1 import re
2
3 from ..utils import (
4 ExtractorError,
5 unified_strdate,
6 )
7 from .subtitles import SubtitlesInfoExtractor
8
9
10 class VikiIE(SubtitlesInfoExtractor):
11 IE_NAME = u'viki'
12
13 _VALID_URL = r'^https?://(?:www\.)?viki\.com/videos/(?P<id>[0-9]+v)'
14 _TEST = {
15 u'url': u'http://www.viki.com/videos/1023585v-heirs-episode-14',
16 u'file': u'1023585v.mp4',
17 u'md5': u'a21454021c2646f5433514177e2caa5f',
18 u'info_dict': {
19 u'title': u'Heirs Episode 14',
20 u'uploader': u'SBS',
21 u'description': u'md5:c4b17b9626dd4b143dcc4d855ba3474e',
22 u'upload_date': u'20131121',
23 u'age_limit': 13,
24 },
25 u'skip': u'Blocked in the US',
26 }
27
28 def _real_extract(self, url):
29 mobj = re.match(self._VALID_URL, url)
30 video_id = mobj.group(1)
31
32 webpage = self._download_webpage(url, video_id)
33 title = self._og_search_title(webpage)
34 description = self._og_search_description(webpage)
35 thumbnail = self._og_search_thumbnail(webpage)
36
37 uploader_m = re.search(
38 r'<strong>Broadcast Network: </strong>\s*([^<]*)<', webpage)
39 if uploader_m is None:
40 uploader = None
41 else:
42 uploader = uploader.group(1).strip()
43
44 rating_str = self._html_search_regex(
45 r'<strong>Rating: </strong>\s*([^<]*)<', webpage,
46 u'rating information', default='').strip()
47 RATINGS = {
48 'G': 0,
49 'PG': 10,
50 'PG-13': 13,
51 'R': 16,
52 'NC': 18,
53 }
54 age_limit = RATINGS.get(rating_str)
55
56 info_url = 'http://www.viki.com/player5_fragment/%s?action=show&controller=videos' % video_id
57 info_webpage = self._download_webpage(
58 info_url, video_id, note=u'Downloading info page')
59 if re.match(r'\s*<div\s+class="video-error', info_webpage):
60 raise ExtractorError(
61 u'Video %s is blocked from your location.' % video_id,
62 expected=True)
63 video_url = self._html_search_regex(
64 r'<source[^>]+src="([^"]+)"', info_webpage, u'video URL')
65
66 upload_date_str = self._html_search_regex(
67 r'"created_at":"([^"]+)"', info_webpage, u'upload date')
68 upload_date = (
69 unified_strdate(upload_date_str)
70 if upload_date_str is not None
71 else None
72 )
73
74 # subtitles
75 video_subtitles = self.extract_subtitles(video_id, info_webpage)
76 if self._downloader.params.get('listsubtitles', False):
77 self._list_available_subtitles(video_id, info_webpage)
78 return
79
80 return {
81 'id': video_id,
82 'title': title,
83 'url': video_url,
84 'description': description,
85 'thumbnail': thumbnail,
86 'age_limit': age_limit,
87 'uploader': uploader,
88 'subtitles': video_subtitles,
89 'upload_date': upload_date,
90 }
91
92 def _get_available_subtitles(self, video_id, info_webpage):
93 res = {}
94 for sturl in re.findall(r'<track src="([^"]+)"/>'):
95 m = re.search(r'/(?P<lang>[a-z]+)\.vtt', sturl)
96 if not m:
97 continue
98 res[m.group('lang')] = sturl
99 return res
|