1 from __future__ import unicode_literals
5 from .common import InfoExtractor
12 class ExpoTVIE(InfoExtractor):
13 _VALID_URL = r'https?://www\.expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])'
15 'url': 'http://www.expotv.com/videos/reviews/1/24/LinneCardscom/17561',
16 'md5': '2985e6d7a392b2f7a05e0ca350fe41d0',
20 'upload_date': '20060212',
21 'title': 'My Favorite Online Scrapbook Store',
23 'description': 'You\'ll find most everything you need at this virtual store front.',
24 'uploader': 'Anna T.',
25 'thumbnail': 're:^https?://.*\.jpg$',
29 def _real_extract(self, url):
30 mobj = re.match(self._VALID_URL, url)
31 video_id = mobj.group('id')
33 webpage = self._download_webpage(url, video_id)
34 player_key = self._search_regex(
35 r'<param name="playerKey" value="([^"]+)"', webpage, 'player key')
36 config = self._download_json(
37 'http://client.expotv.com/video/config/%s/%s' % (video_id, player_key),
38 video_id, 'Downloading video configuration')
41 for fcfg in config['sources']:
42 media_url = fcfg.get('file')
45 if fcfg.get('type') == 'm3u8':
46 formats.extend(self._extract_m3u8_formats(
47 media_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls'))
51 'height': int_or_none(fcfg.get('height')),
52 'format_id': fcfg.get('label'),
53 'ext': self._search_regex(
54 r'filename=.*\.([a-z0-9_A-Z]+)&', media_url,
55 'file extension', default=None) or fcfg.get('type'),
57 self._sort_formats(formats)
59 title = self._og_search_title(webpage)
60 description = self._og_search_description(webpage)
61 thumbnail = config.get('image')
62 view_count = int_or_none(self._search_regex(
63 r'<h5>Plays: ([0-9]+)</h5>', webpage, 'view counts'))
64 uploader = self._search_regex(
65 r'<div class="reviewer">\s*<img alt="([^"]+)"', webpage, 'uploader',
67 upload_date = unified_strdate(self._search_regex(
68 r'<h5>Reviewed on ([0-9/.]+)</h5>', webpage, 'upload date',
75 'description': description,
76 'view_count': view_count,
77 'thumbnail': thumbnail,
79 'upload_date': upload_date,