1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-20 23:17:50 +08:00
youtube-dl/youtube_dl/extractor/xxxymovies.py

64 lines
1.9 KiB
Python
Raw Normal View History

2014-12-29 18:31:22 +08:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
parse_duration,
int_or_none,
)
class XXXYMoviesIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?xxxymovies\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)'
_TEST = {
'url': 'http://xxxymovies.com/videos/138669/ecstatic-orgasm-sofcore/',
'md5': '810b1bdbbffff89dd13bdb369fe7be4b',
'info_dict': {
'id': '138669',
'display_id': 'ecstatic-orgasm-sofcore',
'ext': 'mp4',
'title': 'Ecstatic Orgasm Sofcore',
'duration': 931,
'age_limit': 18,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, video_id)
video_url = self._html_search_regex(
r"video_url\s*:\s*'([^']+)'", webpage, 'video URL')
title = self._html_search_regex(
r'<title>(.*?)\s*-\s*XXXYMovies.com</title>', webpage, 'title')
thumbnail = self._html_search_regex(
r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False)
categories = self._html_search_meta(
'keywords', webpage, 'categories', default='').split(',')
duration = parse_duration(self._search_regex(
r'<span>Duration:</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False))
view_count = int_or_none(self._html_search_regex(
r'<div class="video_views">\s*(\d+)', webpage, 'view count', fatal=False))
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'title': title,
'thumbnail': thumbnail,
'categories': categories,
'duration': duration,
'view_count': view_count,
'age_limit': 18,
}