mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-08-18 13:20:46 +02:00
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
98 lines
3.7 KiB
Python
98 lines
3.7 KiB
Python
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import compat_urlparse
|
|
from ..utils import (
|
|
ExtractorError,
|
|
determine_ext,
|
|
int_or_none,
|
|
sanitized_Request,
|
|
)
|
|
|
|
|
|
class VoiceRepublicIE(InfoExtractor):
|
|
_VALID_URL = r'https?://voicerepublic\.com/(?:talks|embed)/(?P<id>[0-9a-z-]+)'
|
|
_TESTS = [{
|
|
'url': 'http://voicerepublic.com/talks/watching-the-watchers-building-a-sousveillance-state',
|
|
'md5': '0554a24d1657915aa8e8f84e15dc9353',
|
|
'info_dict': {
|
|
'id': '2296',
|
|
'display_id': 'watching-the-watchers-building-a-sousveillance-state',
|
|
'ext': 'm4a',
|
|
'title': 'Watching the Watchers: Building a Sousveillance State',
|
|
'description': 'md5:715ba964958afa2398df615809cfecb1',
|
|
'thumbnail': 're:^https?://.*\.(?:png|jpg)$',
|
|
'duration': 1800,
|
|
'view_count': int,
|
|
}
|
|
}, {
|
|
'url': 'http://voicerepublic.com/embed/watching-the-watchers-building-a-sousveillance-state',
|
|
'only_matching': True,
|
|
}]
|
|
|
|
def _real_extract(self, url):
|
|
display_id = self._match_id(url)
|
|
|
|
req = sanitized_Request(
|
|
compat_urlparse.urljoin(url, '/talks/%s' % display_id))
|
|
# Older versions of Firefox get redirected to an "upgrade browser" page
|
|
req.add_header('User-Agent', 'youtube-dl')
|
|
webpage = self._download_webpage(req, display_id)
|
|
|
|
if '>Queued for processing, please stand by...<' in webpage:
|
|
raise ExtractorError(
|
|
'Audio is still queued for processing', expected=True)
|
|
|
|
config = self._search_regex(
|
|
r'(?s)return ({.+?});\s*\n', webpage,
|
|
'data', default=None)
|
|
data = self._parse_json(config, display_id, fatal=False) if config else None
|
|
if data:
|
|
title = data['title']
|
|
description = data.get('teaser')
|
|
talk_id = data.get('talk_id') or display_id
|
|
talk = data['talk']
|
|
duration = int_or_none(talk.get('duration'))
|
|
formats = [{
|
|
'url': compat_urlparse.urljoin(url, talk_url),
|
|
'format_id': format_id,
|
|
'ext': determine_ext(talk_url) or format_id,
|
|
'vcodec': 'none',
|
|
} for format_id, talk_url in talk['links'].items()]
|
|
else:
|
|
title = self._og_search_title(webpage)
|
|
description = self._html_search_regex(
|
|
r"(?s)<div class='talk-teaser'[^>]*>(.+?)</div>",
|
|
webpage, 'description', fatal=False)
|
|
talk_id = self._search_regex(
|
|
[r"id='jc-(\d+)'", r"data-shareable-id='(\d+)'"],
|
|
webpage, 'talk id', default=None) or display_id
|
|
duration = None
|
|
player = self._search_regex(
|
|
r"class='vr-player jp-jplayer'([^>]+)>", webpage, 'player')
|
|
formats = [{
|
|
'url': compat_urlparse.urljoin(url, talk_url),
|
|
'format_id': format_id,
|
|
'ext': determine_ext(talk_url) or format_id,
|
|
'vcodec': 'none',
|
|
} for format_id, talk_url in re.findall(r"data-([^=]+)='([^']+)'", player)]
|
|
self._sort_formats(formats)
|
|
|
|
thumbnail = self._og_search_thumbnail(webpage)
|
|
view_count = int_or_none(self._search_regex(
|
|
r"class='play-count[^']*'>\s*(\d+) plays",
|
|
webpage, 'play count', fatal=False))
|
|
|
|
return {
|
|
'id': talk_id,
|
|
'display_id': display_id,
|
|
'title': title,
|
|
'description': description,
|
|
'thumbnail': thumbnail,
|
|
'duration': duration,
|
|
'view_count': view_count,
|
|
'formats': formats,
|
|
}
|