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/(?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,
69 def _real_extract(self, url):
70 mobj = re.match(self._VALID_URL, url)
71 video_id = mobj.group('id')
72 display_id = mobj.group('display_id')
77 if video_id.isdigit() and len(video_id) < 11:
78 url_pattern = 'http://www.xtube.com/video-watch/-%s'
80 url_pattern = 'http://www.xtube.com/watch.php?v=%s'
82 webpage = self._download_webpage(
83 url_pattern % video_id, display_id, headers={
84 'Cookie': 'age_verified=1; cookiesAccepted=1',
87 sources = self._parse_json(self._search_regex(
88 r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
89 webpage, 'sources', group='sources'), video_id,
90 transform_source=js_to_json)
93 for format_id, format_url in sources.items():
96 'format_id': format_id,
97 'height': int_or_none(format_id),
99 self._remove_duplicate_formats(formats)
100 self._sort_formats(formats)
102 title = self._search_regex(
103 (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
104 webpage, 'title', group='title')
105 description = self._search_regex(
106 r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
107 uploader = self._search_regex(
108 (r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"',
109 r'<span[^>]+class="nickname"[^>]*>([^<]+)'),
110 webpage, 'uploader', fatal=False)
111 duration = parse_duration(self._search_regex(
112 r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>',
113 webpage, 'duration', fatal=False))
114 view_count = str_to_int(self._search_regex(
115 r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>',
116 webpage, 'view count', fatal=False))
117 comment_count = str_to_int(self._html_search_regex(
118 r'>Comments? \(([\d,\.]+)\)<',
119 webpage, 'comment count', fatal=False))
123 'display_id': display_id,
125 'description': description,
126 'uploader': uploader,
127 'duration': duration,
128 'view_count': view_count,
129 'comment_count': comment_count,
135 class XTubeUserIE(InfoExtractor):
136 IE_DESC = 'XTube user profile'
137 _VALID_URL = r'https?://(?:www\.)?xtube\.com/profile/(?P<id>[^/]+-\d+)'
139 'url': 'http://www.xtube.com/profile/greenshowers-4056496',
141 'id': 'greenshowers-4056496',
144 'playlist_mincount': 155,
147 def _real_extract(self, url):
148 user_id = self._match_id(url)
151 for pagenum in itertools.count(1):
152 request = sanitized_Request(
153 'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum),
155 'Cookie': 'popunder=4',
156 'X-Requested-With': 'XMLHttpRequest',
160 page = self._download_json(
161 request, user_id, 'Downloading videos JSON page %d' % pagenum)
163 html = page.get('html')
167 for video_id in orderedSet([video_id for _, video_id in re.findall(
168 r'data-plid=(["\'])(.+?)\1', html)]):
169 entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key()))
171 page_count = int_or_none(page.get('pageCount'))
172 if not page_count or pagenum == page_count:
175 playlist = self.playlist_result(entries, user_id)
176 playlist['age_limit'] = 18