Merge branch 'peugeot-anysex'

This commit is contained in:
Sergey M․ 2014-08-31 07:06:08 +07:00
commit b170935a8f
2 changed files with 61 additions and 0 deletions

View file

@ -4,6 +4,7 @@ from .addanime import AddAnimeIE
from .adultswim import AdultSwimIE from .adultswim import AdultSwimIE
from .aftonbladet import AftonbladetIE from .aftonbladet import AftonbladetIE
from .anitube import AnitubeIE from .anitube import AnitubeIE
from .anysex import AnySexIE
from .aol import AolIE from .aol import AolIE
from .allocine import AllocineIE from .allocine import AllocineIE
from .aparat import AparatIE from .aparat import AparatIE

View file

@ -0,0 +1,60 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
parse_duration,
int_or_none,
)
class AnySexIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?anysex\.com/(?P<id>\d+)'
_TEST = {
'url': 'http://anysex.com/156592/',
'md5': '023e9fbb7f7987f5529a394c34ad3d3d',
'info_dict': {
'id': '156592',
'ext': 'mp4',
'title': 'Busty and sexy blondie in her bikini strips for you',
'description': 'md5:de9e418178e2931c10b62966474e1383',
'categories': ['Erotic'],
'duration': 270,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('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>(.*?)</title>', webpage, 'title')
description = self._html_search_regex(
r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
thumbnail = self._html_search_regex(
r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False)
categories = re.findall(
r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage)
duration = parse_duration(self._search_regex(
r'<b>Duration:</b> (\d+:\d+)', webpage, 'duration', fatal=False))
view_count = int_or_none(self._html_search_regex(
r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False))
return {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': title,
'description': description,
'thumbnail': thumbnail,
'categories': categories,
'duration': duration,
'view_count': view_count,
}