1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-30 19:02:55 +01:00

[xhamster] Extract categories (closes #11728)

This commit is contained in:
Sergey M․ 2017-05-28 07:50:15 +07:00
parent 164fcbfeb7
commit 8555204274
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

View File

@ -4,6 +4,7 @@ import re
from .common import InfoExtractor
from ..utils import (
clean_html,
dict_get,
ExtractorError,
int_or_none,
@ -25,6 +26,7 @@ class XHamsterIE(InfoExtractor):
'uploader': 'Ruseful2011',
'duration': 893,
'age_limit': 18,
'categories': ['Fake Hub', 'Amateur', 'MILFs', 'POV', 'Boss', 'Office', 'Oral', 'Reality', 'Sexy'],
},
}, {
'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
@ -36,6 +38,7 @@ class XHamsterIE(InfoExtractor):
'uploader': 'jojo747400',
'duration': 200,
'age_limit': 18,
'categories': ['Britney Spears', 'Celebrities', 'HD Videos', 'Sexy', 'Sexy Booty'],
},
'params': {
'skip_download': True,
@ -51,6 +54,7 @@ class XHamsterIE(InfoExtractor):
'uploader': 'parejafree',
'duration': 72,
'age_limit': 18,
'categories': ['Amateur', 'Blowjobs'],
},
'params': {
'skip_download': True,
@ -152,6 +156,12 @@ class XHamsterIE(InfoExtractor):
self._sort_formats(formats)
categories_html = self._search_regex(
r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
'categories', default=None)
categories = [clean_html(category) for category in re.findall(
r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
return {
'id': video_id,
'title': title,
@ -165,6 +175,7 @@ class XHamsterIE(InfoExtractor):
'dislike_count': int_or_none(dislike_count),
'comment_count': int_or_none(comment_count),
'age_limit': age_limit,
'categories': categories,
'formats': formats,
}