unescapeHTML,
unified_strdate,
US_RATINGS,
+ determine_ext,
+ mimetype2ext,
)
from .common import InfoExtractor
'upload_date': '20150430',
'title': '\'The Avengers: Age of Ultron\' Press Conference',
}
+ }, {
+ 'url': 'http://www.viki.com/videos/1048879v-ankhon-dekhi',
+ 'info_dict': {
+ 'id': '1048879v',
+ 'ext': 'mp4',
+ 'upload_date': '20140820',
+ 'description': 'md5:54ff56d51bdfc7a30441ec967394e91c',
+ 'title': 'Ankhon Dekhi',
+ },
+ 'params': {
+ # requires ffmpeg
+ 'skip_download': True,
+ }
}]
def _real_extract(self, url):
req.add_header('User-Agent', self._USER_AGENT)
info_webpage = self._download_webpage(
req, video_id, note='Downloading info page')
- if re.match(r'\s*<div\s+class="video-error', info_webpage):
- raise ExtractorError(
- 'Video %s is blocked from your location.' % video_id,
- expected=True)
- video_url = self._html_search_regex(
- r'<source[^>]+src="([^"]+)"', info_webpage, 'video URL')
+ err_msg = self._html_search_regex(r'<div[^>]+class="video-error[^>]+>(.+)</div>', info_webpage, 'error message', default=None)
+ if err_msg:
+ if 'not available in your region' in err_msg:
+ raise ExtractorError(
+ 'Video %s is blocked from your location.' % video_id,
+ expected=True)
+ else:
+ raise ExtractorError('Viki said: %s %s' % (err_msg, url))
+ mobj = re.search(
+ r'<source[^>]+type="(?P<mime_type>[^"]+)"[^>]+src="(?P<url>[^"]+)"', info_webpage)
+ if not mobj:
+ raise ExtractorError('Unable to find video URL')
+ video_url = unescapeHTML(mobj.group('url'))
+ video_ext = mimetype2ext(mobj.group('mime_type'))
+
+ if determine_ext(video_url) == 'm3u8':
+ formats = self._extract_m3u8_formats(
+ video_url, video_id, ext=video_ext)
+ else:
+ formats = [{
+ 'url': video_url,
+ 'ext': video_ext,
+ }]
upload_date_str = self._html_search_regex(
r'"created_at":"([^"]+)"', info_webpage, 'upload date')
return {
'id': video_id,
'title': title,
- 'url': video_url,
+ 'formats': formats,
'description': description,
'thumbnail': thumbnail,
'age_limit': age_limit,
'ext': 'vtt',
}]
return res
+
+
+class VikiShowIE(InfoExtractor):
+ IE_NAME = 'viki:show'
+ _VALID_URL = r'^https?://(?:www\.)?viki\.com/tv/(?P<id>[0-9]+c)'
+ _TESTS = [{
+ 'url': 'http://www.viki.com/tv/50c-boys-over-flowers',
+ 'info_dict': {
+ 'id': '50c',
+ 'title': 'Boys Over Flowers',
+ 'description': 'md5:ecd3cff47967fe193cff37c0bec52790',
+ },
+ 'playlist_count': 70,
+ }, {
+ 'url': 'http://www.viki.com/tv/1354c-poor-nastya-complete',
+ 'info_dict': {
+ 'id': '1354c',
+ 'title': 'Poor Nastya [COMPLETE]',
+ 'description': 'md5:05bf5471385aa8b21c18ad450e350525',
+ },
+ 'playlist_count': 127,
+ }]
+
+ def _real_extract(self, url):
+ show_id = self._match_id(url)
+ show_page = self._download_webpage(url, show_id, 'Download show page')
+
+ title = self._og_search_title(show_page)
+ description = self._og_search_description(show_page)
+
+ entries = []
+ for video_type in ['episodes', 'clips']:
+ json_url = 'http://api.viki.io/v4/containers/%s/%s.json?app=100000a&per_page=25&sort=number&direction=asc&with_paging=true&page=1' % (show_id, video_type)
+ while json_url is not None:
+ show_json = self._download_json(
+ json_url, show_id, note='Retrieve show json', errnote='Unable to get show json')
+ for video in show_json['response']:
+ video_id = video['id']
+ entries.append(self.url_result(
+ 'http://www.viki.com/videos/%s' % video_id, 'Viki', video_id))
+ json_url = show_json['pagination']['next']
+
+ return self.playlist_result(entries, show_id, title, description)