1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5 import itertools
6
7 from .common import InfoExtractor
8 from ..compat import (
9 compat_urlparse,
10 )
11 from ..utils import (
12 clean_html,
13 get_element_by_class,
14 int_or_none,
15 merge_dicts,
16 url_or_none,
17 urljoin,
18 )
19
20
21 class ThisVidIE(InfoExtractor):
22 _VALID_URL = r'https?://(?:www\.)?thisvid\.com/(?P<type>videos|embed)/(?P<id>[A-Za-z0-9-]+)'
23 _TESTS = [{
24 'url': 'https://thisvid.com/videos/sitting-on-ball-tight-jeans/',
25 'md5': '839becb572995687e11a69dc4358a386',
26 'info_dict': {
27 'id': '3533241',
28 'ext': 'mp4',
29 'title': 'Sitting on ball tight jeans',
30 'description': 'md5:372353bb995883d1b65fddf507489acd',
31 'thumbnail': r're:https?://\w+\.thisvid\.com/(?:[^/]+/)+3533241/preview\.jpg',
32 'uploader_id': '150629',
33 'uploader': 'jeanslevisjeans',
34 'age_limit': 18,
35 }
36 }, {
37 'url': 'https://thisvid.com/embed/3533241/',
38 'md5': '839becb572995687e11a69dc4358a386',
39 'info_dict': {
40 'id': '3533241',
41 'ext': 'mp4',
42 'title': 'Sitting on ball tight jeans',
43 'thumbnail': r're:https?://\w+\.thisvid\.com/(?:[^/]+/)+3533241/preview\.jpg',
44 'uploader_id': '150629',
45 'uploader': 'jeanslevisjeans',
46 'age_limit': 18,
47 }
48 }]
49
50 def _real_extract(self, url):
51 main_id, type_ = re.match(self._VALID_URL, url).group('id', 'type')
52 webpage = self._download_webpage(url, main_id)
53
54 title = self._html_search_regex(
55 r'<title\b[^>]*?>(?:Video:\s+)?(.+?)(?:\s+-\s+ThisVid(?:\.com| tube))?</title>',
56 webpage, 'title')
57
58 if type_ == 'embed':
59 # look for more metadata
60 video_alt_url = url_or_none(self._search_regex(
61 r'''video_alt_url\s*:\s+'(%s/)',''' % (self._VALID_URL, ),
62 webpage, 'video_alt_url', default=None))
63 if video_alt_url and video_alt_url != url:
64 webpage = self._download_webpage(
65 video_alt_url, main_id,
66 note='Redirecting embed to main page', fatal=False) or webpage
67
68 video_holder = get_element_by_class('video-holder', webpage) or ''
69 if '>This video is a private video' in video_holder:
70 self.raise_login_required(
71 (clean_html(video_holder) or 'Private video').split('\n', 1)[0])
72
73 uploader = self._html_search_regex(
74 r'''(?s)<span\b[^>]*>Added by:\s*</span><a\b[^>]+\bclass\s*=\s*["']author\b[^>]+\bhref\s*=\s*["']https://thisvid\.com/members/([0-9]+/.{3,}?)\s*</a>''',
75 webpage, 'uploader', default='')
76 uploader = re.split(r'''/["'][^>]*>\s*''', uploader)
77 if len(uploader) == 2:
78 # id must be non-empty, uploader could be ''
79 uploader_id, uploader = uploader
80 uploader = uploader or None
81 else:
82 uploader_id = uploader = None
83
84 return merge_dicts({
85 '_type': 'url_transparent',
86 'title': title,
87 'age_limit': 18,
88 'uploader': uploader,
89 'uploader_id': uploader_id,
90 }, self.url_result(url, ie='Generic'))
91
92
93 class ThisVidMemberIE(InfoExtractor):
94 _VALID_URL = r'https?://thisvid\.com/members/(?P<id>\d+)'
95 _TESTS = [{
96 'url': 'https://thisvid.com/members/2140501/',
97 'info_dict': {
98 'id': '2140501',
99 'title': 'Rafflesia\'s Profile',
100 },
101 'playlist_mincount': 16,
102 }, {
103 'url': 'https://thisvid.com/members/2140501/favourite_videos/',
104 'info_dict': {
105 'id': '2140501',
106 'title': 'Rafflesia\'s Favourite Videos',
107 },
108 'playlist_mincount': 15,
109 }, {
110 'url': 'https://thisvid.com/members/636468/public_videos/',
111 'info_dict': {
112 'id': '636468',
113 'title': 'Happymouth\'s Public Videos',
114 },
115 'playlist_mincount': 196,
116 },
117 ]
118
119 def _urls(self, html):
