1 from __future__ import unicode_literals
5 from .common import InfoExtractor
14 class WistiaIE(InfoExtractor):
15 _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/iframe/)(?P<id>[a-z0-9]+)'
16 _API_URL = 'http://fast.wistia.com/embed/medias/%s.json'
17 _IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s'
20 'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt',
21 'md5': 'cafeb56ec0c53c18c97405eecb3133df',
25 'title': 'Being Resourceful',
26 'description': 'a Clients From Hell Video Series video from worldwidewebhosting',
27 'upload_date': '20131204',
28 'timestamp': 1386185018,
32 'url': 'wistia:sh7fpupwlt',
33 'only_matching': True,
36 'url': 'wistia:807fafadvk',
37 'only_matching': True,
39 'url': 'http://fast.wistia.com/embed/iframe/sh7fpupwlt',
40 'only_matching': True,
44 def _extract_url(webpage):
46 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/iframe/.+?)\1', webpage)
48 return unescapeHTML(match.group('url'))
50 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
52 return 'wistia:%s' % match.group('id')
56 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
57 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
60 return 'wistia:%s' % match.group('id')
62 def _real_extract(self, url):
63 video_id = self._match_id(url)
65 data_json = self._download_json(
66 self._API_URL % video_id, video_id,
67 # Some videos require this.
69 'Referer': url if url.startswith('http') else self._IFRAME_URL % video_id,
72 if data_json.get('error'):
74 'Error while getting the playlist', expected=True)
76 data = data_json['media']
81 for a in data['assets']:
85 astatus = a.get('status')
87 if (astatus is not None and astatus != 2) or atype in ('preview', 'storyboard'):
89 elif atype in ('still', 'still_image'):
92 'width': int_or_none(a.get('width')),
93 'height': int_or_none(a.get('height')),
97 is_m3u8 = a.get('container') == 'm3u8' or aext == 'm3u8'
101 'tbr': int_or_none(a.get('bitrate')),
102 'vbr': int_or_none(a.get('opt_vbitrate')),
103 'width': int_or_none(a.get('width')),
104 'height': int_or_none(a.get('height')),
105 'filesize': int_or_none(a.get('size')),
106 'vcodec': a.get('codec'),
107 'container': a.get('container'),
108 'ext': 'mp4' if is_m3u8 else aext,
109 'protocol': 'm3u8' if is_m3u8 else None,
110 'preference': 1 if atype == 'original' else None,
113 self._sort_formats(formats)
118 'description': data.get('seoDescription'),
120 'thumbnails': thumbnails,
121 'duration': float_or_none(data.get('duration')),
122 'timestamp': int_or_none(data.get('createdAt')),