mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-07-18 03:08:31 +00:00
Code Issues Projects Releases Wiki Activity

[ie/pornhub] fix code

Browse Source
This commit is contained in:
DrJumba 2025-07-11 04:43:33 +05:30 committed by GitHub
parent 439b931411
commit 1565a11e9a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
yt_dlp/extractor/pornhub.py
View File

@ -20,6 +20,7 @@
remove_quotes, remove_quotes,
remove_start, remove_start,
str_to_int, str_to_int,
traverse_obj,
update_url_query, update_url_query,
url_or_none, url_or_none,
urlencode_postdata, urlencode_postdata,
@ -267,27 +268,6 @@ class PornHubIE(PornHubBaseIE):
def _extract_count(self, pattern, webpage, name): def _extract_count(self, pattern, webpage, name):
return str_to_int(self._search_regex(pattern, webpage, f'{name} count', default=None)) return str_to_int(self._search_regex(pattern, webpage, f'{name} count', default=None))
def _extract_chapters_from_action_tags(self, action_tags, duration):
if not action_tags:
return None
chapter_list = []
for entry in action_tags.split(','):
if ':' not in entry:
continue
title, start_str = entry.split(':', 1)
start_time = int_or_none(start_str)
if start_time is not None:
chapter_list.append({'title': title.strip(), 'start_time': start_time})
for i, chapter in enumerate(chapter_list):
if i + 1 < len(chapter_list):
chapter['end_time'] = chapter_list[i + 1]['start_time']
elif duration is not None:
chapter['end_time'] = duration
return chapter_list or None
def _real_extract(self, url): def _real_extract(self, url):
mobj = self._match_valid_url(url) mobj = self._match_valid_url(url)
host = mobj.group('host') or 'pornhub.com' host = mobj.group('host') or 'pornhub.com'
@ -346,7 +326,12 @@ def dl_webpage(platform):
}) })
thumbnail = flashvars.get('image_url') thumbnail = flashvars.get('image_url')
duration = int_or_none(flashvars.get('video_duration')) duration = int_or_none(flashvars.get('video_duration'))
chapters = self._extract_chapters_from_action_tags(flashvars.get('actionTags'), duration) chapters = traverse_obj(flashvars, (
'actionTags', {lambda x: x.split(',')}, ..., {lambda x: x.split(':', 1)},
all, lambda _, v: int_or_none(v[1]) is not None, {
'title': (0, {str.strip}),
'start_time': (1, {int_or_none}),
})) or None
media_definitions = flashvars.get('mediaDefinitions') media_definitions = flashvars.get('mediaDefinitions')
if isinstance(media_definitions, list): if isinstance(media_definitions, list):
for definition in media_definitions: for definition in media_definitions: