1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-14 05:34:32 +01:00
youtube-dl/youtube_dl/extractor/xvideos.py
2016-08-16 21:20:15 +07:00

73 lines
2.3 KiB
Python

from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote
from ..utils import (
clean_html,
ExtractorError,
determine_ext,
)
class XVideosIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?xvideos\.com/video(?P<id>[0-9]+)(?:.*)'
_TEST = {
'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
'md5': '14cea69fcb84db54293b1e971466c2e1',
'info_dict': {
'id': '4588838',
'ext': 'mp4',
'title': 'Biker Takes his Girl',
'age_limit': 18,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
if mobj:
raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
video_title = self._html_search_regex(
r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
video_thumbnail = self._search_regex(
r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
formats = []
video_url = compat_urllib_parse_unquote(self._search_regex(
r'flv_url=(.+?)&', webpage, 'video URL', default=''))
if video_url:
formats.append({
'url': video_url,
'format_id': 'flv',
})
for kind, _, format_url in re.findall(
r'setVideo([^(]+)\((["\'])(http.+?)\2\)', webpage):
format_id = kind.lower()
if format_id == 'hls':
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
elif format_id in ('urllow', 'urlhigh'):
formats.append({
'url': format_url,
'format_id': '%s-%s' % (determine_ext(format_url, 'mp4'), format_id[3:]),
'quality': -2 if format_id.endswith('low') else None,
})
self._sort_formats(formats)
return {
'id': video_id,
'formats': formats,
'title': video_title,
'thumbnail': video_thumbnail,
'age_limit': 18,
}