yt-dlp/youtube_dl/extractor/wistia.py

163 lines
5.8 KiB
Python
Raw Normal View History

2014-06-24 12:34:39 +00:00
from __future__ import unicode_literals
import re
2013-12-06 08:15:04 +00:00
from .common import InfoExtractor
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 16:18:17 +00:00
from ..utils import (
ExtractorError,
2016-03-17 16:48:17 +00:00
int_or_none,
float_or_none,
unescapeHTML,
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 16:18:17 +00:00
)
2013-12-06 08:15:04 +00:00
class WistiaIE(InfoExtractor):
_VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P<id>[a-z0-9]{10})'
_EMBED_BASE_URL = 'http://fast.wistia.com/embed/'
2013-12-06 08:15:04 +00:00
2016-05-20 14:55:10 +00:00
_TESTS = [{
2014-06-24 12:34:39 +00:00
'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt',
'md5': 'cafeb56ec0c53c18c97405eecb3133df',
'info_dict': {
'id': 'sh7fpupwlt',
'ext': 'mov',
'title': 'Being Resourceful',
2016-03-17 16:48:17 +00:00
'description': 'a Clients From Hell Video Series video from worldwidewebhosting',
'upload_date': '20131204',
'timestamp': 1386185018,
2014-06-24 12:34:39 +00:00
'duration': 117,
2013-12-06 08:15:04 +00:00
},
2016-05-20 14:55:10 +00:00
}, {
'url': 'wistia:sh7fpupwlt',
'only_matching': True,
2016-05-20 15:16:08 +00:00
}, {
# with hls video
'url': 'wistia:807fafadvk',
'only_matching': True,
}, {
'url': 'http://fast.wistia.com/embed/iframe/sh7fpupwlt',
'only_matching': True,
}, {
'url': 'http://fast.wistia.net/embed/medias/sh7fpupwlt.json',
'only_matching': True,
2016-05-20 14:55:10 +00:00
}]
2013-12-06 08:15:04 +00:00
# https://wistia.com/support/embed-and-share/video-on-your-website
@staticmethod
def _extract_url(webpage):
urls = WistiaIE._extract_urls(webpage)
return urls[0] if urls else None
@staticmethod
def _extract_urls(webpage):
urls = []
for match in re.finditer(
r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage):
urls.append(unescapeHTML(match.group('url')))
for match in re.finditer(
r'''(?sx)
<div[^>]+class=(["'])(?:(?!\1).)*?\bwistia_async_(?P<id>[a-z0-9]{10})\b(?:(?!\1).)*?\1
''', webpage):
urls.append('wistia:%s' % match.group('id'))
for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage):
urls.append('wistia:%s' % match.group('id'))
return urls
2013-12-06 08:15:04 +00:00
def _real_extract(self, url):
video_id = self._match_id(url)
2013-12-06 08:15:04 +00:00
2016-05-20 14:55:10 +00:00
data_json = self._download_json(
self._EMBED_BASE_URL + 'medias/%s.json' % video_id, video_id,
2016-05-20 14:55:10 +00:00
# Some videos require this.
headers={
'Referer': url if url.startswith('http') else self._EMBED_BASE_URL + 'iframe/' + video_id,
2016-05-20 14:55:10 +00:00
})
2014-09-20 00:02:11 +00:00
if data_json.get('error'):
2016-05-20 14:55:10 +00:00
raise ExtractorError(
'Error while getting the playlist', expected=True)
2014-09-20 00:02:11 +00:00
data = data_json['media']
2016-03-17 16:48:17 +00:00
title = data['name']
2013-12-06 08:15:04 +00:00
formats = []
thumbnails = []
2016-03-01 17:26:53 +00:00
for a in data['assets']:
aurl = a.get('url')
if not aurl:
continue
2016-03-17 16:48:17 +00:00
astatus = a.get('status')
2016-03-01 17:26:53 +00:00
atype = a.get('type')
if (astatus is not None and astatus != 2) or atype in ('preview', 'storyboard'):
2016-03-17 16:48:17 +00:00
continue
elif atype in ('still', 'still_image'):
2013-12-06 08:15:04 +00:00
thumbnails.append({
'url': aurl,
'width': int_or_none(a.get('width')),
'height': int_or_none(a.get('height')),
'filesize': int_or_none(a.get('size')),
2013-12-06 08:15:04 +00:00
})
2016-03-17 16:48:17 +00:00
else:
2016-05-20 15:16:08 +00:00
aext = a.get('ext')
display_name = a.get('display_name')
format_id = atype
if atype and atype.endswith('_video') and display_name:
format_id = '%s-%s' % (atype[:-6], display_name)
f = {
'format_id': format_id,
'url': aurl,
'tbr': int_or_none(a.get('bitrate')) or None,
2016-03-17 16:48:17 +00:00
'preference': 1 if atype == 'original' else None,
}
if display_name == 'Audio':
f.update({
'vcodec': 'none',
})
else:
f.update({
'width': int_or_none(a.get('width')),
'height': int_or_none(a.get('height')),
'vcodec': a.get('codec'),
})
if a.get('container') == 'm3u8' or aext == 'm3u8':
ts_f = f.copy()
ts_f.update({
'ext': 'ts',
'format_id': f['format_id'].replace('hls-', 'ts-'),
'url': f['url'].replace('.bin', '.ts'),
})
formats.append(ts_f)
f.update({
'ext': 'mp4',
'protocol': 'm3u8_native',
})
else:
f.update({
'container': a.get('container'),
'ext': aext,
'filesize': int_or_none(a.get('size')),
})
formats.append(f)
2013-12-25 14:20:14 +00:00
self._sort_formats(formats)
2013-12-06 08:15:04 +00:00
subtitles = {}
for caption in data.get('captions', []):
language = caption.get('language')
if not language:
continue
subtitles[language] = [{
'url': self._EMBED_BASE_URL + 'captions/' + video_id + '.vtt?language=' + language,
}]
2013-12-06 08:15:04 +00:00
return {
'id': video_id,
2016-03-17 16:48:17 +00:00
'title': title,
'description': data.get('seoDescription'),
2013-12-06 08:15:04 +00:00
'formats': formats,
'thumbnails': thumbnails,
'duration': float_or_none(data.get('duration')),
2016-03-17 16:48:17 +00:00
'timestamp': int_or_none(data.get('createdAt')),
'subtitles': subtitles,
2013-12-06 08:15:04 +00:00
}