1 from __future__ import unicode_literals
2
3 import itertools
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8 int_or_none,
9 orderedSet,
10 parse_duration,
11 sanitized_Request,
12 str_to_int,
13 )
14
15
16 class XTubeIE(InfoExtractor):
17 _VALID_URL = r'''(?x)
18 (?:
19 xtube:|
20 https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?P<display_id>[^/]+)-)
21 )
22 (?P<id>[^/?&#]+)
23 '''
24
25 _TESTS = [{
26 # old URL schema
27 'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
28 'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
29 'info_dict': {
30 'id': 'kVTUy_G222_',
31 'ext': 'mp4',
32 'title': 'strange erotica',
33 'description': 'contains:an ET kind of thing',
34 'uploader': 'greenshowers',
35 'duration': 450,
36 'view_count': int,
37 'comment_count': int,
38 'age_limit': 18,
39 }
40 }, {
41 # new URL schema
42 'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
43 'only_matching': True,
44 }, {
45 'url': 'xtube:625837',
46 'only_matching': True,
47 }]
48
49 def _real_extract(self, url):
50 mobj = re.match(self._VALID_URL, url)
51 video_id = mobj.group('id')
52 display_id = mobj.group('display_id')
53
54 if not display_id:
55 display_id = video_id
56 url = 'http://www.xtube.com/watch.php?v=%s' % video_id
57
58 req = sanitized_Request(url)
59 req.add_header('Cookie', 'age_verified=1; cookiesAccepted=1')
60 webpage = self._download_webpage(req, display_id)
61
62 sources = self._parse_json(self._search_regex(
63 r'sources\s*:\s*({.+?}),', webpage, 'sources'), video_id)
64
65 formats = []
66 for format_id, format_url in sources.items():
67 formats.append({
68 'url': format_url,
69 'format_id': format_id,
70 'height': int_or_none(format_id),
71 })
72 self._sort_formats(formats)
73
74 title = self._search_regex(
75 (r'<h1>(?P<title>[^<]+)</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
76 webpage, 'title', group='title')
77 description = self._search_regex(
78 r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
79 uploader = self._search_regex(
80 (r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"',
81 r'<span[^>]+class="nickname"[^>]*>([^<]+)'),
82 webpage, 'uploader', fatal=False)
83 duration = parse_duration(self._search_regex(
84 r'<dt>Runtime:</dt>\s*<dd>([^<]+)</dd>',
85 webpage, 'duration', fatal=False))
86 view_count = str_to_int(self._search_regex(
87 r'<dt>Views:</dt>\s*<dd>([\d,\.]+)</dd>',
88 webpage, 'view count', fatal=False))
89 comment_count = str_to_int(self._html_search_regex(
90 r'>Comments? \(([\d,\.]+)\)<',
91 webpage, 'comment count', fatal=False))
92
93 return {
94 'id': video_id,
95 'display_id': display_id,
96 'title': title,
97 'description': description,
98 'uploader': uploader,
99 'duration': duration,
100 'view_count': view_count,
101 'comment_count': comment_count,
102 'age_limit': 18,
103 'formats': formats,
104 }
105
106
107 class XTubeUserIE(InfoExtractor):
108 IE_DESC = 'XTube user profile'
109 _VALID_URL = r'https?://(?:www\.)?xtube\.com/profile/(?P<id>[^/]+-\d+)'
110 _TEST = {
111 'url': 'http://www.xtube.com/profile/greenshowers-4056496',
112 'info_dict': {
113 'id': 'greenshowers-4056496',
114 'age_limit': 18,
115 },
116 'playlist_mincount': 155,
117 }
118
119 def _real_extract(self, url):
120 user_id = self._match_id(url)
121
122 entries = []
123 for pagenum in itertools.count(1):
124 request = sanitized_Request(
125 'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum),
126 headers={
127 'Cookie': 'popunder=4',
128 'X-Requested-With': 'XMLHttpRequest',
129 'Referer': url,
130 })
131
132 page = self._download_json(
133 request, user_id, 'Downloading videos JSON page %d' % pagenum)
134
135 html = page.get('html')
136 if not html:
137 break
138
139 for video_id in orderedSet([video_id for _, video_id in re.findall(
140 r'data-plid=(["\'])(.+?)\1', html)]):
141 entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key()))
142
143 page_count = int_or_none(page.get('pageCount'))
144 if not page_count or pagenum == page_count:
145 break
146
147 playlist = self.playlist_result(entries, user_id)
148 playlist['age_limit'] = 18
149 return playlist
|
