]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/drtuber.py
debian/copyright: Fix lintian's dep5-copyright-license-name-not-unique.
[youtubedl] / 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 str_to_int
7
8
9 class DrTuberIE(InfoExtractor):
10 _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)'
11 _TEST = {
12 'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
13 'md5': '93e680cf2536ad0dfb7e74d94a89facd',
14 'info_dict': {
15 'id': '1740434',
16 'display_id': 'hot-perky-blonde-naked-golf',
17 'ext': 'mp4',
18 'title': 'hot perky blonde naked golf',
19 'like_count': int,
20 'dislike_count': int,
21 'comment_count': int,
22 'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
23 'thumbnail': 're:https?://.*\.jpg$',
24 'age_limit': 18,
25 }
26 }
27
28 def _real_extract(self, url):
29 mobj = re.match(self._VALID_URL, url)
30 video_id = mobj.group('id')
31 display_id = mobj.group('display_id')
32
33 webpage = self._download_webpage(url, display_id)
34
35 video_url = self._html_search_regex(
36 r'<source src="([^"]+)"', webpage, 'video URL')
37
38 title = self._html_search_regex(
39 [r'class="hd_title" style="[^"]+">([^<]+)</h1>', r'<title>([^<]+) - \d+'],
40 webpage, 'title')
41
42 thumbnail = self._html_search_regex(
43 r'poster="([^"]+)"',
44 webpage, 'thumbnail', fatal=False)
45
46 like_count = str_to_int(self._html_search_regex(
47 r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
48 webpage, 'like count', fatal=False))
49 dislike_count = str_to_int(self._html_search_regex(
50 r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
51 webpage, 'like count', fatal=False))
52 comment_count = str_to_int(self._html_search_regex(
53 r'<span class="comments_count">([\d,\.]+)</span>',
54 webpage, 'comment count', fatal=False))
55
56 cats_str = self._search_regex(
57 r'<span>Categories:</span><div>(.+?)</div>', webpage, 'categories', fatal=False)
58 categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
59
60 return {
61 'id': video_id,
62 'display_id': display_id,
63 'url': video_url,
64 'title': title,
65 'thumbnail': thumbnail,
66 'like_count': like_count,
67 'dislike_count': dislike_count,
68 'comment_count': comment_count,
69 'categories': categories,
70 'age_limit': self._rta_search(webpage),
71 }