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

   1 from .common import InfoExtractor
   2 from math import ceil
   3 import re
   4
   5 class ToypicsIE(InfoExtractor):
   6     _VALID_URL = r'(?:http://)?videos\.toypics\.net/.*'
   7     _TEST = {
   8         'url': 'http://videos.toypics.net/view/514/chancebulged,-2-1/',
   9         #'md5': '8a8b546956bbd0e769dbe28f6e80abb3', == $head -c10K 12929646011616163504.mp4 |md5sum //no idea why it fails
  10         'info_dict': {
  11             'id': '514',
  12             'ext': 'mp4',
  13             'title': 'Chance-Bulge\'d, 2',
  14             'age_limit': 18
  15         }
  16     }
  17     PAGINATED=8
  18
  19     def _real_extract(self, url):
  20         mobj = re.match(r'(http://)?videos\.toypics\.net/(?P<username>[^/?]+)$', url)
  21         if not mobj:
  22             return self.extract_one(url)
  23         return [self.extract_one(u) for u in self.process_paginated(url,
  24             r'public/">Public Videos \((?P<videos_count>[0-9]+)\)</a></li>',
  25             r'<p class="video-entry-title">\n\s*<a href="(http://videos.toypics.net/view/[^"]+)">'
  26         )]
  27
  28     def process_paginated(self, profile_url, re_total, re_video_page):
  29         profile_page = self._download_webpage(profile_url, 'profile' , 'getting profile page: '+profile_url)
  30         videos_count = self._html_search_regex(re_total, profile_page, 'videos count')
  31         lst = []
  32         for n in xrange(1,int(ceil(float(videos_count)/self.PAGINATED)) +1):
  33             lpage_url = profile_url +'/public/%d'%n
  34             lpage = self._download_webpage(lpage_url, 'page %d'%n)
  35             lst.extend(re.findall(re_video_page, lpage))
  36         return lst
  37
  38     def extract_one(self,url):
  39         mobj = re.match(r'(http://)?videos\.toypics\.net/view/(?P<videoid>[0-9]+)/.*', url)
  40         video_id = mobj.group('videoid')
  41         page = self._download_webpage(url, video_id, 'getting page: '+url)
  42         video_url = self._html_search_regex(
  43             r'src:\s+"(http://static[0-9]+\.toypics\.net/flvideo/[^"]+)"', page, 'video URL')
  44         title = self._html_search_regex(
  45             r'<title>Toypics - ([^<]+)</title>', page, 'title')
  46         username = self._html_search_regex(
  47             r'toypics.net/([^/"]+)" class="user-name">', page, 'username')
  48         return {
  49             'id': video_id,
  50             'url': video_url,
  51             'ext': video_url[-3:],
  52             'title': title,
  53             'uploader': username,
  54             'age_limit': 18
  55         }