120 for m in re.finditer(r'''<a\b[^>]+\bhref\s*=\s*["'](?P<url>%s\b)[^>]+>''' % (ThisVidIE._VALID_URL, ), html):
121 yield m.group('url')
122
123 def _real_extract(self, url):
124 pl_id = self._match_id(url)
125 webpage = self._download_webpage(url, pl_id)
126
127 title = re.split(
128 r'(?i)\s*\|\s*ThisVid\.com\s*$',
129 self._og_search_title(webpage, default=None) or self._html_search_regex(r'(?s)<title\b[^>]*>(.+?)</title', webpage, 'title', fatal=False) or '', 1)[0] or None
130
131 def entries(page_url, html=None):
132 for page in itertools.count(1):
133 if not html:
134 html = self._download_webpage(
135 page_url, pl_id, note='Downloading page %d' % (page, ),
136 fatal=False) or ''
137 for u in self._urls(html):
138 yield u
139 next_page = get_element_by_class('pagination-next', html) or ''
140 if next_page:
141 # member list page
142 next_page = urljoin(url, self._search_regex(
143 r'''<a\b[^>]+\bhref\s*=\s*("|')(?P<url>(?!#)(?:(?!\1).)+)''',
144 next_page, 'next page link', group='url', default=None))
145 # in case a member page should have pagination-next with empty link, not just `else:`
146 if next_page is None:
147 # playlist page
148 parsed_url = compat_urlparse.urlparse(page_url)
149 base_path, num = parsed_url.path.rsplit('/', 1)
150 num = int_or_none(num)
151 if num is None:
152 base_path, num = parsed_url.path.rstrip('/'), 1
153 parsed_url = parsed_url._replace(path=base_path + ('/%d' % (num + 1, )))
154 next_page = compat_urlparse.urlunparse(parsed_url)
155 if page_url == next_page:
156 next_page = None
157 if not next_page:
158 break
159 page_url, html = next_page, None
160
161 return self.playlist_from_matches(
162 entries(url, webpage), playlist_id=pl_id, playlist_title=title, ie='ThisVid')
163
164
165 class ThisVidPlaylistIE(ThisVidMemberIE):
166 _VALID_URL = r'https?://thisvid\.com/playlist/(?P<id>\d+)/video/(?P<video_id>[A-Za-z0-9-]+)'
167 _TESTS = [{
168 'url': 'https://thisvid.com/playlist/6615/video/big-italian-booty-28/',
169 'info_dict': {
170 'id': '6615',
171 'title': 'Underwear Stuff',
172 },
173 'playlist_mincount': 200,
174 }, {
175 'url': 'https://thisvid.com/playlist/6615/video/big-italian-booty-28/',
176 'info_dict': {
177 'id': '1072387',
178 'ext': 'mp4',
179 'title': 'Big Italian Booty 28',
180 'description': 'md5:1bccf7b13765e18fb27bf764dba7ede2',
181 'uploader_id': '367912',
182 'uploader': 'Jcmusclefun',
183 'age_limit': 18,
184 },
185 'params': {
186 'noplaylist': True,
187 },
188 }]
189
190 def _get_video_url(self, pl_url):
191 video_id = re.match(self._VALID_URL, pl_url).group('video_id')
192 return urljoin(pl_url, '/videos/%s/' % (video_id, ))
193
194 def _urls(self, html):
195 for m in re.finditer(r'''<a\b[^>]+\bhref\s*=\s*["'](?P<url>%s\b)[^>]+>''' % (self._VALID_URL, ), html):
196 yield self._get_video_url(m.group('url'))
197
198 def _real_extract(self, url):
199 pl_id = self._match_id(url)
200
201 if self._downloader.params.get('noplaylist'):
202 self.to_screen('Downloading just the featured video because of --no-playlist')
203 return self.url_result(self._get_video_url(url), 'ThisVid')
204
205 self.to_screen(
206 'Downloading playlist %s - add --no-playlist to download just the featured video' % (pl_id, ))
207 result = super(ThisVidPlaylistIE, self)._real_extract(url)
208
209 # rework title returned as `the title - the title`
210 title = result['title']
211 t_len = len(title)
212 if t_len > 5 and t_len % 2 != 0:
213 t_len = t_len // 2
214 if title[t_len] == '-':
215 title = [t.strip() for t in (title[:t_len], title[t_len + 1:])]
216 if title[0] and title[0] == title[1]:
217 result['title'] = title[0]
218 return result
|