]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/teamcoco.py
1 # -*- coding: utf-8 -*-
2 from __future__
import unicode_literals
9 from .common
import InfoExtractor
15 from ..compat
import compat_ord
18 class TeamcocoIE(InfoExtractor
):
19 _VALID_URL
= r
'http://teamcoco\.com/video/(?P<video_id>[0-9]+)?/?(?P<display_id>.*)'
22 'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant',
23 'md5': '3f7746aa0dc86de18df7539903d399ea',
27 'title': 'Conan Becomes A Mary Kay Beauty Consultant',
28 'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.',
33 'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
34 'md5': 'cde9ba0fa3506f5f017ce11ead928f9a',
38 'description': 'Louis C.K. got starstruck by George W. Bush, so what? Part one.',
39 'title': 'Louis C.K. Interview Pt. 1 11/3/11',
44 'url': 'http://teamcoco.com/video/timothy-olyphant-drinking-whiskey',
48 'title': 'Timothy Olyphant Raises A Toast To “Justified”',
49 'description': 'md5:15501f23f020e793aeca761205e42c24',
52 'skip_download': True, # m3u8 downloads
57 r
'"eVar42"\s*:\s*(\d+)',
58 r
'Ginger\.TeamCoco\.openInApp\("video",\s*"([^"]+)"',
59 r
'"id_not"\s*:\s*(\d+)'
62 def _real_extract(self
, url
):
63 mobj
= re
.match(self
._VALID
_URL
, url
)
65 display_id
= mobj
.group('display_id')
66 webpage
, urlh
= self
._download
_webpage
_handle
(url
, display_id
)
67 if 'src=expired' in urlh
.geturl():
68 raise ExtractorError('This video is expired.', expected
=True)
70 video_id
= mobj
.group('video_id')
72 video_id
= self
._html
_search
_regex
(
73 self
._VIDEO
_ID
_REGEXES
, webpage
, 'video id')
77 preload_codes
= self
._html
_search
_regex
(
78 r
'(function.+)setTimeout\(function\(\)\{playlist',
79 webpage
, 'preload codes')
80 base64_fragments
= re
.findall(r
'"([a-zA-z0-9+/=]+)"', preload_codes
)
81 base64_fragments
.remove('init')
83 def _check_sequence(cur_fragments
):
86 for i
in range(len(cur_fragments
)):
87 cur_sequence
= (''.join(cur_fragments
[i
:] + cur_fragments
[:i
])).encode('ascii')
89 raw_data
= base64
.b64decode(cur_sequence
)
90 if compat_ord(raw_data
[0]) == compat_ord('{'):
91 return json
.loads(raw_data
.decode('utf-8'))
92 except (TypeError, binascii
.Error
, UnicodeDecodeError, ValueError):
96 for i
in range(len(base64_fragments
) + 1):
97 for j
in range(i
, len(base64_fragments
) + 1):
98 data
= _check_sequence(base64_fragments
[:i
] + base64_fragments
[j
:])
102 self
.to_screen('Try to compute possible data sequence. This may take some time.')
106 raise ExtractorError(
107 'Preload information could not be extracted', expected
=True)
110 get_quality
= qualities(['500k', '480p', '1000k', '720p', '1080p'])
111 for filed
in data
['files']:
112 if determine_ext(filed
['url']) == 'm3u8':
113 formats
.extend(self
._extract
_m
3u8_formats
(
114 filed
['url'], video_id
, ext
='mp4'))
116 m_format
= re
.search(r
'(\d+(k|p))\.mp4', filed
['url'])
117 if m_format
is not None:
118 format_id
= m_format
.group(1)
120 format_id
= filed
['bitrate']
122 int(filed
['bitrate'])
123 if filed
['bitrate'].isdigit()
130 'format_id': format_id
,
131 'quality': get_quality(format_id
),
134 self
._sort
_formats
(formats
)
138 'display_id': display_id
,
140 'title': data
['title'],
141 'thumbnail': data
.get('thumb', {}).get('href'),
142 'description': data
.get('teaser'),
143 'duration': data
.get('duration'),
144 'age_limit': self
._family
_friendly
_search
(webpage
),