2 from __future__ import unicode_literals
8 from .common import InfoExtractor
19 class MGTVIE(InfoExtractor):
20 _VALID_URL = r'https?://(?:www\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P<id>\d+)\.html'
22 _GEO_COUNTRIES = ['CN']
25 'url': 'http://www.mgtv.com/v/1/290525/f/3116640.html',
30 'description': '我是歌手第四季双年巅峰会',
32 'thumbnail': r're:^https?://.*\.jpg$',
35 'url': 'http://www.mgtv.com/b/301817/3826653.html',
36 'only_matching': True,
39 def _real_extract(self, url):
40 video_id = self._match_id(url)
42 api_data = self._download_json(
43 'https://pcweb.api.mgtv.com/player/video', video_id, query={
44 'tk2': base64.urlsafe_b64encode(b'did=%s|pno=1030|ver=0.3.0301|clit=%d' % (compat_str(uuid.uuid4()).encode(), time.time()))[::-1],
46 }, headers=self.geo_verification_headers())['data']
47 except ExtractorError as e:
48 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
49 error = self._parse_json(e.cause.read().decode(), None)
50 if error.get('code') == 40005:
51 self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
52 raise ExtractorError(error['msg'], expected=True)
54 info = api_data['info']
55 title = info['title'].strip()
56 stream_data = self._download_json(
57 'https://pcweb.api.mgtv.com/player/getSource', video_id, query={
58 'pm2': api_data['atc']['pm2'],
60 }, headers=self.geo_verification_headers())['data']
61 stream_domain = stream_data['stream_domain'][0]
64 for idx, stream in enumerate(stream_data['stream']):
65 stream_path = stream.get('url')
68 format_data = self._download_json(
69 stream_domain + stream_path, video_id,
70 note='Download video info for format #%d' % idx)
71 format_url = format_data.get('info')
74 tbr = int_or_none(stream.get('filebitrate') or self._search_regex(
75 r'_(\d+)_mp4/', format_url, 'tbr', default=None))
77 'format_id': compat_str(tbr or idx),
81 'protocol': 'm3u8_native',
85 'format_note': stream.get('name'),
87 self._sort_formats(formats)
93 'description': info.get('desc'),
94 'duration': int_or_none(info.get('duration')),
95 'thumbnail': info.get('thumb'),