youtube-dl/youtube_dl/extractor/xnxx.py

85 lines
2.8 KiB
Python
Raw Permalink Normal View History

2016-10-02 11:39:18 +00:00
# coding: utf-8
2014-03-09 16:22:53 +00:00
from __future__ import unicode_literals
2018-03-10 16:13:14 +00:00
import re
2013-06-23 20:01:57 +00:00
from .common import InfoExtractor
2018-03-10 16:13:14 +00:00
from ..utils import (
determine_ext,
int_or_none,
NO_DEFAULT,
str_to_int,
)
2013-06-23 20:01:57 +00:00
class XNXXIE(InfoExtractor):
_VALID_URL = r'https?://(?:video|www)\.xnxx\.com/video-?(?P<id>[0-9a-z]+)/'
_TESTS = [{
2016-06-22 21:24:00 +00:00
'url': 'http://www.xnxx.com/video-55awb78/skyrim_test_video',
2018-03-10 16:13:14 +00:00
'md5': '7583e96c15c0f21e9da3453d9920fbba',
2014-03-09 16:22:53 +00:00
'info_dict': {
2016-06-22 21:24:00 +00:00
'id': '55awb78',
2018-03-10 16:13:14 +00:00
'ext': 'mp4',
2016-06-22 21:24:00 +00:00
'title': 'Skyrim Test Video',
2018-03-10 16:13:14 +00:00
'thumbnail': r're:^https?://.*\.jpg',
'duration': 469,
'view_count': int,
2014-03-09 16:22:53 +00:00
'age_limit': 18,
},
}, {
'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
'only_matching': True,
}, {
'url': 'http://www.xnxx.com/video-55awb78/',
'only_matching': True,
}]
2013-06-23 20:01:57 +00:00
def _real_extract(self, url):
video_id = self._match_id(url)
2018-03-10 16:13:14 +00:00
2013-06-23 20:01:57 +00:00
webpage = self._download_webpage(url, video_id)
2018-03-10 16:13:14 +00:00
def get(meta, default=NO_DEFAULT, fatal=True):
return self._search_regex(
r'set%s\s*\(\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % meta,
webpage, meta, default=default, fatal=fatal, group='value')
title = self._og_search_title(
webpage, default=None) or get('VideoTitle')
2013-06-23 20:01:57 +00:00
2018-03-10 16:13:14 +00:00
formats = []
for mobj in re.finditer(
r'setVideo(?:Url(?P<id>Low|High)|HLS)\s*\(\s*(?P<q>["\'])(?P<url>(?:https?:)?//.+?)(?P=q)', webpage):
format_url = mobj.group('url')
if determine_ext(format_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4', entry_protocol='m3u8_native',
preference=1, m3u8_id='hls', fatal=False))
else:
format_id = mobj.group('id')
if format_id:
format_id = format_id.lower()
formats.append({
'url': format_url,
'format_id': format_id,
'quality': -1 if format_id == 'low' else 0,
})
self._sort_formats(formats)
2013-06-23 20:01:57 +00:00
2018-03-10 16:13:14 +00:00
thumbnail = self._og_search_thumbnail(webpage, default=None) or get(
'ThumbUrl', fatal=False) or get('ThumbUrl169', fatal=False)
duration = int_or_none(self._og_search_property('duration', webpage))
view_count = str_to_int(self._search_regex(
r'id=["\']nb-views-number[^>]+>([\d,.]+)', webpage, 'view count',
default=None))
2013-06-23 20:01:57 +00:00
2014-03-09 16:22:53 +00:00
return {
2013-06-23 20:01:57 +00:00
'id': video_id,
2018-03-10 16:13:14 +00:00
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
2013-10-18 21:35:17 +00:00
'age_limit': 18,
2018-03-10 16:13:14 +00:00
'formats': formats,
2014-03-09 16:22:53 +00:00
}