-# coding: utf-8
from __future__ import unicode_literals
-from .common import InfoExtractor
import re
+from .common import InfoExtractor
+
+
class SpankBangIE(InfoExtractor):
- """Extractor for http://spankbang.com"""
-
- _VALID_URL = r"https?://(?:www\.)?spankbang\.com/(?P<id>\w+)/video/.*"
+ _VALID_URL = r'https?://(?:(?:www|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
+ _TESTS = [{
+ 'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
+ 'md5': '1cc433e1d6aa14bc376535b8679302f7',
+ 'info_dict': {
+ 'id': '3vvn',
+ 'ext': 'mp4',
+ 'title': 'fantasy solo',
+ 'description': 'Watch fantasy solo free HD porn video - 05 minutes - dillion harper masturbates on a bed free adult movies.',
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ 'uploader': 'silly2587',
+ 'age_limit': 18,
+ }
+ }, {
+ # 480p only
+ 'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- title = self._html_search_regex(r"<h1>(?:<img.+?>)?(.*?)</h1>", webpage, "title")
-
- stream_key = self._html_search_regex(r"""var\s+stream_key\s*[=]\s*['"](.+?)['"]\s*;""", webpage, "stream_key")
-
- qualities = re.findall(r"<span.+?>([0-9]+p).*?</span>", webpage)
-
- formats = []
- for q in sorted(qualities):
- formats.append({
- "format_id": q,
- "format": q,
- "ext": "mp4",
- "url": "http://spankbang.com/_{}/{}/title/{}__mp4".format(video_id, stream_key, q)
- })
+ stream_key = self._html_search_regex(
+ r'''var\s+stream_key\s*=\s*['"](.+?)['"]''',
+ webpage, 'stream key')
+
+ formats = [{
+ 'url': 'http://spankbang.com/_%s/%s/title/%sp__mp4' % (video_id, stream_key, height),
+ 'ext': 'mp4',
+ 'format_id': '%sp' % height,
+ 'height': int(height),
+ } for height in re.findall(r'<(?:span|li|p)[^>]+[qb]_(\d+)p', webpage)]
+ self._check_formats(formats, video_id)
+ self._sort_formats(formats)
+
+ title = self._html_search_regex(
+ r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
+ description = self._og_search_description(webpage)
+ thumbnail = self._og_search_thumbnail(webpage)
+ uploader = self._search_regex(
+ r'class="user"[^>]*><img[^>]+>([^<]+)',
+ webpage, 'uploader', fatal=False)
+
+ age_limit = self._rta_search(webpage)
return {
- "id": video_id,
- "title": title,
- "description": self._og_search_description(webpage),
- "formats": formats
+ 'id': video_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'uploader': uploader,
+ 'formats': formats,
+ 'age_limit': age_limit,
}
-
-# vim: tabstop=4 expandtab