mirrors/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-07-29 23:55:50 +00:00
Code Issues Projects Releases Wiki Activity

Redesigned link extraction process

Browse source
This commit is contained in:
Thomas Christlieb 2017-02-05 21:13:51 +01:00
parent ee32d5ae0f
commit 63cf1124fa
1 changed files with 10 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
youtube_dl/extractor/iqiyi.py
View file

@ -19,6 +19,7 @@ from ..utils import (
ExtractorError, ExtractorError,
ohdave_rsa_encrypt, ohdave_rsa_encrypt,
remove_start, remove_start,
extract_attributes,
) )
@ -301,10 +302,14 @@ class IqiyiIE(InfoExtractor):
def _extract_playlist(self, webpage): def _extract_playlist(self, webpage):
PAGE_SIZE = 50 PAGE_SIZE = 50
links = re.findall( links = []
r'<a[^>]+href="(http://www\.iqiyi\.com/.+\.html)"[^>]+class="site-piclist_pic_link".*>', for link in re.findall(r'<a[^>]+class="[^"]*site-piclist_pic_link[^"]*"[^>]*>', webpage):
webpage) attribs = extract_attributes(link)
if not links: # It must be a valid url, and links on the playlist page have NO title-Attribute in them
# (links to other videos on the video page have, so beware of that!)
if attribs['href'].startswith('http') and 'title' not in attribs:
links.append(attribs['href'])
if len(links) == 0:
return return
album_id = self._search_regex( album_id = self._search_regex(
@ -331,7 +336,7 @@ class IqiyiIE(InfoExtractor):
break break
else: else:
break break
return self.playlist_result(entries, album_id, album_title) return self.playlist_result(entries, album_id, album_title)
def _real_extract(self, url): def _real_extract(self, url):