]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/eporner.py
Update upstream source from tag 'upstream/2020.03.24'
[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 encode_base_n,
9 ExtractorError,
10 int_or_none,
11 merge_dicts,
12 parse_duration,
13 str_to_int,
14 url_or_none,
15 )
16
17
18 class EpornerIE(InfoExtractor):
19 _VALID_URL = r'https?://(?:www\.)?eporner\.com/(?:hd-porn|embed)/(?P<id>\w+)(?:/(?P<display_id>[\w-]+))?'
20 _TESTS = [{
21 'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
22 'md5': '39d486f046212d8e1b911c52ab4691f8',
23 'info_dict': {
24 'id': 'qlDUmNsj6VS',
25 'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
26 'ext': 'mp4',
27 'title': 'Infamous Tiffany Teen Strip Tease Video',
28 'description': 'md5:764f39abf932daafa37485eb46efa152',
29 'timestamp': 1232520922,
30 'upload_date': '20090121',
31 'duration': 1838,
32 'view_count': int,
33 'age_limit': 18,
34 },
35 'params': {
36 'proxy': '127.0.0.1:8118'
37 }
38 }, {
39 # New (May 2016) URL layout
40 'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/',
41 'only_matching': True,
42 }, {
43 'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0',
44 'only_matching': True,
45 }, {
46 'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0',
47 'only_matching': True,
48 }]
49
50 def _real_extract(self, url):
51 mobj = re.match(self._VALID_URL, url)
52 video_id = mobj.group('id')
53 display_id = mobj.group('display_id') or video_id
54
55 webpage, urlh = self._download_webpage_handle(url, display_id)
56
57 video_id = self._match_id(urlh.geturl())
58
59 hash = self._search_regex(
60 r'hash\s*:\s*["\']([\da-f]{32})', webpage, 'hash')
61
62 title = self._og_search_title(webpage, default=None) or self._html_search_regex(
63 r'<title>(.+?) - EPORNER', webpage, 'title')
64
65 # Reverse engineered from vjs.js
66 def calc_hash(s):
67 return ''.join((encode_base_n(int(s[lb:lb + 8], 16), 36) for lb in range(0, 32, 8)))
68
69 video = self._download_json(
70 'http://www.eporner.com/xhr/video/%s' % video_id,
71 display_id, note='Downloading video JSON',
72 query={
73 'hash': calc_hash(hash),
74 'device': 'generic',
75 'domain': 'www.eporner.com',
76 'fallback': 'false',
77 })
78
79 if video.get('available') is False:
80 raise ExtractorError(
81 '%s said: %s' % (self.IE_NAME, video['message']), expected=True)
82
83 sources = video['sources']
84
85 formats = []
86 for kind, formats_dict in sources.items():
87 if not isinstance(formats_dict, dict):
88 continue
89 for format_id, format_dict in formats_dict.items():
90 if not isinstance(format_dict, dict):
91 continue
92 src = url_or_none(format_dict.get('src'))
93 if not src or not src.startswith('http'):
94 continue
95 if kind == 'hls':
96 formats.extend(self._extract_m3u8_formats(
97 src, display_id, 'mp4', entry_protocol='m3u8_native',
98 m3u8_id=kind, fatal=False))
99 else:
100 height = int_or_none(self._search_regex(
101 r'(\d+)[pP]', format_id, 'height', default=None))
102 fps = int_or_none(self._search_regex(
103 r'(\d+)fps', format_id, 'fps', default=None))
104
105 formats.append({
106 'url': src,
107 'format_id': format_id,
108 'height': height,
109 'fps': fps,
110 })
111 self._sort_formats(formats)
112
113 json_ld = self._search_json_ld(webpage, display_id, default={})
114
115 duration = parse_duration(self._html_search_meta(
116 'duration', webpage, default=None))
117 view_count = str_to_int(self._search_regex(
118 r'id="cinemaviews">\s*([0-9,]+)\s*<small>views',
119 webpage, 'view count', fatal=False))
120
121 return merge_dicts(json_ld, {
122 'id': video_id,
123 'display_id': display_id,
124 'title': title,
125 'duration': duration,
126 'view_count': view_count,
127 'formats': formats,
128 'age_limit': 18,
129 })