[xhamster:user] Add extractor (closes #16330, closes #18454)

This commit is contained in:
Sergey M․ 2019-09-01 03:12:56 +07:00
parent 8945b10f6e
commit df228355fd
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
2 changed files with 49 additions and 0 deletions

View File

@ -1425,6 +1425,7 @@
from .xhamster import (
XHamsterIE,
XHamsterEmbedIE,
XHamsterUserIE,
)
from .xiami import (
XiamiSongIE,

View File

@ -1,5 +1,6 @@
from __future__ import unicode_literals
import itertools
import re
from .common import InfoExtractor
@ -8,6 +9,7 @@
clean_html,
determine_ext,
dict_get,
extract_attributes,
ExtractorError,
int_or_none,
parse_duration,
@ -331,3 +333,49 @@ def _real_extract(self, url):
video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
return self.url_result(video_url, 'XHamster')
class XHamsterUserIE(InfoExtractor):
_VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P<id>[^/?#&]+)' % XHamsterIE._DOMAINS
_TESTS = [{
# Paginated user profile
'url': 'https://xhamster.com/users/netvideogirls/videos',
'info_dict': {
'id': 'netvideogirls',
},
'playlist_mincount': 267,
}, {
# Non-paginated user profile
'url': 'https://xhamster.com/users/firatkaan/videos',
'info_dict': {
'id': 'firatkaan',
},
'playlist_mincount': 1,
}]
def _entries(self, user_id):
next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id
for pagenum in itertools.count(1):
page = self._download_webpage(
next_page_url, user_id, 'Downloading page %s' % pagenum)
for video_tag in re.findall(
r'(<a[^>]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)',
page):
video = extract_attributes(video_tag)
video_url = url_or_none(video.get('href'))
if not video_url or not XHamsterIE.suitable(video_url):
continue
video_id = XHamsterIE._match_id(video_url)
yield self.url_result(
video_url, ie=XHamsterIE.ie_key(), video_id=video_id)
mobj = re.search(r'<a[^>]+data-page=["\']next[^>]+>', page)
if not mobj:
break
next_page = extract_attributes(mobj.group(0))
next_page_url = url_or_none(next_page.get('href'))
if not next_page_url:
break
def _real_extract(self, url):
user_id = self._match_id(url)
return self.playlist_result(self._entries(user_id), user_id)