xZero707/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-27 06:10:38 +01:00
Code Issues Packages Projects Releases Wiki Activity

[voicerepublic] fix extraction

Browse Source
This commit is contained in:
Remita Amine 2020-01-19 20:15:02 +01:00
parent 9cf30dc017
commit be96f9924f
1 changed files with 19 additions and 57 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
youtube_dl/extractor/voicerepublic.py
View File

@ -1,17 +1,12 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import compat_str
compat_str,
compat_urlparse,
)
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
determine_ext, determine_ext,
int_or_none, int_or_none,
sanitized_Request, urljoin,
) )
@ -26,8 +21,7 @@ class VoiceRepublicIE(InfoExtractor):
'ext': 'm4a', 'ext': 'm4a',
'title': 'Watching the Watchers: Building a Sousveillance State', 'title': 'Watching the Watchers: Building a Sousveillance State',
'description': 'Secret surveillance programs have metadata too. The people and companies that operate secret surveillance programs can be surveilled.', 'description': 'Secret surveillance programs have metadata too. The people and companies that operate secret surveillance programs can be surveilled.',
'thumbnail': r're:^https?://.*\.(?:png|jpg)$', 'duration': 1556,
'duration': 1800,
'view_count': int, 'view_count': int,
} }
}, { }, {
@ -38,63 +32,31 @@ class VoiceRepublicIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
req = sanitized_Request( webpage = self._download_webpage(url, display_id)
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: if '>Queued for processing, please stand by...<' in webpage:
raise ExtractorError( raise ExtractorError(
'Audio is still queued for processing', expected=True) 'Audio is still queued for processing', expected=True)
config = self._search_regex( talk = self._parse_json(self._search_regex(
r'(?s)return ({.+?});\s*\n', webpage, r'initialSnapshot\s*=\s*({.+?});',
'data', default=None) webpage, 'talk'), display_id)['talk']
data = self._parse_json(config, display_id, fatal=False) if config else None title = talk['title']
if data:
title = data['title']
description = data.get('teaser')
talk_id = compat_str(data.get('talk_id') or display_id)
talk = data['talk']
duration = int_or_none(talk.get('duration'))
formats = [{ formats = [{
'url': compat_urlparse.urljoin(url, talk_url), 'url': urljoin(url, talk_url),
'format_id': format_id, 'format_id': format_id,
'ext': determine_ext(talk_url) or format_id, 'ext': determine_ext(talk_url) or format_id,
'vcodec': 'none', 'vcodec': 'none',
} for format_id, talk_url in talk['links'].items()] } for format_id, talk_url in talk['media_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) 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 { return {
'id': talk_id, 'id': compat_str(talk.get('id') or display_id),
'display_id': display_id, 'display_id': display_id,
'title': title, 'title': title,
'description': description, 'description': talk.get('teaser'),
'thumbnail': thumbnail, 'thumbnail': talk.get('image_url'),
'duration': duration, 'duration': int_or_none(talk.get('archived_duration')),
'view_count': view_count, 'view_count': int_or_none(talk.get('play_count')),
'formats': formats, 'formats': formats,
} }