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

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