]>
jfr.im git - yt-dlp.git/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]{10})'
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,
46 # https://wistia.com/support/embed-and-share/video-on-your-website
48 def _extract_url(webpage
):
50 r
'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P
<url
>(?
:https?
:)?
//(?
:fast\
.)?wistia\
.(?
:net|com
)/embed
/(?
:iframe|medias
)/[a
-z0
-9]{10}
)', webpage)
52 return unescapeHTML(match.group('url
'))
56 <script[^>]+src=(["'])(?
:https?
:)?
//fast\
.wistia\
.com
/assets
/external
/E
-v1\
.js\
1[^
>]*>.*?
57 <div
[^
>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2
60 return 'wistia:%s' % match.group('id')
62 match = re.search(r'(?:data-wistia-?id=["\']|Wistia\
.embed\
(["\']|id=["\']wistia_
)(?P
<id>[a
-z0
-9]{10}
)', webpage)
64 return 'wistia
:%s' % match.group('id')
66 def _real_extract(self, url):
67 video_id = self._match_id(url)
69 data_json = self._download_json(
70 self._API_URL % video_id, video_id,
71 # Some videos require this.
73 'Referer
': url if url.startswith('http
') else self._IFRAME_URL % video_id,
76 if data_json.get('error
'):
78 'Error
while getting the playlist
', expected=True)
80 data = data_json['media
']
85 for a in data['assets
']:
89 astatus = a.get('status
')
91 if (astatus is not None and astatus != 2) or atype in ('preview
', 'storyboard
'):
93 elif atype in ('still
', 'still_image
'):
96 'width
': int_or_none(a.get('width
')),
97 'height
': int_or_none(a.get('height
')),
101 is_m3u8 = a.get('container
') == 'm3u8
' or aext == 'm3u8
'
105 'tbr
': int_or_none(a.get('bitrate
')),
106 'vbr
': int_or_none(a.get('opt_vbitrate
')),
107 'width
': int_or_none(a.get('width
')),
108 'height
': int_or_none(a.get('height
')),
109 'filesize
': int_or_none(a.get('size
')),
110 'vcodec
': a.get('codec
'),
111 'container
': a.get('container
'),
112 'ext
': 'mp4
' if is_m3u8 else aext,
113 'protocol
': 'm3u8
' if is_m3u8 else None,
114 'preference
': 1 if atype == 'original
' else None,
117 self._sort_formats(formats)
122 'description
': data.get('seoDescription
'),
124 'thumbnails
': thumbnails,
125 'duration
': float_or_none(data.get('duration
')),
126 'timestamp
': int_or_none(data.get('createdAt
')),