kumi/yt-dlp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[ard] Fix format extraction (fixes #3006 and #3032)

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-06-03 21:56:49 +02:00
parent 0d69795014
commit 6a3fa81ffb
1 changed files with 10 additions and 17 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
youtube_dl/extractor/ard.py
View file

@ -39,16 +39,18 @@ class ARDIE(InfoExtractor):
title = self._html_search_regex( title = self._html_search_regex(
[r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>', [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
r'<meta name="dcterms.title" content="(.*?)"/>',
r'<h4 class="headline">(.*?)</h4>'], r'<h4 class="headline">(.*?)</h4>'],
webpage, 'title') webpage, 'title')
description = self._html_search_meta( description = self._html_search_meta(
'dcterms.abstract', webpage, 'description') 'dcterms.abstract', webpage, 'description')
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._og_search_thumbnail(webpage)
streams = [
mo.groupdict() media_info = self._download_json(
for mo in re.finditer( 'http://www.ardmediathek.de/play/media/%s' % video_id, video_id)
r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)', webpage)] # The second element of the _mediaArray contains the standard http urls
streams = media_info['_mediaArray'][1]['_mediaStreamArray']
if not streams: if not streams:
if '"fsk"' in webpage: if '"fsk"' in webpage:
raise ExtractorError('This video is only available after 20:00') raise ExtractorError('This video is only available after 20:00')
@ -56,21 +58,12 @@ class ARDIE(InfoExtractor):
formats = [] formats = []
for s in streams: for s in streams:
format = { format = {
'quality': int(s['quality']), 'quality': s['_quality'],
'url': s['_stream'],
} }
if s.get('rtmp_url'):
format['protocol'] = 'rtmp'
format['url'] = s['rtmp_url']
format['playpath'] = s['video_url']
else:
format['url'] = s['video_url']
quality_name = self._search_regex( format['format_id'] = '%s-%s' % (
r'[,.]([a-zA-Z0-9_-]+),?\.mp4', format['url'], determine_ext(format['url']), format['quality'])
'quality name', default='NA')
format['format_id'] = '%s-%s-%s-%s' % (
determine_ext(format['url']), quality_name, s['media_type'],
s['quality'])
formats.append(format) formats.append(format)