github-com-ytdl-org/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-01-07 17:16:08 +00:00
Code Issues Releases Wiki Activity

Add tests and improve for HotNewHipHop

Browse source
This commit is contained in:
Philipp Hagemeister 2013-06-27 17:56:48 +02:00
parent b8f7b1579a
commit ed4a915e08
2 changed files with 11 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
test/tests.json
View file

@ -714,5 +714,14 @@
"info_dict": { "info_dict": {
"title": "Watch Till End: Herd of deer jump over a fence." "title": "Watch Till End: Herd of deer jump over a fence."
} }
},
{
"name": "HotNewHipHop",
"url": "http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html'",
"file": "1435540.mp3",
"md5": "2c2cd2f76ef11a9b3b581e8b232f3d96",
"info_dict": {
"title": "Freddie Gibbs Songs - Lay It Down"
}
} }
] ]

6
youtube_dl/extractor/hotnewhiphop.py
View file

@ -5,8 +5,7 @@ from .common import InfoExtractor
class HotNewHipHopIE(InfoExtractor): class HotNewHipHopIE(InfoExtractor):
_VALID_URL = r'(http://www\.hotnewhiphop.com/.*\.(?P<id>.*)\.html)' _VALID_URL = r'http://www\.hotnewhiphop.com/.*\.(?P<id>.*)\.html'
IE_NAME = u'HotNewHipHop'
def _real_extract(self, url): def _real_extract(self, url):
m = re.match(self._VALID_URL, url) m = re.match(self._VALID_URL, url)
@ -22,12 +21,11 @@ class HotNewHipHopIE(InfoExtractor):
u'video URL') u'video URL')
return self.url_result(video_url, ie='Youtube') return self.url_result(video_url, ie='Youtube')
video_url = base64.b64decode(video_url_base64) video_url = base64.b64decode(video_url_base64).decode('utf-8')
video_title = self._html_search_regex(r"<title>(.*)</title>", video_title = self._html_search_regex(r"<title>(.*)</title>",
webpage_src, u'title') webpage_src, u'title')
#"og:image" content=
# Getting thumbnail and if not thumbnail sets correct title for WSHH candy video. # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
thumbnail = self._html_search_regex(r'"og:image" content="(.*)"', thumbnail = self._html_search_regex(r'"og:image" content="(.*)"',
webpage_src, u'thumbnail', fatal=False) webpage_src, u'thumbnail', fatal=False)