mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-12-14 12:15:23 +00:00
Code Issues Projects Releases Wiki Activity

[ie/pornhub] Optimize metadata extraction (#15231)

Browse Source 
Closes #14621
Authored by: norepro
This commit is contained in:
norepro
2025-12-12 12:52:09 -08:00
committed by GitHub
parent 5f37f67d37
commit f2ee2a46fc
1 changed files with 10 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
yt_dlp/extractor/pornhub.py
View File

@@ -24,6 +24,7 @@ from ..utils import (
url_or_none, url_or_none,
urlencode_postdata, urlencode_postdata,
) )
from ..utils.traversal import find_elements, traverse_obj
class PornHubBaseIE(InfoExtractor): class PornHubBaseIE(InfoExtractor):
@@ -137,23 +138,24 @@ class PornHubIE(PornHubBaseIE):
_EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)'] _EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)']
_TESTS = [{ _TESTS = [{
'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015', 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
'md5': 'a6391306d050e4547f62b3f485dd9ba9', 'md5': '4d4a4e9178b655776f86cf89ecaf0edf',
'info_dict': { 'info_dict': {
'id': '648719015', 'id': '648719015',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Seductive Indian beauty strips down and fingers her pink pussy', 'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
'uploader': 'Babes', 'uploader': 'BABES-COM',
'uploader_id': '/users/babes-com',
'upload_date': '20130628', 'upload_date': '20130628',
'timestamp': 1372447216, 'timestamp': 1372447216,
'duration': 361, 'duration': 361,
'view_count': int, 'view_count': int,
'like_count': int, 'like_count': int,
'dislike_count': int,
'comment_count': int, 'comment_count': int,
'age_limit': 18, 'age_limit': 18,
'tags': list, 'tags': list,
'categories': list, 'categories': list,
'cast': list, 'cast': list,
'thumbnail': r're:https?://.+',
}, },
}, { }, {
# non-ASCII title # non-ASCII title
@@ -480,13 +482,6 @@ class PornHubIE(PornHubBaseIE):
comment_count = self._extract_count( comment_count = self._extract_count(
r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment') r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
def extract_list(meta_key):
div = self._search_regex(
rf'(?s)<div[^>]+\bclass=["\'].*?\b{meta_key}Wrapper[^>]*>(.+?)</div>',
webpage, meta_key, default=None)
if div:
return [clean_html(x).strip() for x in re.findall(r'(?s)<a[^>]+\bhref=[^>]+>.+?</a>', div)]
info = self._search_json_ld(webpage, video_id, default={}) info = self._search_json_ld(webpage, video_id, default={})
# description provided in JSON-LD is irrelevant # description provided in JSON-LD is irrelevant
info['description'] = None info['description'] = None
@@ -505,9 +500,11 @@ class PornHubIE(PornHubBaseIE):
'comment_count': comment_count, 'comment_count': comment_count,
'formats': formats, 'formats': formats,
'age_limit': 18, 'age_limit': 18,
'tags': extract_list('tags'), **traverse_obj(webpage, {
'categories': extract_list('categories'), 'tags': ({find_elements(attr='data-label', value='tag')}, ..., {clean_html}),
'cast': extract_list('pornstars'), 'categories': ({find_elements(attr='data-label', value='category')}, ..., {clean_html}),
'cast': ({find_elements(attr='data-label', value='pornstar')}, ..., {clean_html}),
}),
'subtitles': subtitles, 'subtitles': subtitles,
}, info) }, info)