]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/eporner.py
Prepare for release.
[youtubedl] / youtube_dl / extractor / eporner.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8 parse_duration,
9 str_to_int,
10 )
11
12
13 class EpornerIE(InfoExtractor):
14 _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\d+)/(?P<display_id>[\w-]+)'
15 _TEST = {
16 'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
17 'md5': '39d486f046212d8e1b911c52ab4691f8',
18 'info_dict': {
19 'id': '95008',
20 'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
21 'ext': 'mp4',
22 'title': 'Infamous Tiffany Teen Strip Tease Video',
23 'duration': 1838,
24 'view_count': int,
25 'age_limit': 18,
26 }
27 }
28
29 def _real_extract(self, url):
30 mobj = re.match(self._VALID_URL, url)
31 video_id = mobj.group('id')
32 display_id = mobj.group('display_id')
33
34 webpage = self._download_webpage(url, display_id)
35 title = self._html_search_regex(
36 r'<title>(.*?) - EPORNER', webpage, 'title')
37
38 redirect_code = self._html_search_regex(
39 r'<script type="text/javascript" src="/config5/%s/([a-f\d]+)/">' % video_id,
40 webpage, 'redirect_code')
41 redirect_url = 'http://www.eporner.com/config5/%s/%s' % (video_id, redirect_code)
42 player_code = self._download_webpage(
43 redirect_url, display_id, note='Downloading player config')
44
45 sources = self._search_regex(
46 r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', player_code, 'sources')
47
48 formats = []
49 for video_url, format_id in re.findall(r'file\s*:\s*"([^"]+)",\s*label\s*:\s*"([^"]+)"', sources):
50 fmt = {
51 'url': video_url,
52 'format_id': format_id,
53 }
54 m = re.search(r'^(\d+)', format_id)
55 if m:
56 fmt['height'] = int(m.group(1))
57 formats.append(fmt)
58 self._sort_formats(formats)
59
60 duration = parse_duration(self._html_search_meta('duration', webpage))
61 view_count = str_to_int(self._search_regex(
62 r'id="cinemaviews">\s*([0-9,]+)\s*<small>views',
63 webpage, 'view count', fatal=False))
64
65 return {
66 'id': video_id,
67 'display_id': display_id,
68 'title': title,
69 'duration': duration,
70 'view_count': view_count,
71 'formats': formats,
72 'age_limit': self._rta_search(webpage),
73 }