1 from __future__ import unicode_literals
6 from .common import InfoExtractor
17 class XTubeIE(InfoExtractor):
21 https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?:embedded/)?(?P<display_id>[^/]+)-)
28 'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
29 'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
33 'title': 'strange erotica',
34 'description': 'contains:an ET kind of thing',
35 'uploader': 'greenshowers',
42 # FLV videos with duplicated formats
43 'url': 'http://www.xtube.com/video-watch/A-Super-Run-Part-1-YT-9299752',
44 'md5': 'a406963eb349dd43692ec54631efd88b',
47 'display_id': 'A-Super-Run-Part-1-YT',
49 'title': 'A Super Run - Part 1 (YT)',
50 'description': 'md5:ca0d47afff4a9b2942e4b41aa970fd93',
51 'uploader': 'tshirtguy59',
59 'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
60 'only_matching': True,
62 'url': 'xtube:625837',
63 'only_matching': True,
65 'url': 'xtube:kVTUy_G222_',
66 'only_matching': True,
68 'url': 'https://www.xtube.com/video-watch/embedded/milf-tara-and-teen-shared-and-cum-covered-extreme-bukkake-32203482?embedsize=big',
69 'only_matching': True,
72 def _real_extract(self, url):
73 mobj = re.match(self._VALID_URL, url)
74 video_id = mobj.group('id')
75 display_id = mobj.group('display_id')
80 if video_id.isdigit() and len(video_id) < 11:
81 url_pattern = 'http://www.xtube.com/video-watch/-%s'
83 url_pattern = 'http://www.xtube.com/watch.php?v=%s'
85 webpage = self._download_webpage(
86 url_pattern % video_id, display_id, headers={
87 'Cookie': 'age_verified=1; cookiesAccepted=1',
90 sources = self._parse_json(self._search_regex(
91 r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
92 webpage, 'sources', group='sources'), video_id,
93 transform_source=js_to_json)
96 for format_id, format_url in sources.items():
99 'format_id': format_id,
100 'height': int_or_none(format_id),
102 self._remove_duplicate_formats(formats)
103 self._sort_formats(formats)
105 title = self._search_regex(
106 (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
107 webpage, 'title', group='title')
108 description = self._search_regex(
109 r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
110 uploader = self._search_regex(
111 (r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"',
112 r'<span[^>]+class="nickname"[^>]*>([^<]+)'),
113 webpage, 'uploader', fatal=False)
114 duration = parse_duration(self._search_regex(
115 r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>',
116 webpage, 'duration', fatal=False))
117 view_count = str_to_int(self._search_regex(
118 r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>',
119 webpage, 'view count', fatal=False))
120 comment_count = str_to_int(self._html_search_regex(
121 r'>Comments? \(([\d,\.]+)\)<',
122 webpage, 'comment count', fatal=False))
126 'display_id': display_id,
128 'description': description,
129 'uploader': uploader,
130 'duration': duration,
131 'view_count': view_count,
132 'comment_count': comment_count,
138 class XTubeUserIE(InfoExtractor):
139 IE_DESC = 'XTube user profile'
140 _VALID_URL = r'https?://(?:www\.)?xtube\.com/profile/(?P<id>[^/]+-\d+)'
142 'url': 'http://www.xtube.com/profile/greenshowers-4056496',
144 'id': 'greenshowers-4056496',
147 'playlist_mincount': 155,
150 def _real_extract(self, url):
151 user_id = self._match_id(url)
154 for pagenum in itertools.count(1):
155 request = sanitized_Request(
156 'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum),
158 'Cookie': 'popunder=4',
159 'X-Requested-With': 'XMLHttpRequest',
163 page = self._download_json(
164 request, user_id, 'Downloading videos JSON page %d' % pagenum)
166 html = page.get('html')
170 for video_id in orderedSet([video_id for _, video_id in re.findall(
171 r'data-plid=(["\'])(.+?)\1', html)]):
172 entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key()))
174 page_count = int_or_none(page.get('pageCount'))
175 if not page_count or pagenum == page_count:
178 playlist = self.playlist_result(entries, user_id)
179 playlist['age_limit'] = 18