]>
Commit | Line | Data |
---|---|---|
c5ba203e AS |
1 | from __future__ import unicode_literals |
2 | ||
dcc2a706 | 3 | import re |
aa488e13 | 4 | import json |
dcc2a706 | 5 | |
6 | from .common import InfoExtractor | |
7 | from ..utils import ( | |
dcc2a706 | 8 | compat_urllib_request, |
607dbbad S |
9 | parse_duration, |
10 | str_to_int, | |
dcc2a706 | 11 | ) |
12 | ||
607dbbad | 13 | |
dcc2a706 | 14 | class XTubeIE(InfoExtractor): |
607dbbad | 15 | _VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<videoid>[^/?&]+))' |
dcc2a706 | 16 | _TEST = { |
c5ba203e | 17 | 'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_', |
c5ba203e AS |
18 | 'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab', |
19 | 'info_dict': { | |
607dbbad S |
20 | 'id': 'kVTUy_G222_', |
21 | 'ext': 'mp4', | |
22 | 'title': 'strange erotica', | |
23 | 'description': 'surreal gay themed erotica...almost an ET kind of thing', | |
24 | 'uploader': 'greenshowers', | |
25 | 'duration': 450, | |
26 | 'age_limit': 18, | |
dcc2a706 | 27 | } |
28 | } | |
29 | ||
30 | def _real_extract(self, url): | |
31 | mobj = re.match(self._VALID_URL, url) | |
32 | video_id = mobj.group('videoid') | |
33 | url = 'http://www.' + mobj.group('url') | |
34 | ||
35 | req = compat_urllib_request.Request(url) | |
36 | req.add_header('Cookie', 'age_verified=1') | |
37 | webpage = self._download_webpage(req, video_id) | |
38 | ||
607dbbad S |
39 | video_title = self._html_search_regex(r'<p class="title">([^<]+)', webpage, 'title') |
40 | video_uploader = self._html_search_regex( | |
41 | r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, 'uploader', fatal=False) | |
42 | video_description = self._html_search_regex( | |
43 | r'<p class="fieldsDesc">([^<]+)', webpage, 'description', fatal=False) | |
607dbbad S |
44 | duration = parse_duration(self._html_search_regex( |
45 | r'<span class="bold">Runtime:</span> ([^<]+)</p>', webpage, 'duration', fatal=False)) | |
46 | view_count = self._html_search_regex( | |
47 | r'<span class="bold">Views:</span> ([\d,\.]+)</p>', webpage, 'view count', fatal=False) | |
48 | if view_count: | |
49 | view_count = str_to_int(view_count) | |
50 | comment_count = self._html_search_regex( | |
51 | r'<div id="commentBar">([\d,\.]+) Comments</div>', webpage, 'comment count', fatal=False) | |
52 | if comment_count: | |
53 | comment_count = str_to_int(comment_count) | |
54 | ||
aa488e13 S |
55 | player_quality_option = json.loads(self._html_search_regex( |
56 | r'playerQualityOption = ({.+?});', webpage, 'player quality option')) | |
57 | ||
58 | QUALITIES = ['3gp', 'mp4_normal', 'mp4_high', 'flv', 'mp4_ultra', 'mp4_720', 'mp4_1080'] | |
59 | formats = [ | |
60 | { | |
56dd5572 | 61 | 'url': furl, |
aa488e13 S |
62 | 'format_id': format_id, |
63 | 'preference': QUALITIES.index(format_id) if format_id in QUALITIES else -1, | |
56dd5572 | 64 | } for format_id, furl in player_quality_option.items() |
aa488e13 S |
65 | ] |
66 | self._sort_formats(formats) | |
dcc2a706 | 67 | |
68 | return { | |
69 | 'id': video_id, | |
70 | 'title': video_title, | |
71 | 'uploader': video_uploader, | |
72 | 'description': video_description, | |
607dbbad S |
73 | 'duration': duration, |
74 | 'view_count': view_count, | |
75 | 'comment_count': comment_count, | |
aa488e13 | 76 | 'formats': formats, |
dcc2a706 | 77 | 'age_limit': 18, |
9f5809b3 | 78 | } |
79 | ||
22a6f150 | 80 | |
9f5809b3 | 81 | class XTubeUserIE(InfoExtractor): |
82 | IE_DESC = 'XTube user profile' | |
83 | _VALID_URL = r'https?://(?:www\.)?xtube\.com/community/profile\.php\?(.*?)user=(?P<username>[^&#]+)(?:$|[&#])' | |
22a6f150 PH |
84 | _TEST = { |
85 | 'url': 'http://www.xtube.com/community/profile.php?user=greenshowers', | |
86 | 'info_dict': { | |
87 | 'id': 'greenshowers', | |
88 | }, | |
89 | 'playlist_mincount': 155, | |
90 | } | |
9f5809b3 | 91 | |
92 | def _real_extract(self, url): | |
93 | mobj = re.match(self._VALID_URL, url) | |
94 | username = mobj.group('username') | |
95 | ||
96 | profile_page = self._download_webpage( | |
97 | url, username, note='Retrieving profile page') | |
98 | ||
99 | video_count = int(self._search_regex( | |
100 | r'<strong>%s\'s Videos \(([0-9]+)\)</strong>'%username, profile_page, | |
101 | 'video count')) | |
102 | ||
103 | PAGE_SIZE = 25 | |
104 | urls = [] | |
105 | page_count = (video_count + PAGE_SIZE + 1) // PAGE_SIZE | |
106 | for n in range(1, page_count + 1): | |
107 | lpage_url = 'http://www.xtube.com/user_videos.php?page=%d&u=%s' % (n, username) | |
108 | lpage = self._download_webpage( | |
109 | lpage_url, username, | |
110 | note='Downloading page %d/%d' % (n, page_count)) | |
111 | urls.extend( | |
112 | re.findall(r'addthis:url="([^"]+)"', lpage)) | |
113 | ||
114 | return { | |
115 | '_type': 'playlist', | |
116 | 'id': username, | |
117 | 'entries': [{ | |
118 | '_type': 'url', | |
119 | 'url': eurl, | |
120 | 'ie_key': 'XTube', | |
121 | } for eurl in urls] | |
122 | } |