text(idoc, './/trt', 'segment duration').strip())
161 file_els = idoc.findall('.//files/file') or idoc.findall('./files/file')
165 for file_el in file_els:
166 media_url = file_el.text
167 if not media_url or determine_ext(media_url) == 'f4m':
169 if file_el.text not in unique_urls:
170 unique_urls.append(file_el.text)
171 unique_file_els.append(file_el)
173 for file_el in unique_file_els:
174 bitrate = file_el.attrib.get('bitrate')
175 ftype = file_el.attrib.get('type')
176 media_url = file_el.text
177 if determine_ext(media_url) == 'm3u8':
178 formats.extend(self._extract_m3u8_formats(
179 media_url, segment_title, 'mp4', 'm3u8_native', preference=0, m3u8_id='hls'))
182 'format_id': '%s_%s' % (bitrate, ftype),
183 'url': file_el.text.strip(),
184 # The bitrate may not be a number (for example: 'iphone')
185 'tbr': int(bitrate) if bitrate.isdigit() else None,
188 self._sort_formats(formats)
192 'title': segment_title,
194 'duration': segment_duration,
195 'description': episode_description
201 'display_id': episode_path,
203 'title': '%s - %s' % (show_title, episode_title),
204 'description': episode_description,
205 'duration': episode_duration