midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[xhamster] Extract categories (closes #11728)

Browse source
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
1 changed files with 11 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
youtube_dl/extractor/xhamster.py
View file

@ -4,6 +4,7 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
clean_html,
dict_get, dict_get,
ExtractorError, ExtractorError,
int_or_none, int_or_none,
@ -25,6 +26,7 @@ class XHamsterIE(InfoExtractor):
'uploader': 'Ruseful2011', 'uploader': 'Ruseful2011',
'duration': 893, 'duration': 893,
'age_limit': 18, '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', 'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
@ -36,6 +38,7 @@ class XHamsterIE(InfoExtractor):
'uploader': 'jojo747400', 'uploader': 'jojo747400',
'duration': 200, 'duration': 200,
'age_limit': 18, 'age_limit': 18,
'categories': ['Britney Spears', 'Celebrities', 'HD Videos', 'Sexy', 'Sexy Booty'],
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
@ -51,6 +54,7 @@ class XHamsterIE(InfoExtractor):
'uploader': 'parejafree', 'uploader': 'parejafree',
'duration': 72, 'duration': 72,
'age_limit': 18, 'age_limit': 18,
'categories': ['Amateur', 'Blowjobs'],
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
@ -152,6 +156,12 @@ class XHamsterIE(InfoExtractor):
self._sort_formats(formats) 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 { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
@ -165,6 +175,7 @@ class XHamsterIE(InfoExtractor):
'dislike_count': int_or_none(dislike_count), 'dislike_count': int_or_none(dislike_count),
'comment_count': int_or_none(comment_count), 'comment_count': int_or_none(comment_count),
'age_limit': age_limit, 'age_limit': age_limit,
'categories': categories,
'formats': formats, 'formats': formats,
} }