]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/wistia.py
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|medias)/)(?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,
42 'url': 'http://fast.wistia.net/embed/medias/sh7fpupwlt.json',
43 'only_matching': True,
47 def _extract_url(webpage
):
49 r
'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:fast\
.)?wistia\
.(?
:net|com
)/embed
/iframe
/.+?
)\
1', webpage)
51 return unescapeHTML(match.group('url
'))
53 match = re.search(r'(?
:id=["\']wistia_|data-wistia-?id=["\']|Wistia\
.embed\
(["\'])(?P<id>[^"\']+)', webpage)
55 return 'wistia
:%s' % match.group('id')
59 <script[^>]+src=(["'])(?
:https?
:)?
//fast\
.wistia\
.com
/assets
/external
/E
-v1\
.js\
1[^
>]*>.*?
60 <div
[^
>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
63 return 'wistia:%s' % match.group('id')
65 def _real_extract(self, url):
66 video_id = self._match_id(url)
68 data_json = self._download_json(
69 self._API_URL % video_id, video_id,
70 # Some videos require this.
72 'Referer': url if url.startswith('http') else self._IFRAME_URL % video_id,
75 if data_json.get('error'):
77 'Error while getting the playlist', expected=True)
79 data = data_json['media']
84 for a in data['assets']:
88 astatus = a.get('status')
90 if (astatus is not None and astatus != 2) or atype in ('preview', 'storyboard'):
92 elif atype in ('still', 'still_image'):
95 'width': int_or_none(a.get('width')),
96 'height': int_or_none(a.get('height')),
100 is_m3u8 = a.get('container') == 'm3u8' or aext == 'm3u8'
104 'tbr': int_or_none(a.get('bitrate')),
105 'vbr': int_or_none(a.get('opt_vbitrate')),
106 'width': int_or_none(a.get('width')),
107 'height': int_or_none(a.get('height')),
108 'filesize': int_or_none(a.get('size')),
109 'vcodec': a.get('codec'),
110 'container': a.get('container'),
111 'ext': 'mp4' if is_m3u8 else aext,
112 'protocol': 'm3u8' if is_m3u8 else None,
113 'preference': 1 if atype == 'original' else None,
116 self._sort_formats(formats)
121 'description': data.get('seoDescription'),
123 'thumbnails': thumbnails,
124 'duration': float_or_none(data.get('duration')),
125 'timestamp': int_or_none(data.get('createdAt')),