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

   1 from .common import InfoExtractor
   2 from math import ceil
   3 import re
   4
   5
   6 class ToypicsIE(InfoExtractor):
   7     IE_DESC = 'Toypics user profile'
   8     _VALID_URL = r'http://videos\.toypics\.net/view/(?P<id>[0-9]+)/.*'
   9     _TEST = {
  10         'url': 'http://videos.toypics.net/view/514/chancebulged,-2-1/',
  11         'md5': '16e806ad6d6f58079d210fe30985e08b',
  12         'info_dict': {
  13             'id': '514',
  14             'ext': 'mp4',
  15             'title': 'Chance-Bulge\'d, 2',
  16             'age_limit': 18,
  17             'uploader': 'kidsune',
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         mobj = re.match(self._VALID_URL, url)
  23         video_id = mobj.group('id')
  24         page = self._download_webpage(url, video_id)
  25         video_url = self._html_search_regex(
  26             r'src:\s+"(http://static[0-9]+\.toypics\.net/flvideo/[^"]+)"', page, 'video URL')
  27         title = self._html_search_regex(
  28             r'<title>Toypics - ([^<]+)</title>', page, 'title')
  29         username = self._html_search_regex(
  30             r'toypics.net/([^/"]+)" class="user-name">', page, 'username')
  31         return {
  32             'id': video_id,
  33             'url': video_url,
  34             'title': title,
  35             'uploader': username,
  36             'age_limit': 18,
  37         }
  38
  39
  40 class ToypicsUserIE(InfoExtractor):
  41     IE_DESC = 'Toypics user profile'
  42     _VALID_URL = r'http://videos\.toypics\.net/(?P<username>[^/?]+)(?:$|[?#])'
  43
  44     def _real_extract(self, url):
  45         mobj = re.match(self._VALID_URL, url)
  46         username = mobj.group('username')
  47
  48         profile_page = self._download_webpage(
  49             url, username, note='Retrieving profile page')
  50
  51         video_count = int(self._search_regex(
  52             r'public/">Public Videos \(([0-9]+)\)</a></li>', profile_page,
  53             'video count'))
  54
  55         PAGE_SIZE = 8
  56         urls = []
  57         page_count = (video_count + PAGE_SIZE + 1) // PAGE_SIZE
  58         for n in range(1, page_count + 1):
  59             lpage_url = url + '/public/%d' % n
  60             lpage = self._download_webpage(
  61                 lpage_url, username,
  62                 note='Downloading page %d/%d' % (n, page_count))
  63             urls.extend(
  64                 re.findall(
  65                     r'<p class="video-entry-title">\n\s*<a href="(http://videos.toypics.net/view/[^"]+)">',
  66                     lpage))
  67
  68         return {
  69             '_type': 'playlist',
  70             'id': username,
  71             'entries': [{
  72                 '_type': 'url',
  73                 'url': url,
  74                 'ie_key': 'Toypics',
  75             } for url in urls]
  76         }