mirror of https://github.com/yt-dlp/yt-dlp.git
[extractor:update]
Support profiles, searches, channels, quickies and favourites
This commit is contained in:
Tahasanul Abraham
parent
87264d4fda
commit
da07bbeb12
|
|
@ -2478,7 +2478,10 @@ from .xtube import XTubeUserIE, XTubeIE
|
|||
from .xuite import XuiteIE
|
||||
from .xvideos import (
|
||||
XVideosIE,
|
||||
XVideosQuickiesIE
|
||||
XVideosChannelIE,
|
||||
XVideosPlaylistIE,
|
||||
XVideosRelatedIE,
|
||||
XVideosSearchIE,
|
||||
)
|
||||
from .xxxymovies import XXXYMoviesIE
|
||||
from .yahoo import (
|
||||
|
|
|
|||
|
|
@ -1,13 +1,24 @@
|
|||
import re
|
||||
import itertools
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urllib_parse_unquote
|
||||
from ..compat import (
|
||||
compat_parse_qs,
|
||||
compat_str,
|
||||
compat_urlparse,
|
||||
compat_urllib_parse_unquote,
|
||||
compat_urllib_parse_urlencode,
|
||||
)
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
determine_ext,
|
||||
extract_attributes,
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
try_get,
|
||||
url_basename,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
|
|
@ -159,22 +170,239 @@ class XVideosIE(InfoExtractor):
|
|||
}
|
||||
|
||||
|
||||
class XVideosQuickiesIE(InfoExtractor):
|
||||
IE_NAME = 'xvideos:quickies'
|
||||
_VALID_URL = r'https?://(?P<domain>(?:[^/]+\.)?xvideos2?\.com)/amateur-channels/[^#]+#quickies/a/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.xvideos.com/amateur-channels/wifeluna#quickies/a/47258683',
|
||||
'md5': '16e322a93282667f1963915568f782c1',
|
||||
'info_dict': {
|
||||
'id': '47258683',
|
||||
'ext': 'mp4',
|
||||
'title': 'Verification video',
|
||||
'age_limit': 18,
|
||||
'duration': 16,
|
||||
'thumbnail': r're:^https://cdn.*-pic.xvideos-cdn.com/.+\.jpg',
|
||||
}
|
||||
}]
|
||||
class XVideosPlaylistIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:[^/]+\.)?xvideos2?\.com/
|
||||
(?:c(?:/[sm]:[^/]+)*|
|
||||
profiles|
|
||||
favorite)/
|
||||
(?P<id>[^#?/]+)
|
||||
'''
|
||||
_TESTS = []
|
||||
|
||||
def _extract_videos_from_json_list(self, json_list, path='video'):
|
||||
return (
|
||||
'https://www.xvideos.com/%s%d/%s' % (path, x.get('id'), str(x.get('u')).split('/')[-1])
|
||||
for x in json_list if isinstance(x, dict))
|
||||
|
||||
def _get_playlist_url(self, url, playlist_id):
|
||||
"""URL of first playlist page"""
|
||||
id_match = re.match(self._VALID_URL, url).groupdict()
|
||||
video_sort = id_match.get('sort')
|
||||
if video_sort:
|
||||
url, _ = compat_urlparse.urldefrag(url)
|
||||
if url.endswith('/'):
|
||||
url = url[:-1]
|
||||
url = '%s/%s' % (url, video_sort.replace('-', '/'))
|
||||
return url
|
||||
|
||||
def _get_next_page(self, url, num, page):
|
||||
'''URL of num'th continuation page of url'''
|
||||
if page.startswith('{'):
|
||||
url, sub = re.subn(r'(/)(\d{1,7})($|[#?/])', r'\g<1>%d\3' % (num, ), url)
|
||||
if sub == 0:
|
||||
url += '/%d' % (num, )
|
||||
return url
|
||||
next_page = self._search_regex(
|
||||
r'''(?s)(<a\s[^>]*?\bclass\s*=\s*(?P<q>'|").*?\bnext-page\b.*?(?P=q)[^>]*?>)''',
|
||||
page, 'next page', default=None)
|
||||
if next_page:
