[spankbang:playlist] Add extractor (closes #19145)

This commit is contained in:
Sergey M․ 2019-02-08 00:09:50 +07:00
parent f06a1cabe8
commit 49bd993fd9
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
2 changed files with 36 additions and 2 deletions

View File

@ -1058,7 +1058,10 @@ from .southpark import (
SouthParkEsIE, SouthParkEsIE,
SouthParkNlIE SouthParkNlIE
) )
from .spankbang import SpankBangIE from .spankbang import (
SpankBangIE,
SpankBangPlaylistIE,
)
from .spankwire import SpankwireIE from .spankwire import SpankwireIE
from .spiegel import SpiegelIE, SpiegelArticleIE from .spiegel import SpiegelIE, SpiegelArticleIE
from .spiegeltv import SpiegeltvIE from .spiegeltv import SpiegeltvIE

View File

@ -5,6 +5,7 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
orderedSet,
parse_duration, parse_duration,
parse_resolution, parse_resolution,
str_to_int, str_to_int,
@ -12,7 +13,7 @@ from ..utils import (
class SpankBangIE(InfoExtractor): class SpankBangIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)' _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)\b'
_TESTS = [{ _TESTS = [{
'url': 'http://spankbang.com/3vvn/video/fantasy+solo', 'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
'md5': '1cc433e1d6aa14bc376535b8679302f7', 'md5': '1cc433e1d6aa14bc376535b8679302f7',
@ -103,3 +104,33 @@ class SpankBangIE(InfoExtractor):
'formats': formats, 'formats': formats,
'age_limit': age_limit, 'age_limit': age_limit,
} }
class SpankBangPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/[^/]+'
_TEST = {
'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties',
'info_dict': {
'id': 'ug0k',
'title': 'Big Ass Titties',
},
'playlist_mincount': 50,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(
url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
entries = [self.url_result(
'https://spankbang.com/%s/video' % video_id,
ie=SpankBangIE.ie_key(), video_id=video_id)
for video_id in orderedSet(re.findall(
r'<a[^>]+\bhref=["\']/?([\da-z]+)/play/', webpage))]
title = self._html_search_regex(
r'<h1>([^<]+)\s+playlist</h1>', webpage, 'playlist title',
fatal=False)
return self.playlist_result(entries, playlist_id, title)