mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-11-24 19:22:06 +00:00
Redesigned link extraction process
This commit is contained in:
parent
ee32d5ae0f
commit
63cf1124fa
1 changed files with 10 additions and 5 deletions
|
@ -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(
|
||||||
|
|
Loading…
Reference in a new issue