yt-dlp/yt_dlp/extractor/wistia.py

198 lines
7.0 KiB
Python
Raw Normal View History

import re
2013-12-06 09:15:04 +01:00
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 17:18:17 +01:00
from ..utils import (
ExtractorError,
float_or_none,
2021-01-01 13:26:37 +01:00
int_or_none,
try_get,
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 17:18:17 +01:00
)
2013-12-06 09:15:04 +01:00
2021-01-01 13:26:37 +01:00
class WistiaBaseIE(InfoExtractor):
_VALID_ID_REGEX = r'(?P<id>[a-z0-9]{10})'
_VALID_URL_BASE = r'https?://(?:\w+\.)?wistia\.(?:net|com)/(?:embed/)?'
_EMBED_BASE_URL = 'http://fast.wistia.com/embed/'
2013-12-06 09:15:04 +01:00
2021-01-01 13:26:37 +01:00
def _download_embed_config(self, config_type, config_id, referer):
base_url = self._EMBED_BASE_URL + '%ss/%s' % (config_type, config_id)
embed_config = self._download_json(
base_url + '.json', config_id, headers={
'Referer': referer if referer.startswith('http') else base_url, # Some videos require this.
2016-05-20 16:55:10 +02:00
})
2021-01-01 13:26:37 +01:00
if isinstance(embed_config, dict) and embed_config.get('error'):
2016-05-20 16:55:10 +02:00
raise ExtractorError(
'Error while getting the playlist', expected=True)
2021-01-01 13:26:37 +01:00
return embed_config
def _extract_media(self, embed_config):
data = embed_config['media']
video_id = data['hashedId']
2016-03-17 17:48:17 +01:00
title = data['name']
2013-12-06 09:15:04 +01:00
formats = []
thumbnails = []
2016-03-01 18:26:53 +01:00
for a in data['assets']:
aurl = a.get('url')
if not aurl:
continue
2016-03-17 17:48:17 +01:00
astatus = a.get('status')
2016-03-01 18:26:53 +01:00
atype = a.get('type')
if (astatus is not None and astatus != 2) or atype in ('preview', 'storyboard'):
2016-03-17 17:48:17 +01:00
continue
elif atype in ('still', 'still_image'):
2013-12-06 09:15:04 +01:00
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 09:15:04 +01:00
})
2016-03-17 17:48:17 +01:00
else:
2016-05-20 17:16:08 +02:00
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,
'quality': 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 15:20:14 +01:00
self._sort_formats(formats)
2013-12-06 09:15:04 +01:00
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 09:15:04 +01:00
return {
'id': video_id,
2016-03-17 17:48:17 +01:00
'title': title,
'description': data.get('seoDescription'),
2013-12-06 09:15:04 +01:00
'formats': formats,
'thumbnails': thumbnails,
'duration': float_or_none(data.get('duration')),
2016-03-17 17:48:17 +01:00
'timestamp': int_or_none(data.get('createdAt')),
'subtitles': subtitles,
2013-12-06 09:15:04 +01:00
}
2021-01-01 13:26:37 +01:00
class WistiaIE(WistiaBaseIE):
_VALID_URL = r'(?:wistia:|%s(?:iframe|medias)/)%s' % (WistiaBaseIE._VALID_URL_BASE, WistiaBaseIE._VALID_ID_REGEX)
_TESTS = [{
# with hls video
'url': 'wistia:807fafadvk',
'md5': 'daff0f3687a41d9a71b40e0e8c2610fe',
'info_dict': {
'id': '807fafadvk',
'ext': 'mp4',
'title': 'Drip Brennan Dunn Workshop',
'description': 'a JV Webinars video',
'upload_date': '20160518',
'timestamp': 1463607249,
'duration': 4987.11,
},
}, {
'url': 'wistia:sh7fpupwlt',
'only_matching': True,
}, {
'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt',
'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,
}]
# 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
def _real_extract(self, url):
video_id = self._match_id(url)
embed_config = self._download_embed_config('media', video_id, url)
return self._extract_media(embed_config)
class WistiaPlaylistIE(WistiaBaseIE):
_VALID_URL = r'%splaylists/%s' % (WistiaBaseIE._VALID_URL_BASE, WistiaBaseIE._VALID_ID_REGEX)
2021-01-01 13:26:37 +01:00
_TEST = {
'url': 'https://fast.wistia.net/embed/playlists/aodt9etokc',
'info_dict': {
'id': 'aodt9etokc',
},
'playlist_count': 3,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
playlist = self._download_embed_config('playlist', playlist_id, url)
entries = []
for media in (try_get(playlist, lambda x: x[0]['medias']) or []):
embed_config = media.get('embed_config')
if not embed_config:
continue
entries.append(self._extract_media(embed_config))
return self.playlist_result(entries, playlist_id)