R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[spiegeltv] ability to extract correct title for embedded videos (/embed/ in path)

Browse Source 
These URLs are used on the spiegel.de main site when embedding short
content from spiegel.tv.
This commit is contained in:
runningbits 2017-04-03 23:27:15 +02:00
parent b68e00b08a
commit e7a33a4eb3
1 changed files with 17 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
youtube_dl/extractor/spiegeltv.py
View File

@ -24,6 +24,19 @@ class SpiegeltvIE(InfoExtractor):
# m3u8 download
'skip_download': True,
}
}, {
'url': 'http://www.spiegel.tv/filme/putins-trollfabriken/embed/?autoplay=true',
'info_dict': {
'id': 'putins-trollfabriken',
'ext': 'm4v',
'title': 'Putins Trollfabriken',
'description': 'Propagandakrieg in den sozialen Medien',
'thumbnail': r're:http://.*\.jpg$',
},
'params': {
# m3u8 download
'skip_download': True,
}
}, {
'url': 'http://www.spiegel.tv/#/filme/alleskino-die-wahrheit-ueber-maenner/',
'only_matching': True,
@ -34,7 +47,10 @@ class SpiegeltvIE(InfoExtractor):
url = url.replace('/#/', '/')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h1.*?>(.*?)</h1>', webpage, 'title')
if '/embed/' not in url:
title = self._html_search_regex(r'<h1.*?>(.*?)</h1>', webpage, 'title')
else:
title = self._html_search_regex(r'<title.*?>(.*?)(?:\s*\-\s* Embed)?</title>', webpage, 'title')
apihost = 'http://spiegeltv-ivms2-restapi.s3.amazonaws.com'
version_json = self._download_json(