|
||||
next_page = extract_attributes(next_page)
|
||||
next_page = next_page.get('href')
|
||||
if next_page:
|
||||
return urljoin(url, next_page)
|
||||
return False
|
||||
|
||||
def _extract_videos(self, url, playlist_id, num, page):
|
||||
"""Get iterable videos plus stop flag"""
|
||||
return ((
|
||||
'https://www.xvideos.com/video' + x.group('video_id')
|
||||
for x in re.finditer(r'''class\s*=\s*"title"\s*>\s*<\s*a\s*href\s*=\s*(\'|")\/video(?P<video_id>(.*?))\1''', page)),
|
||||
None)
|
||||
|
||||
def _real_extract(self, url):
|
||||
domain, id_ = self._match_valid_url(url).group('domain', 'id')
|
||||
return self.url_result(f'https://{domain}/video{id_}/_', XVideosIE, id_)
|
||||
id_match = re.match(self._VALID_URL, url).groupdict()
|
||||
playlist_id = id_match['id']
|
||||
if "video" in playlist_id and url.endswith(playlist_id):
|
||||
url += '/0'
|
||||
|
||||
next_page = self._get_playlist_url(url, playlist_id)
|
||||
|
||||
if id_match['quickiesid']:
|
||||
return self.url_result(next_page, XVideosIE)
|
||||
|
||||
matches = []
|
||||
for count in itertools.count(0):
|
||||
webpage = self._download_webpage(
|
||||
next_page,
|
||||
'%s (+%d)' % (playlist_id, count) if count > 0 else playlist_id)
|
||||
|
||||
vids, stop = self._extract_videos(next_page, playlist_id, count, webpage)
|
||||
|
||||
if vids:
|
||||
matches.append(vids)
|
||||
|
||||
if stop:
|
||||
break
|
||||
next_page = self._get_next_page(next_page, count + 1, webpage)
|
||||
if not next_page:
|
||||
break
|
||||
|
||||
return self.playlist_from_matches(
|
||||
itertools.chain.from_iterable(matches), playlist_id)
|
||||
|
||||
|
||||
class XVideosRelatedIE(XVideosPlaylistIE):
|
||||
_VALID_URL = XVideosIE._VALID_URL + r'(?:/[^/]+)*?\#_related-(?P<related>videos|playlists)'
|
||||
|
||||
_TESTS = []
|
||||
|
||||
def _extract_videos(self, url, playlist_id, num, page):
|
||||
id_match = re.match(self._VALID_URL, url).groupdict()
|
||||
related = id_match.get('related')
|
||||
if not related:
|
||||
return super(XVideosRelatedIE, self)._extract_videos(url, playlist_id, num, page)
|
||||
|
||||
if related == 'videos':
|
||||
related_json = self._search_regex(
|
||||
r'(?s)videos_related\s*=\s*(\[.*?])\s*;',
|
||||
page, 'related', default='[]')
|
||||
related_json = self._parse_json(related_json, playlist_id, fatal=False) or []
|
||||
return (self._extract_videos_from_json_list(related_json), True)
|
||||
# playlists
|
||||
related_json = self._download_json(
|
||||
'https://www.xvideos.com/video-playlists/' + playlist_id, playlist_id, fatal=False)
|
||||
return (
|
||||
self._extract_videos_from_json_list(
|
||||
try_get(related_json, lambda x: x['playlists'], list) or [],
|
||||
path='favorite/'),
|
||||
True)
|
||||
|
||||
|
||||
class XVideosChannelIE(XVideosPlaylistIE):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:[^/]+\.)?xvideos2?\.com/
|
||||
(?:
|
||||
(?:amateur-|pornstar-|model-)?channel|profile|
|
||||
pornstar|model|amateur
|
||||
)s/
|
||||
(?P<id>[^#?/]+)
|
||||
(?:\#_tab(?P<tab>Videos|Favorites|Playlists|AboutMe)(?:,(?P<sort>[^,]+))?)?
|
||||
(?:\#quickies/a/(?P<quickiesid>.*))?
