0
0
Fork 0

[pornhub] Extract metadata from JSON-LD (closes #26614)

main
Sergey M․ 2020-09-19 06:34:34 +07:00
parent ce5b904050
commit cd85a1bb8b
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 12 additions and 5 deletions

View File

@ -17,6 +17,7 @@ from ..utils import (
determine_ext, determine_ext,
ExtractorError, ExtractorError,
int_or_none, int_or_none,
merge_dicts,
NO_DEFAULT, NO_DEFAULT,
orderedSet, orderedSet,
remove_quotes, remove_quotes,
@ -59,13 +60,14 @@ class PornHubIE(PornHubBaseIE):
''' '''
_TESTS = [{ _TESTS = [{
'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015', 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
'md5': '1e19b41231a02eba417839222ac9d58e', 'md5': 'a6391306d050e4547f62b3f485dd9ba9',
'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',
'upload_date': '20130628', 'upload_date': '20130628',
'timestamp': 1372447216,
'duration': 361, 'duration': 361,
'view_count': int, 'view_count': int,
'like_count': int, 'like_count': int,
@ -82,8 +84,8 @@ class PornHubIE(PornHubBaseIE):
'id': '1331683002', 'id': '1331683002',
'ext': 'mp4', 'ext': 'mp4',
'title': '重庆婷婷女王足交', 'title': '重庆婷婷女王足交',
'uploader': 'Unknown',
'upload_date': '20150213', 'upload_date': '20150213',
'timestamp': 1423804862,
'duration': 1753, 'duration': 1753,
'view_count': int, 'view_count': int,
'like_count': int, 'like_count': int,
@ -121,6 +123,7 @@ class PornHubIE(PornHubBaseIE):
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
'skip': 'This video has been disabled',
}, { }, {
'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d', 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
'only_matching': True, 'only_matching': True,
@ -338,7 +341,7 @@ class PornHubIE(PornHubBaseIE):
video_uploader = self._html_search_regex( video_uploader = self._html_search_regex(
r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<', r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
webpage, 'uploader', fatal=False) webpage, 'uploader', default=None)
view_count = self._extract_count( view_count = self._extract_count(
r'<span class="count">([\d,\.]+)</span> [Vv]iews', webpage, 'view') r'<span class="count">([\d,\.]+)</span> [Vv]iews', webpage, 'view')
@ -356,7 +359,11 @@ class PornHubIE(PornHubBaseIE):
if div: if div:
return re.findall(r'<a[^>]+\bhref=[^>]+>([^<]+)', div) return re.findall(r'<a[^>]+\bhref=[^>]+>([^<]+)', div)
return { info = self._search_json_ld(webpage, video_id, default={})
# description provided in JSON-LD is irrelevant
info['description'] = None
return merge_dicts({
'id': video_id, 'id': video_id,
'uploader': video_uploader, 'uploader': video_uploader,
'upload_date': upload_date, 'upload_date': upload_date,
@ -372,7 +379,7 @@ class PornHubIE(PornHubBaseIE):
'tags': extract_list('tags'), 'tags': extract_list('tags'),
'categories': extract_list('categories'), 'categories': extract_list('categories'),
'subtitles': subtitles, 'subtitles': subtitles,
} }, info)
class PornHubPlaylistBaseIE(PornHubBaseIE): class PornHubPlaylistBaseIE(PornHubBaseIE):