mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-21 20:46:36 -05:00
[xnxx] Modernize
This commit is contained in:
parent
9e55e37a2e
commit
bdebf51c8f
1 changed files with 20 additions and 26 deletions
|
@ -1,55 +1,49 @@
|
||||||
|
# encoding: utf-8
|
||||||
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
import re
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
compat_urllib_parse,
|
compat_urllib_parse,
|
||||||
|
|
||||||
ExtractorError,
|
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
class XNXXIE(InfoExtractor):
|
class XNXXIE(InfoExtractor):
|
||||||
_VALID_URL = r'^(?:https?://)?(?:video|www)\.xnxx\.com/video([0-9]+)/(.*)'
|
_VALID_URL = r'^https?://(?:video|www)\.xnxx\.com/video(?P<id>[0-9]+)/(.*)'
|
||||||
VIDEO_URL_RE = r'flv_url=(.*?)&'
|
|
||||||
VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
|
|
||||||
VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&'
|
|
||||||
_TEST = {
|
_TEST = {
|
||||||
u'url': u'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
|
'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
|
||||||
u'file': u'1135332.flv',
|
'md5': '0831677e2b4761795f68d417e0b7b445',
|
||||||
u'md5': u'0831677e2b4761795f68d417e0b7b445',
|
'info_dict': {
|
||||||
u'info_dict': {
|
'id': '1135332',
|
||||||
u"title": u"lida \u00bb Naked Funny Actress (5)",
|
'ext': 'flv',
|
||||||
u"age_limit": 18,
|
'title': 'lida » Naked Funny Actress (5)',
|
||||||
|
'age_limit': 18,
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
mobj = re.match(self._VALID_URL, url)
|
mobj = re.match(self._VALID_URL, url)
|
||||||
if mobj is None:
|
video_id = mobj.group('id')
|
||||||
raise ExtractorError(u'Invalid URL: %s' % url)
|
|
||||||
video_id = mobj.group(1)
|
|
||||||
|
|
||||||
# Get webpage content
|
# Get webpage content
|
||||||
webpage = self._download_webpage(url, video_id)
|
webpage = self._download_webpage(url, video_id)
|
||||||
|
|
||||||
video_url = self._search_regex(self.VIDEO_URL_RE,
|
video_url = self._search_regex(r'flv_url=(.*?)&',
|
||||||
webpage, u'video URL')
|
webpage, 'video URL')
|
||||||
video_url = compat_urllib_parse.unquote(video_url)
|
video_url = compat_urllib_parse.unquote(video_url)
|
||||||
|
|
||||||
video_title = self._html_search_regex(self.VIDEO_TITLE_RE,
|
video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XNXX.COM',
|
||||||
webpage, u'title')
|
webpage, 'title')
|
||||||
|
|
||||||
video_thumbnail = self._search_regex(self.VIDEO_THUMB_RE,
|
video_thumbnail = self._search_regex(r'url_bigthumb=(.*?)&',
|
||||||
webpage, u'thumbnail', fatal=False)
|
webpage, 'thumbnail', fatal=False)
|
||||||
|
|
||||||
return [{
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'url': video_url,
|
'url': video_url,
|
||||||
'uploader': None,
|
|
||||||
'upload_date': None,
|
|
||||||
'title': video_title,
|
'title': video_title,
|
||||||
'ext': 'flv',
|
'ext': 'flv',
|
||||||
'thumbnail': video_thumbnail,
|
'thumbnail': video_thumbnail,
|
||||||
'description': None,
|
|
||||||
'age_limit': 18,
|
'age_limit': 18,
|
||||||
}]
|
}
|
||||||
|
|
Loading…
Reference in a new issue