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'https://www.xvideos.com/pornstar-channels/sienna-west',
|
||||
'playlist_mincount': 5,
|
||||
}, {
|
||||
'url': 'https://www.xvideos.com/pornstars/silvia-jons#_tabVideos',
|
||||
'playlist_mincount': 5,
|
||||
}, {
|
||||
'url': 'https://www.xvideos.com/channels/miss_floyd#_tabVideos',
|
||||
'playlist_mincount': 5,
|
||||
}, {
|
||||
'url': 'https://www.xvideos.com/models/migurt-1',
|
||||
'playlist_mincount': 5,
|
||||
}, {
|
||||
'url': 'https://www.xvideos.com/amateur-channels/wifeluna#quickies/a/47258683',
|
||||
'playlist_mincount': 5,
|
||||
}, ]
|
||||
|
||||
def _get_playlist_url(self, url, playlist_id):
|
||||
webpage = self._download_webpage(url, playlist_id)
|
||||
id_match = re.match(self._VALID_URL, url).groupdict()
|
||||
tab = (id_match.get('tab') or '').lower()
|
||||
quickiesid = (id_match.get('quickiesid') or '').lower()
|
||||
|
||||
if not tab and not quickiesid:
|
||||
url += '#_tabVideos'
|
||||
|
||||
if tab and not quickiesid:
|
||||
if tab in ('videos', 'favorites'):
|
||||
url, frag = compat_urlparse.urldefrag(url)
|
||||
if not url.endswith('/'):
|
||||
url += '/'
|
||||
frag = frag.split(',')
|
||||
url += tab
|
||||
if tab == 'videos':
|
||||
url += '/' + (frag[1] if len(frag) > 1 else 'best')
|
||||
url += '/0'
|
||||
return url
|
||||
|
||||
elif quickiesid:
|
||||
url = f'https://www.xvideos.com/video{quickiesid}/_'
|
||||
return url
|
||||
|
||||
# activity
|
||||
conf = self._search_regex(
|
||||
r'(?s)\.\s*xv\s*\.\s*conf\s*=\s*(\{.*?})[\s;]*</script',
|
||||
webpage, 'XV conf')
|
||||
conf = self._parse_json(conf, playlist_id)
|
||||
act = try_get(conf,
|
||||
((lambda x: x['dyn'][y])
|
||||
for y in ('page_main_cat', 'user_main_cat')),
|
||||
compat_str) or 'straight'
|
||||
|
||||
url, _ = compat_urlparse.urldefrag(url)
|
||||
if url.endswith('/'):
|
||||
url = url[:-1]
|
||||
|
||||
return '%s/activity/%s' % (url, act, )
|
||||
|
||||
def _get_next_page(self, url, num, page):
|
||||
if page.startswith('{') or '#_tab' in url:
|
||||
return super(XVideosChannelIE, self)._get_next_page(url, num, page)
|
||||
|
||||
act_time = int_or_none(url_basename(url)) or 0
|
||||
last_act = int(self._search_regex(
|
||||
r'(?s)id\s*=\s*"?activity-event-(\d{10})(?!.*id\s*=\s*"?activity-event-\d+.*).+$',
|
||||
page, 'last activity', default=act_time))
|
||||
if last_act == act_time:
|
||||
return False
|
||||
return (
|
||||
url.replace('/%d' % (act_time, ), '/%d' % (last_act, ))
|
||||
if act_time
|
||||
else url + ('/%d' % (last_act, )))
|
||||
|
||||
def _extract_videos(self, url, playlist_id, num, page):
|
||||
tab = next((x for x in ('videos', 'favorites') if '/%s/' % (x, ) in url), None)
|
||||
if tab == 'videos':
|
||||
tab_json = self._parse_json(page, playlist_id, fatal=False) or {}
|
||||
more = try_get(tab_json, lambda x: x['current_page'] + 1, int)
|
||||
more = int_or_none(more, scale=tab_json.get('nb_videos'), invscale=tab_json.get('nb_per_page'), default=0)
|
||||
return (
|
||||
self._extract_videos_from_json_list(
|
||||
try_get(tab_json, lambda x: x['videos'], list) or []),
|
||||
more > 0)
|
||||
|
||||
if tab == 'favorites':
|
||||
return ((
|
||||
'https://www.xvideos.com' + x.group('playlist')
|
||||
for x in re.finditer(r'''<a\s[^>]*?href\s*=\s*('|")(?P<playlist>/favorite/\d+/[^#?]+?)\1''', page)),
|
||||
None)
|
||||
|
||||
return super(XVideosChannelIE, self)._extract_videos(url, playlist_id, num, page)
|
||||
|
||||
|
||||
class XVideosSearchIE(XVideosPlaylistIE):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:[^/]+\.)?xvideos2?\.com/
|
||||
\?k=(?P<id>[^#?/&]+)
|
||||
'''
|
||||
_TESTS = [{
|
||||
# uninteresting search with probably at least two pages of results,
|
||||
# but not too many more
|
||||
'url': 'http://www.xvideos.com/?k=libya&sort=length',
|
||||
'playlist_mincount': 30,
|
||||
}, ]
|
||||
|
||||
def _get_next_page(self, url, num, page):
|
||||
parsed_url = compat_urlparse.urlparse(url)
|
||||
qs = compat_parse_qs(parsed_url.query)
|
||||
qs['p'] = [num]
|
||||
parsed_url = (
|
||||
list(parsed_url[:4])
|
||||
+ [compat_urllib_parse_urlencode(qs, True), None])
|
||||
return compat_urlparse.urlunparse(parsed_url), False
|
||||
|
|
|
|||
Loading…
Reference in New Issue