etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-22 06:00:00 +00:00
Code Issues Projects Releases Wiki Activity

improve sohu extractor

Browse source
This commit is contained in:
huohuarong 2013-08-06 10:26:57 +08:00
parent b5a6d40818
commit d5b00ee6e0
1 changed files with 2 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
youtube_dl/extractor/sohu.py
View file

@ -31,6 +31,7 @@ def _real_extract(self, url):
compiled = re.compile(pattern, re.DOTALL)
title = self._search_regex(compiled, webpage, u'video title')
title = clean_html(title).split('-')[0].strip()
self.to_screen('Title: %s' % title)
pattern = re.compile(r'var vid="(\d+)"')
result = re.search(pattern, webpage)
if not result:
@ -70,6 +71,7 @@ def _real_extract(self, url):
base_url_3 = 'http://allot/?prot=prot&file=clipsURL[i]&new=su[i]'
files_info = []
for i in range(num_of_parts):
self.to_screen('Geting json infomation of part %s/%s' % (i + 1, num_of_parts))
middle_url = 'http://%s/?prot=%s&file=%s&new=%s' % (allot, prot, clipsURL[i], su[i])
logging.info('middle url part %d: %s' % (i, middle_url))
middle_info = urllib2.urlopen(middle_url).read().split('|')