aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/worldstarhiphop.py
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2014-09-29 05:02:58 +0200
committerPhilipp Hagemeister <phihag@phihag.de>2014-09-29 05:02:58 +0200
commit12548cd9330222848f6b49fe9eac91aaff897325 (patch)
treec339c8e18813c9c895b0fd927980f3646c9dd10c /youtube_dl/extractor/worldstarhiphop.py
parent25930395225c45a9e5045ada291d37817371b086 (diff)
downloadyoutube-dl-12548cd9330222848f6b49fe9eac91aaff897325.tar.xz
[worldstarhiphop] Correct title extraction
Diffstat (limited to 'youtube_dl/extractor/worldstarhiphop.py')
-rw-r--r--youtube_dl/extractor/worldstarhiphop.py22
1 files changed, 10 insertions, 12 deletions
diff --git a/youtube_dl/extractor/worldstarhiphop.py b/youtube_dl/extractor/worldstarhiphop.py
index 4e89acd81..bda3870db 100644
--- a/youtube_dl/extractor/worldstarhiphop.py
+++ b/youtube_dl/extractor/worldstarhiphop.py
@@ -13,37 +13,35 @@ class WorldStarHipHopIE(InfoExtractor):
"info_dict": {
"id": "wshh6a7q1ny0G34ZwuIO",
"ext": "mp4",
- "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!"
+ "title": "KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!"
}
}
def _real_extract(self, url):
- m = re.match(self._VALID_URL, url)
- video_id = m.group('id')
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
- webpage_src = self._download_webpage(url, video_id)
-
- m_vevo_id = re.search(r'videoId=(.*?)&amp?',
- webpage_src)
+ m_vevo_id = re.search(r'videoId=(.*?)&amp?', webpage)
if m_vevo_id is not None:
return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo')
video_url = self._search_regex(
- r'so\.addVariable\("file","(.*?)"\)', webpage_src, 'video URL')
+ r'so\.addVariable\("file","(.*?)"\)', webpage, 'video URL')
if 'youtube' in video_url:
return self.url_result(video_url, ie='Youtube')
video_title = self._html_search_regex(
- r"<title>(.*)</title>", webpage_src, 'title')
+ r'(?s)<div class="content-heading">\s*<h1>(.*?)</h1>',
+ webpage, 'title')
# Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
thumbnail = self._html_search_regex(
- r'rel="image_src" href="(.*)" />', webpage_src, 'thumbnail',
+ r'rel="image_src" href="(.*)" />', webpage, 'thumbnail',
fatal=False)
if not thumbnail:
- _title = r"""candytitles.*>(.*)</span>"""
- mobj = re.search(_title, webpage_src)
+ _title = r'candytitles.*>(.*)</span>'
+ mobj = re.search(_title, webpage)
if mobj is not None:
video_title = mobj.group(1)