]>
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]{10})'
16 _EMBED_BASE_URL
= 'http://fast.wistia.com/embed/'
19 'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt',
20 'md5': 'cafeb56ec0c53c18c97405eecb3133df',
24 'title': 'Being Resourceful',
25 'description': 'a Clients From Hell Video Series video from worldwidewebhosting',
26 'upload_date': '20131204',
27 'timestamp': 1386185018,
31 'url': 'wistia:sh7fpupwlt',
32 'only_matching': True,
35 'url': 'wistia:807fafadvk',
36 'only_matching': True,
38 'url': 'http://fast.wistia.com/embed/iframe/sh7fpupwlt',
39 'only_matching': True,
41 'url': 'http://fast.wistia.net/embed/medias/sh7fpupwlt.json',
42 'only_matching': True,
45 # https://wistia.com/support/embed-and-share/video-on-your-website
47 def _extract_url(webpage
):
48 urls
= WistiaIE
._extract
_urls
(webpage
)
49 return urls
[0] if urls
else None
52 def _extract_urls(webpage
):
54 for match
in re
.finditer(
55 r
'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P
<url
>(?
:https?
:)?
//(?
:fast\
.)?wistia\
.(?
:net|com
)/embed
/(?
:iframe|medias
)/[a
-z0
-9]{10}
)', webpage):
56 urls.append(unescapeHTML(match.group('url
')))
57 for match in re.finditer(
59 <div[^>]+class=(["'])(?
:(?
!\
1).)*?
\bwistia
_async
_(?P
<id>[a
-z0
-9]{10}
)\b(?
:(?
!\
1).)*?\
1
61 urls.append('wistia:%s' % match.group('id'))
62 for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage):
63 urls.append('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._EMBED_BASE_URL + 'medias/%s.json' % video_id, video_id,
71 # Some videos require this.
73 'Referer': url if url.startswith('http') else self._EMBED_BASE_URL + 'iframe/' + 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')),
98 'filesize': int_or_none(a.get('size')),
102 display_name = a.get('display_name')
104 if atype and atype.endswith('_video') and display_name:
105 format_id = '%s-%s' % (atype[:-6], display_name)
107 'format_id': format_id,
109 'tbr': int_or_none(a.get('bitrate')) or None,
110 'preference': 1 if atype == 'original' else None,
112 if display_name == 'Audio':
118 'width': int_or_none(a.get('width')),
119 'height': int_or_none(a.get('height')),
120 'vcodec': a.get('codec'),
122 if a.get('container') == 'm3u8' or aext == 'm3u8':
126 'format_id': f['format_id'].replace('hls-', 'ts-'),
127 'url': f['url'].replace('.bin', '.ts'),
132 'protocol': 'm3u8_native',
136 'container': a.get('container'),
138 'filesize': int_or_none(a.get('size')),
142 self._sort_formats(formats)
145 for caption in data.get('captions', []):
146 language = caption.get('language')
149 subtitles[language] = [{
150 'url': self._EMBED_BASE_URL + 'captions/' + video_id + '.vtt?language=' + language,
156 'description': data.get('seoDescription'),
158 'thumbnails': thumbnails,
159 'duration': float_or_none(data.get('duration')),
160 'timestamp': int_or_none(data.get('createdAt')),
161 'subtitles': subtitles,