MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-09 22:39:32 +01:00
Code Issues Projects Releases Wiki Activity

[daum] Get the video page from a canonical url to extract the full id (fixes #1373) and extract description.

Browse Source
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-09-05 10:08:17 +02:00
parent 085bea4513
commit 9363169b67
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
youtube_dl/extractor/daum.py
View File

@ -18,6 +18,7 @@ class DaumIE(InfoExtractor):
u'file': u'52554690.mp4', u'file': u'52554690.mp4',
u'info_dict': { u'info_dict': {
u'title': u'DOTA 2GETHER 시즌2 6회 - 2부', u'title': u'DOTA 2GETHER 시즌2 6회 - 2부',
u'description': u'DOTA 2GETHER 시즌2 6회 - 2부',
u'upload_date': u'20130831', u'upload_date': u'20130831',
u'duration': 3868, u'duration': 3868,
}, },
@ -26,7 +27,8 @@ class DaumIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1) video_id = mobj.group(1)
webpage = self._download_webpage(url, video_id) canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
webpage = self._download_webpage(canonical_url, video_id)
full_id = self._search_regex(r'<link rel="video_src" href=".+?vid=(.+?)"', full_id = self._search_regex(r'<link rel="video_src" href=".+?vid=(.+?)"',
webpage, u'full id') webpage, u'full id')
query = compat_urllib_parse.urlencode({'vid': full_id}) query = compat_urllib_parse.urlencode({'vid': full_id})
@ -63,6 +65,7 @@ def _real_extract(self, url):
'title': info.find('TITLE').text, 'title': info.find('TITLE').text,
'formats': formats, 'formats': formats,
'thumbnail': self._og_search_thumbnail(webpage), 'thumbnail': self._og_search_thumbnail(webpage),
'description': info.find('CONTENTS').text,
'duration': int(info.find('DURATION').text), 'duration': int(info.find('DURATION').text),
'upload_date': info.find('REGDTTM').text[:8], 'upload_date': info.find('REGDTTM').text[:8],
} }