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',
85 def find_video_info(collection
, slug
):
86 for video
in collection
.get('videos'):
87 if video
.get('slug') == slug
:
91 def find_collection_by_linkURL(collections
, linkURL
):
92 for collection
in collections
:
93 if collection
.get('linkURL') == linkURL
:
97 def find_collection_containing_video(collections
, slug
):
98 for collection
in collections
:
99 for video
in collection
.get('videos'):
100 if video
.get('slug') == slug
:
101 return collection
, video
104 def _real_extract(self
, url
):
105 mobj
= re
.match(self
._VALID
_URL
, url
)
106 show_path
= mobj
.group('show_path')
107 episode_path
= mobj
.group('episode_path')
108 is_playlist
= True if mobj
.group('is_playlist') else False
110 webpage
= self
._download
_webpage
(url
, episode_path
)
112 # Extract the value of `bootstrappedData` from the Javascript in the page.
113 bootstrapped_data
= self
._parse
_json
(self
._search
_regex
(
114 r
'var bootstrappedData = ({.*});', webpage
, 'bootstraped data'), episode_path
)
116 # Downloading videos from a /videos/playlist/ URL needs to be handled differently.
117 # NOTE: We are only downloading one video (the current one) not the playlist
119 collections
= bootstrapped_data
['playlists']['collections']
120 collection
= self
.find_collection_by_linkURL(collections
, show_path
)
121 video_info
= self
.find_video_info(collection
, episode_path
)
123 show_title
= video_info
['showTitle']
124 segment_ids
= [video_info
['videoPlaybackID']]
126 collections
= bootstrapped_data
['show']['collections']
127 collection
, video_info
= self
.find_collection_containing_video(collections
, episode_path
)
128 # Video wasn't found in the collections, let's try `slugged_video`.
129 if video_info
is None:
130 if bootstrapped_data
.get('slugged_video', {}).get('slug') == episode_path
:
131 video_info
= bootstrapped_data
['slugged_video']
133 raise ExtractorError('Unable to find video info')
135 show
= bootstrapped_data
['show']
136 show_title
= show
['title']
137 stream
= video_info
.get('stream')
138 clips
= [stream
] if stream
else video_info
.get('clips')
140 raise ExtractorError(
141 'This video is only available via cable service provider subscription that'
142 ' is not currently supported. You may want to use --cookies.'
143 if video_info
.get('auth') is True else 'Unable to find stream or clips',
145 segment_ids
= [clip
['videoPlaybackID'] for clip
in clips
]
147 episode_id
= video_info
['id']
148 episode_title
= video_info
['title']
149 episode_description
= video_info
['description']
150 episode_duration
= video_info
.get('duration')
153 for part_num
, segment_id
in enumerate(segment_ids
):
154 segment_url
= 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id
156 segment_title
= '%s - %s' % (show_title
, episode_title
)
157 if len(segment_ids
) > 1:
158 segment_title
+= ' Part %d' % (part_num
+ 1)
160 idoc
= self
._download
_xml
(
161 segment_url
, segment_title
,
162 'Downloading segment information', 'Unable to download segment information')
164 segment_duration
= float_or_none(
165 xpath_text(idoc
, './/trt', 'segment duration').strip())
168 file_els
= idoc
.findall('.//files/file') or idoc
.findall('./files/file')
172 for file_el
in file_els
:
173 media_url
= file_el
.text
174 if not media_url
or determine_ext(media_url
) == 'f4m':
176 if file_el
.text
not in unique_urls
:
177 unique_urls
.append(file_el
.text
)
178 unique_file_els
.append(file_el
)
180 for file_el
in unique_file_els
:
181 bitrate
= file_el
.attrib
.get('bitrate')
182 ftype
= file_el
.attrib
.get('type')
183 media_url
= file_el
.text
184 if determine_ext(media_url
) == 'm3u8':
185 formats
.extend(self
._extract
_m
3u8_formats
(
186 media_url
, segment_title
, 'mp4', preference
=0, m3u8_id
='hls'))
189 'format_id': '%s_%s' % (bitrate
, ftype
),
190 'url': file_el
.text
.strip(),
191 # The bitrate may not be a number (for example: 'iphone')
192 'tbr': int(bitrate
) if bitrate
.isdigit() else None,
195 self
._sort
_formats
(formats
)
199 'title': segment_title
,
201 'duration': segment_duration
,
202 'description': episode_description
208 'display_id': episode_path
,
210 'title': '%s - %s' % (show_title
, episode_title
),
211 'description': episode_description
,
212 'duration': episode_duration