yt_dlp/extractor/toypics.py

   1 from .common import InfoExtractor
   2 import re
   3
   4
   5 class ToypicsIE(InfoExtractor):
   6     IE_DESC = 'Toypics video'
   7     _VALID_URL = r'https?://videos\.toypics\.net/view/(?P<id>[0-9]+)'
   8     _TEST = {
   9         'url': 'http://videos.toypics.net/view/514/chancebulged,-2-1/',
  10         'md5': '16e806ad6d6f58079d210fe30985e08b',
  11         'info_dict': {
  12             'id': '514',
  13             'ext': 'mp4',
  14             'title': "Chance-Bulge'd, 2",
  15             'age_limit': 18,
  16             'uploader': 'kidsune',
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         video_id = self._match_id(url)
  22
  23         webpage = self._download_webpage(url, video_id)
  24
  25         formats = self._parse_html5_media_entries(
  26             url, webpage, video_id)[0]['formats']
  27         title = self._html_search_regex([
  28             r'<h1[^>]+class=["\']view-video-title[^>]+>([^<]+)</h',
  29             r'<title>([^<]+) - Toypics</title>',
  30         ], webpage, 'title')
  31
  32         uploader = self._html_search_regex(
  33             r'More videos from <strong>([^<]+)</strong>', webpage, 'uploader',
  34             fatal=False)
  35
  36         return {
  37             'id': video_id,
  38             'formats': formats,
  39             'title': title,
  40             'uploader': uploader,
  41             'age_limit': 18,
  42         }
  43
  44
  45 class ToypicsUserIE(InfoExtractor):
  46     IE_DESC = 'Toypics user profile'
  47     _VALID_URL = r'https?://videos\.toypics\.net/(?!view)(?P<id>[^/?#&]+)'
  48     _TEST = {
  49         'url': 'http://videos.toypics.net/Mikey',
  50         'info_dict': {
  51             'id': 'Mikey',
  52         },
  53         'playlist_mincount': 19,
  54     }
  55
  56     def _real_extract(self, url):
  57         username = self._match_id(url)
  58
  59         profile_page = self._download_webpage(
  60             url, username, note='Retrieving profile page')
  61
  62         video_count = int(self._search_regex(
  63             r'public/">Public Videos \(([0-9]+)\)</a></li>', profile_page,
  64             'video count'))
  65
  66         PAGE_SIZE = 8
  67         urls = []
  68         page_count = (video_count + PAGE_SIZE + 1) // PAGE_SIZE
  69         for n in range(1, page_count + 1):
  70             lpage_url = url + '/public/%d' % n
  71             lpage = self._download_webpage(
  72                 lpage_url, username,
  73                 note='Downloading page %d/%d' % (n, page_count))
  74             urls.extend(
  75                 re.findall(
  76                     r'<div[^>]+class=["\']preview[^>]+>\s*<a[^>]+href="(https?://videos\.toypics\.net/view/[^"]+)"',
  77                     lpage))
  78
  79         return {
  80             '_type': 'playlist',
  81             'id': username,
  82             'entries': [{
  83                 '_type': 'url',
  84                 'url': eurl,
  85                 'ie_key': 'Toypics',
  86             } for eurl in urls]
  87         }