]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/viki.py
debian/copyright: Fix lintian's dep5-copyright-license-name-not-unique.
[youtubedl] / youtube_dl / extractor / viki.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from ..compat import (
6 compat_urlparse,
7 compat_urllib_request,
8 )
9 from ..utils import (
10 ExtractorError,
11 unescapeHTML,
12 unified_strdate,
13 US_RATINGS,
14 determine_ext,
15 mimetype2ext,
16 )
17 from .common import InfoExtractor
18
19
20 class VikiIE(InfoExtractor):
21 IE_NAME = 'viki'
22
23 # iPad2
24 _USER_AGENT = 'Mozilla/5.0(iPad; U; CPU OS 4_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8F191 Safari/6533.18.5'
25
26 _VALID_URL = r'^https?://(?:www\.)?viki\.com/videos/(?P<id>[0-9]+v)'
27 _TESTS = [{
28 'url': 'http://www.viki.com/videos/1023585v-heirs-episode-14',
29 'info_dict': {
30 'id': '1023585v',
31 'ext': 'mp4',
32 'title': 'Heirs Episode 14',
33 'uploader': 'SBS',
34 'description': 'md5:c4b17b9626dd4b143dcc4d855ba3474e',
35 'upload_date': '20131121',
36 'age_limit': 13,
37 },
38 'skip': 'Blocked in the US',
39 }, {
40 'url': 'http://www.viki.com/videos/1067139v-the-avengers-age-of-ultron-press-conference',
41 'md5': 'ca6493e6f0a6ec07da9aa8d6304b4b2c',
42 'info_dict': {
43 'id': '1067139v',
44 'ext': 'mp4',
45 'description': 'md5:d70b2f9428f5488321bfe1db10d612ea',
46 'upload_date': '20150430',
47 'title': '\'The Avengers: Age of Ultron\' Press Conference',
48 }
49 }, {
50 'url': 'http://www.viki.com/videos/1048879v-ankhon-dekhi',
51 'info_dict': {
52 'id': '1048879v',
53 'ext': 'mp4',
54 'upload_date': '20140820',
55 'description': 'md5:54ff56d51bdfc7a30441ec967394e91c',
56 'title': 'Ankhon Dekhi',
57 },
58 'params': {
59 # requires ffmpeg
60 'skip_download': True,
61 }
62 }]
63
64 def _real_extract(self, url):
65 video_id = self._match_id(url)
66
67 webpage = self._download_webpage(url, video_id)
68 title = self._og_search_title(webpage)
69 description = self._og_search_description(webpage)
70 thumbnail = self._og_search_thumbnail(webpage)
71
72 uploader_m = re.search(
73 r'<strong>Broadcast Network: </strong>\s*([^<]*)<', webpage)
74 if uploader_m is None:
75 uploader = None
76 else:
77 uploader = uploader_m.group(1).strip()
78
79 rating_str = self._html_search_regex(
80 r'<strong>Rating: </strong>\s*([^<]*)<', webpage,
81 'rating information', default='').strip()
82 age_limit = US_RATINGS.get(rating_str)
83
84 req = compat_urllib_request.Request(
85 'http://www.viki.com/player5_fragment/%s?action=show&controller=videos' % video_id)
86 req.add_header('User-Agent', self._USER_AGENT)
87 info_webpage = self._download_webpage(
88 req, video_id, note='Downloading info page')
89 err_msg = self._html_search_regex(r'<div[^>]+class="video-error[^>]+>(.+)</div>', info_webpage, 'error message', default=None)
90 if err_msg:
91 if 'not available in your region' in err_msg:
92 raise ExtractorError(
93 'Video %s is blocked from your location.' % video_id,
94 expected=True)
95 else:
96 raise ExtractorError('Viki said: ' + err_msg)
97 mobj = re.search(
98 r'<source[^>]+type="(?P<mime_type>[^"]+)"[^>]+src="(?P<url>[^"]+)"', info_webpage)
99 if not mobj:
100 raise ExtractorError('Unable to find video URL')
101 video_url = unescapeHTML(mobj.group('url'))
102 video_ext = mimetype2ext(mobj.group('mime_type'))
103
104 if determine_ext(video_url) == 'm3u8':
105 formats = self._extract_m3u8_formats(
106 video_url, video_id, ext=video_ext)
107 else:
108 formats = [{
109 'url': video_url,
110 'ext': video_ext,
111 }]
112
113 upload_date_str = self._html_search_regex(
114 r'"created_at":"([^"]+)"', info_webpage, 'upload date')
115 upload_date = (
116 unified_strdate(upload_date_str)
117 if upload_date_str is not None
118 else None
119 )
120
121 # subtitles
122 video_subtitles = self.extract_subtitles(video_id, info_webpage)
123
124 return {
125 'id': video_id,
126 'title': title,
127 'formats': formats,
128 'description': description,
129 'thumbnail': thumbnail,
130 'age_limit': age_limit,
131 'uploader': uploader,
132 'subtitles': video_subtitles,
133 'upload_date': upload_date,
134 }
135
136 def _get_subtitles(self, video_id, info_webpage):
137 res = {}
138 for sturl_html in re.findall(r'<track src="([^"]+)"', info_webpage):
139 sturl = unescapeHTML(sturl_html)
140 m = re.search(r'/(?P<lang>[a-z]+)\.vtt', sturl)
141 if not m:
142 continue
143 res[m.group('lang')] = [{
144 'url': compat_urlparse.urljoin('http://www.viki.com', sturl),
145 'ext': 'vtt',
146 }]
147 return res