1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-23 00:16:48 +00:00

[voicerepublic] Add new extractor

This commit is contained in:
Duncan 2015-05-10 12:30:07 +12:00
parent 3800b908b1
commit c6ddbdb66c
2 changed files with 56 additions and 0 deletions

View File

@ -634,6 +634,7 @@ from .vk import (
VKUserVideosIE,
)
from .vodlocker import VodlockerIE
from .voicerepublic import VoiceRepublicIE
from .vporn import VpornIE
from .vrt import VRTIE
from .vube import VubeIE

View File

@ -0,0 +1,55 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_urllib_request,
)
class VoiceRepublicIE(InfoExtractor):
_VALID_URL = r'https?://voicerepublic\.com/talks/(?P<id>[0-9a-z-]+)'
_TEST = {
'url': 'https://voicerepublic.com/talks/watching-the-watchers-building-a-sousveillance-state',
'md5': '0554a24d1657915aa8e8f84e15dc9353',
'info_dict': {
'id': '2296',
'ext': 'm4a',
'title': 'Watching the Watchers: Building a Sousveillance State',
'thumbnail': 'https://voicerepublic.com/system/flyer/2296.png',
'description': 'md5:715ba964958afa2398df615809cfecb1',
'creator': 'M. C. McGrath',
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
req = compat_urllib_request.Request(url)
# 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)
thumbnail = self._og_search_thumbnail(webpage)
video_id = self._search_regex(r'/(\d+)\.png', thumbnail, 'id')
if '<div class=\'vr-player jp-jplayer\'' in webpage:
formats = [{
'url': 'https://voicerepublic.com/vrmedia/{}-clean.{}'.format(video_id, ext),
'ext': ext,
'format_id': ext,
'vcodec': 'none',
} for ext in ['m4a', 'mp3', 'ogg']]
self._sort_formats(formats)
else:
# Audio is still queued for processing
formats = []
return {
'id': video_id,
'title': self._og_search_title(webpage),
'formats': formats,
'url': self._og_search_url(webpage),
'thumbnail': thumbnail,
'description': self._og_search_description(webpage),
'creator': self._search_regex(r'<meta content=\'([^\']*?)\' name=\'author\'>', webpage, 'author', fatal=False),
}