Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/drtuber.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     NO_DEFAULT,
   8     str_to_int,
   9 )
  10
  11
  12 class DrTuberIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)'
  14     _TEST = {
  15         'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
  16         'md5': '93e680cf2536ad0dfb7e74d94a89facd',
  17         'info_dict': {
  18             'id': '1740434',
  19             'display_id': 'hot-perky-blonde-naked-golf',
  20             'ext': 'mp4',
  21             'title': 'hot perky blonde naked golf',
  22             'like_count': int,
  23             'comment_count': int,
  24             'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
  25             'thumbnail': 're:https?://.*\.jpg$',
  26             'age_limit': 18,
  27         }
  28     }
  29
  30     def _real_extract(self, url):
  31         mobj = re.match(self._VALID_URL, url)
  32         video_id = mobj.group('id')
  33         display_id = mobj.group('display_id')
  34
  35         webpage = self._download_webpage(url, display_id)
  36
  37         video_url = self._html_search_regex(
  38             r'<source src="([^"]+)"', webpage, 'video URL')
  39
  40         title = self._html_search_regex(
  41             (r'class="title_watch"[^>]*><p>([^<]+)<',
  42              r'<p[^>]+class="title_substrate">([^<]+)</p>',
  43              r'<title>([^<]+) - \d+'),
  44             webpage, 'title')
  45
  46         thumbnail = self._html_search_regex(
  47             r'poster="([^"]+)"',
  48             webpage, 'thumbnail', fatal=False)
  49
  50         def extract_count(id_, name, default=NO_DEFAULT):
  51             return str_to_int(self._html_search_regex(
  52                 r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
  53                 webpage, '%s count' % name, default=default, fatal=False))
  54
  55         like_count = extract_count('rate_likes', 'like')
  56         dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
  57         comment_count = extract_count('comments_count', 'comment')
  58
  59         cats_str = self._search_regex(
  60             r'<div[^>]+class="categories_list">(.+?)</div>',
  61             webpage, 'categories', fatal=False)
  62         categories = [] if not cats_str else re.findall(
  63             r'<a title="([^"]+)"', cats_str)
  64
  65         return {
  66             'id': video_id,
  67             'display_id': display_id,
  68             'url': video_url,
  69             'title': title,
  70             'thumbnail': thumbnail,
  71             'like_count': like_count,
  72             'dislike_count': dislike_count,
  73             'comment_count': comment_count,
  74             'categories': categories,
  75             'age_limit': self._rta_search(webpage),
  76         }