]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/mgtv.py
2 from __future__
import unicode_literals
8 from .common
import InfoExtractor
21 class MGTVIE(InfoExtractor
):
22 _VALID_URL
= r
'https?://(?:w(?:ww)?\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P<id>\d+)\.html'
27 'url': 'http://www.mgtv.com/v/1/290525/f/3116640.html',
32 'description': '我是歌手第四季双年巅峰会',
34 'thumbnail': r
're:^https?://.*\.jpg$',
37 'url': 'https://w.mgtv.com/b/427837/15588271.html',
41 'title': '春日迟迟再出发 沉浸版',
42 'description': 'md5:a7a05a05b1aa87bd50cae619b19bbca6',
43 'thumbnail': r
're:^https?://.+\.jpg',
47 'url': 'https://w.mgtv.com/b/333652/7329822.html',
52 'description': 'md5:cd81be6499bafe32e4d143abd822bf9c',
53 'thumbnail': r
're:^https?://.+\.jpg',
57 'url': 'https://w.mgtv.com/b/427837/15591647.html',
58 'only_matching': True,
60 'url': 'https://w.mgtv.com/b/388252/15634192.html?fpa=33318&fpos=4&lastp=ch_home',
61 'only_matching': True,
63 'url': 'http://www.mgtv.com/b/301817/3826653.html',
64 'only_matching': True,
66 'url': 'https://w.mgtv.com/b/301817/3826653.html',
67 'only_matching': True,
70 def _real_extract(self
, url
):
71 video_id
= self
._match
_id
(url
)
72 tk2
= base64
.urlsafe_b64encode(
73 f
'did={compat_str(uuid.uuid4()).encode()}|pno=1030|ver=0.3.0301|clit={int(time.time())}'.encode())[::-1]
75 api_data
= self
._download
_json
(
76 'https://pcweb.api.mgtv.com/player/video', video_id
, query
={
80 }, headers
=self
.geo_verification_headers())['data']
81 except ExtractorError
as e
:
82 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 401:
83 error
= self
._parse
_json
(e
.cause
.read().decode(), None)
84 if error
.get('code') == 40005:
85 self
.raise_geo_restricted(countries
=self
._GEO
_COUNTRIES
)
86 raise ExtractorError(error
['msg'], expected
=True)
88 info
= api_data
['info']
89 title
= info
['title'].strip()
90 stream_data
= self
._download
_json
(
91 'https://pcweb.api.mgtv.com/player/getSource', video_id
, query
={
92 'pm2': api_data
['atc']['pm2'],
96 }, headers
=self
.geo_verification_headers())['data']
97 stream_domain
= stream_data
['stream_domain'][0]
100 for idx
, stream
in enumerate(stream_data
['stream']):
101 stream_path
= stream
.get('url')
104 format_data
= self
._download
_json
(
105 stream_domain
+ stream_path
, video_id
,
106 note
=f
'Download video info for format #{idx}')
107 format_url
= format_data
.get('info')
110 tbr
= int_or_none(stream
.get('filebitrate') or self
._search
_regex
(
111 r
'_(\d+)_mp4/', format_url
, 'tbr', default
=None))
113 'format_id': compat_str(tbr
or idx
),
114 'url': url_or_none(format_url
),
117 'protocol': 'm3u8_native',
121 'format_note': stream
.get('name'),
123 self
._sort
_formats
(formats
)
129 'description': info
.get('desc'),
130 'duration': int_or_none(info
.get('duration')),
131 'thumbnail': info
.get('thumb'),
132 'subtitles': self
.extract_subtitles(video_id
, stream_domain
),
135 def _get_subtitles(self
, video_id
, domain
):
136 info
= self
._download
_json
(f
'https://pcweb.api.mgtv.com/video/title?videoId={video_id}',
137 video_id
, fatal
=False) or {}
139 for sub
in try_get(info
, lambda x
: x
['data']['title']) or []:
140 url_sub
= sub
.get('url')
143 locale
= sub
.get('captionCountrySimpleName')
144 sub
= self
._download
_json
(f
'{domain}{url_sub}', video_id
, fatal
=False,
145 note
=f
'Download subtitle for locale {sub.get("name")} ({locale})') or {}
146 sub_url
= url_or_none(sub
.get('info'))
149 subtitles
.setdefault(locale
or 'en', []).append({