[meipai] Add extractor
[youtube-dl] / youtube_dl / extractor / meipai.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from ..utils import parse_iso8601
5 from .common import InfoExtractor
6
7
8 class MeipaiIE(InfoExtractor):
9     IE_DESC = '美拍'
10     _VALID_URL = r'https?://(?:www\.)?meipai.com/media/(?P<id>[0-9]+)'
11     _TESTS = [
12         {
13             'url': 'http://www.meipai.com/media/531697625',
14             'md5': 'e3e9600f9e55a302daecc90825854b4f',
15             'info_dict': {
16                 'id': '531697625',
17                 'ext': 'mp4',
18                 'title': '#葉子##阿桑##余姿昀##超級女聲#',
19                 'description': '#葉子##阿桑##余姿昀##超級女聲#',
20                 'thumbnail': 're:^https?://.*\.jpg$',
21                 'creator': '她她-TATA',
22                 'tags': ['葉子', '阿桑', '余姿昀', '超級女聲'],
23                 'release_date': 1465492420,
24             }
25         },
26         {
27             'url': 'http://www.meipai.com/media/576409659',
28             'md5': '2e807c16ebe67b8b6b3c8dcacbc32f48',
29             'info_dict': {
30                 'id': '576409659',
31                 'ext': 'mp4',
32                 'title': '#失語者##蔡健雅##吉他彈唱#',
33                 'description': '#失語者##蔡健雅##吉他彈唱#',
34                 'thumbnail': 're:^https?://.*\.jpg$',
35                 'creator': '她她-TATA',
36                 'tags': ['失語者', '蔡健雅', '吉他彈唱'],
37                 'release_date': 1472534847,
38             }
39         },
40         # record of live streaming
41         {
42             'url': 'http://www.meipai.com/media/585526361',
43             'md5': 'ff7d6afdbc6143342408223d4f5fb99a',
44             'info_dict': {
45                 'id': '585526361',
46                 'ext': 'mp4',
47                 'title': '姿昀和善願 練歌練琴啦😁😁😁',
48                 'description': '姿昀和善願 練歌練琴啦😁😁😁',
49                 'thumbnail': 're:^https?://.*\.jpg$',
50                 'creator': '她她-TATA',
51                 'release_date': 1474311799,
52             }
53         },
54     ]
55
56     def _real_extract(self, url):
57         video_id = self._match_id(url)
58         webpage = self._download_webpage(url, video_id)
59
60         title = self._og_search_title(webpage, default=None)
61         if title is None:
62             # fall back to text used in title
63             title = self._html_search_regex(
64                 r'<title[^>]*>(.+)</title>', webpage, 'title')
65
66         release_date = self._og_search_property(
67             'video:release_date', webpage, 'release date', fatal=False)
68         release_date = parse_iso8601(release_date)
69
70         tags = self._og_search_property(
71             'video:tag', webpage, 'tags', default='').split(',')
72
73         info = {
74             'id': video_id,
75             'title': title,
76             'thumbnail': self._og_search_thumbnail(webpage),
77             'description': self._og_search_description(webpage),
78             'release_date': release_date,
79             'creator': self._og_search_property(
80                 'video:director', webpage, 'creator', fatal=False),
81             'tags': tags,
82         }
83
84         keywords = self._html_search_meta(
85             'keywords', webpage, 'keywords', default=[])
86
87         if '直播回放' in keywords:
88             # recorded playback of live streaming
89             m3u8_url = self._html_search_regex(
90                 r'file:\s*encodeURIComponent\(["\'](.+)["\']\)',
91                 webpage,
92                 'm3u8_url')
93             info['formats'] = self._extract_m3u8_formats(
94                 m3u8_url, video_id, 'mp4', 'm3u8_native')
95         else:
96             # regular uploaded video
97             info['url'] = self._og_search_video_url(webpage)
98
99         return info