paradizelost/youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[spiegeltv] Match hash-style URLs (Closes #4210)

Browse Source
This commit is contained in:
Philipp Hagemeister 2014-11-16 00:40:09 +01:00
parent 89c15fe0b3
commit 939fe70de0
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
youtube_dl/extractor/spiegeltv.py
View File

@ -6,7 +6,7 @@ from ..utils import float_or_none
class SpiegeltvIE(InfoExtractor): class SpiegeltvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.tv/filme/(?P<id>[\-a-z0-9]+)' _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/(?:#/)?filme/(?P<id>[\-a-z0-9]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.spiegel.tv/filme/flug-mh370/', 'url': 'http://www.spiegel.tv/filme/flug-mh370/',
'info_dict': { 'info_dict': {
@ -20,9 +20,14 @@ class SpiegeltvIE(InfoExtractor):
# rtmp download # rtmp download
'skip_download': True, 'skip_download': True,
} }
}, {
'url': 'http://www.spiegel.tv/#/filme/alleskino-die-wahrheit-ueber-maenner/',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
if '/#/' in url:
url = url.replace('/#/', '/')
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h1.*?>(.*?)</h1>', webpage, 'title') title = self._html_search_regex(r'<h1.*?>(.*?)</h1>', webpage, 'title')