]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/meipai.py
2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
12 class MeipaiIE(InfoExtractor
):
14 _VALID_URL
= r
'https?://(?:www\.)?meipai\.com/media/(?P<id>[0-9]+)'
16 # regular uploaded video
17 'url': 'http://www.meipai.com/media/531697625',
18 'md5': 'e3e9600f9e55a302daecc90825854b4f',
22 'title': '#葉子##阿桑##余姿昀##超級女聲#',
23 'description': '#葉子##阿桑##余姿昀##超級女聲#',
24 'thumbnail': r
're:^https?://.*\.jpg$',
26 'timestamp': 1465492420,
27 'upload_date': '20160609',
30 'tags': ['葉子', '阿桑', '余姿昀', '超級女聲'],
33 # record of live streaming
34 'url': 'http://www.meipai.com/media/585526361',
35 'md5': 'ff7d6afdbc6143342408223d4f5fb99a',
39 'title': '姿昀和善願 練歌練琴啦😁😁😁',
40 'description': '姿昀和善願 練歌練琴啦😁😁😁',
41 'thumbnail': r
're:^https?://.*\.jpg$',
43 'timestamp': 1474311799,
44 'upload_date': '20160919',
50 def _real_extract(self
, url
):
51 video_id
= self
._match
_id
(url
)
52 webpage
= self
._download
_webpage
(url
, video_id
)
54 title
= self
._og
_search
_title
(
55 webpage
, default
=None) or self
._html
_search
_regex
(
56 r
'<title[^>]*>([^<]+)</title>', webpage
, 'title')
60 # recorded playback of live streaming
61 m3u8_url
= self
._html
_search
_regex
(
62 r
'file:\s*encodeURIComponent\((["\'])(?P
<url
>(?
:(?
!\
1).)+)\
1\
)',
63 webpage, 'm3u8 url
', group='url
', default=None)
65 formats.extend(self._extract_m3u8_formats(
66 m3u8_url, video_id, 'mp4
', entry_protocol='m3u8_native
',
67 m3u8_id='hls
', fatal=False))
70 # regular uploaded video
71 video_url = self._search_regex(
72 r'data
-video
=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'video url',
73 group='url', default=None)
80 timestamp = unified_timestamp(self._og_search_property(
81 'video:release_date', webpage, 'release date', fatal=False))
83 tags = self._og_search_property(
84 'video:tag', webpage, 'tags', default='').split(',')
86 view_count = int_or_none(self._html_search_meta(
87 'interactionCount', webpage, 'view count'))
88 duration = parse_duration(self._html_search_meta(
89 'duration', webpage, 'duration'))
90 creator = self._og_search_property(
91 'video:director', webpage, 'creator', fatal=False)
96 'description': self._og_search_description(webpage),
97 'thumbnail': self._og_search_thumbnail(webpage),
99 'timestamp': timestamp,
100 'view_count': view_count,