_ Git - youtube-dl/blob - youtube_dl/extractor/spankbang.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 import re
   6
   7 class SpankBangIE(InfoExtractor):
   8     """Extractor for http://spankbang.com"""
   9
  10     _VALID_URL = r"https?://(?:www\.)?spankbang\.com/(?P<id>\w+)/video/.*"
  11
  12     def _real_extract(self, url):
  13         video_id = self._match_id(url)
  14         webpage = self._download_webpage(url, video_id)
  15
  16         title = self._html_search_regex(r"<h1>(?:<img.+?>)?(.*?)</h1>", webpage, "title")
  17
  18         stream_key = self._html_search_regex(r"""var\s+stream_key\s*[=]\s*['"](.+?)['"]\s*;""", webpage, "stream_key")
  19
  20         qualities = re.findall(r"<span.+?>([0-9]+p).*?</span>", webpage)
  21
  22         formats = []
  23         for q in sorted(qualities):
  24             formats.append({
  25                 "format_id": q,
  26                 "format": q,
  27                 "ext": "mp4",
  28                 "url": "http://spankbang.com/_{}/{}/title/{}__mp4".format(video_id, stream_key, q)
  29             })
  30
  31         return {
  32             "id": video_id,
  33             "title": title,
  34             "description": self._og_search_description(webpage),
  35             "formats": formats
  36         }
  37
  38 # vim: tabstop=4 expandtab