Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-09 21:57:14 +08:00
Code Issues Releases Wiki Activity

[asiancrush] fix extractor, add support for yuyutv and midnightpulp

Browse Source
This commit is contained in:
Elliot Algase 2019-06-07 23:57:46 -04:00
parent f8c55c6664
commit 8861b4b414
1 changed files with 80 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

106
youtube_dl/extractor/asiancrush.py
View File

@ -5,14 +5,13 @@ import re
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils import (
extract_attributes,
remove_end,
)
from ..utils import extract_attributes
class AsianCrushIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?asiancrush\.com/video/(?:[^/]+/)?0+(?P<id>\d+)v\b'
IE_NAME = 'asiancrush'
_DOMAINS = r'(?:asiancrush\.com|yuyutv\.com|midnightpulp\.com)'
_VALID_URL = r'https?://(?:www\.)?(?P<host>%s)/video/(?:[^/]+/)?0+(?P<id>\d+)v\b' % _DOMAINS
_TESTS = [{
'url': 'https://www.asiancrush.com/video/012869v/women-who-flirt/',
'md5': 'c3b740e48d0ba002a42c0b72857beae6',
@ -20,7 +19,7 @@ class AsianCrushIE(InfoExtractor):
'id': '1_y4tmjm5r',
'ext': 'mp4',
'title': 'Women Who Flirt',
'description': 'md5:3db14e9186197857e7063522cb89a805',
'description': 'md5:7e986615808bcfb11756eb503a751487',
'timestamp': 1496936429,
'upload_date': '20170608',
'uploader_id': 'craig@crifkin.com',
@ -28,11 +27,42 @@ class AsianCrushIE(InfoExtractor):
}, {
'url': 'https://www.asiancrush.com/video/she-was-pretty/011886v-pretty-episode-3/',
'only_matching': True,
}, {
'url': 'https://www.yuyutv.com/video/013886v/the-act-of-killing/',
'md5': '90dc82dfcd52e1f44c0b065bc1dd3827',
'info_dict': {
'id': '1_66x4rg7o',
'ext': 'mp4',
'title': 'The Act of Killing',
'description': 'md5:76d745019ef586b3dc59c2a344758741',
'timestamp': 1557419432,
'upload_date': '20190509',
'uploader_id': 'admin@ottera.tv',
},
}, {
'url': 'https://www.yuyutv.com/video/peep-show/013922v-warring-factions/',
'only_matching': True,
}, {
'url': 'https://www.midnightpulp.com/video/010400v/drifters/',
'md5': '44c7993934434afd7f1ee928ef0f734b',
'info_dict': {
'id': '1_sh88xpyz',
'ext': 'mp4',
'title': 'Drifters',
'description': 'md5:beccb5d5d2955d6defbf88ea256607db',
'timestamp': 1497470628,
'upload_date': '20170614',
'uploader_id': 'craig@crifkin.com',
},
}, {
'url': 'https://www.midnightpulp.com/video/mononoke/016378v-zashikiwarashi-part-1/',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
host = mobj.group('host')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
entry_id, partner_id, title = [None] * 3
@ -51,7 +81,7 @@ class AsianCrushIE(InfoExtractor):
r'\bentry_id["\']\s*:\s*["\'](\d+)', webpage, 'entry id')
player = self._download_webpage(
'https://api.asiancrush.com/embeddedVideoPlayer', video_id,
'https://api.%s/embeddedVideoPlayer' % host, video_id,
query={'id': entry_id})
kaltura_id = self._search_regex(
@ -63,15 +93,23 @@ class AsianCrushIE(InfoExtractor):
r'/p(?:artner_id)?/(\d+)', player, 'partner id',
default='513551')
return self.url_result(
'kaltura:%s:%s' % (partner_id, kaltura_id),
ie=KalturaIE.ie_key(), video_id=kaltura_id,
video_title=title)
description = self._html_search_regex(r'<div class="description">(.+?)</div>', webpage, 'description', fatal=False, flags=re.DOTALL)
return {
'_type': 'url_transparent',
'url': 'kaltura:%s:%s' % (partner_id, kaltura_id),
'ie_key': KalturaIE.ie_key(),
'id': video_id,
'title': title,
'description': description,
}
class AsianCrushPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?asiancrush\.com/series/0+(?P<id>\d+)s\b'
_TEST = {
_VIDEO_IE = AsianCrushIE
_DOMAINS = r'(?:asiancrush\.com|yuyutv\.com|midnightpulp\.com)'
_VALID_URL = r'https?://(?:www\.)?(?P<host>%s)/series/0+(?P<id>\d+)s\b' % _DOMAINS
_TESTS = [{
'url': 'https://www.asiancrush.com/series/012481s/scholar-walks-night/',
'info_dict': {
'id': '12481',
@ -79,7 +117,23 @@ class AsianCrushPlaylistIE(InfoExtractor):
'description': 'md5:7addd7c5132a09fd4741152d96cce886',
},
'playlist_count': 20,
}
}, {
'url': 'https://www.yuyutv.com/series/013920s/peep-show/',
'info_dict': {
'id': '13920',
'title': 'Peep Show',
'description': 'md5:15b59e05eb41fd2082671577eaf1b02d',
},
'playlist_count': 54,
}, {
'url': 'https://www.midnightpulp.com/series/016375s/mononoke/',
'info_dict': {
'id': '16375',
'title': 'Mononoke',
'description': 'md5:4a6d4f36eb1165f1854dbc9ac3b83c07',
},
'playlist_count': 12,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
@ -89,22 +143,22 @@ class AsianCrushPlaylistIE(InfoExtractor):
entries = []
for mobj in re.finditer(
r'<a[^>]+href=(["\'])(?P<url>%s.*?)\1[^>]*>' % AsianCrushIE._VALID_URL,
r'<a[^>]+href=(["\'])(?P<url>%s.*?)\1[^>]*>' % self._VIDEO_IE._VALID_URL,
webpage):
attrs = extract_attributes(mobj.group(0))
if attrs.get('class') == 'clearfix':
entries.append(self.url_result(
mobj.group('url'), ie=AsianCrushIE.ie_key()))
mobj.group('url'), ie=self._VIDEO_IE.ie_key()))
title = remove_end(
self._html_search_regex(
r'(?s)<h1\b[^>]\bid=["\']movieTitle[^>]+>(.+?)</h1>', webpage,
'title', default=None) or self._og_search_title(
webpage, default=None) or self._html_search_meta(
'twitter:title', webpage, 'title',
default=None) or self._search_regex(
r'<title>([^<]+)</title>', webpage, 'title', fatal=False),
' | AsianCrush')
title = re.sub(r'\s*\|\s*.+?$', '',
self._html_search_regex(
r'(?s)<h1\b[^>]\bid=["\']movieTitle[^>]+>(.+?)</h1>', webpage,
'title', default=None) or self._og_search_title(
webpage, default=None) or self._html_search_meta(
'twitter:title', webpage, 'title',
default=None) or self._search_regex(
r'<title>([^<]+)</title>', webpage, 'title', fatal=False)
)
description = self._og_search_description(
webpage, default=None) or self._html_search_meta(