]>
Commit | Line | Data |
---|---|---|
6c376029 | 1 | # coding: utf-8 |
9933b574 PH |
2 | from __future__ import unicode_literals |
3 | ||
21fbf0f9 | 4 | import functools |
34541395 | 5 | import itertools |
21fbf0f9 | 6 | import operator |
9a372f14 | 7 | # import os |
125cfd78 | 8 | import re |
9 | ||
10 | from .common import InfoExtractor | |
1cc79574 | 11 | from ..compat import ( |
34541395 | 12 | compat_HTTPError, |
9a372f14 S |
13 | # compat_urllib_parse_unquote, |
14 | # compat_urllib_parse_unquote_plus, | |
15 | # compat_urllib_parse_urlparse, | |
1cc79574 PH |
16 | ) |
17 | from ..utils import ( | |
50789175 | 18 | ExtractorError, |
ed8648a3 | 19 | int_or_none, |
6bb05b32 | 20 | js_to_json, |
8f9a477e | 21 | orderedSet, |
9a372f14 | 22 | # sanitized_Request, |
e1e35d1a | 23 | remove_quotes, |
0320ddc1 | 24 | str_to_int, |
125cfd78 | 25 | ) |
9a372f14 S |
26 | # from ..aes import ( |
27 | # aes_decrypt_text | |
28 | # ) | |
125cfd78 | 29 | |
9933b574 | 30 | |
125cfd78 | 31 | class PornHubIE(InfoExtractor): |
bc4b2d75 S |
32 | IE_DESC = 'PornHub and Thumbzilla' |
33 | _VALID_URL = r'''(?x) | |
34 | https?:// | |
35 | (?: | |
a99cc4ca | 36 | (?:[a-z]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| |
bc4b2d75 S |
37 | (?:www\.)?thumbzilla\.com/video/ |
38 | ) | |
b52c9ef1 | 39 | (?P<id>[\da-z]+) |
bc4b2d75 | 40 | ''' |
360075e2 | 41 | _TESTS = [{ |
9933b574 | 42 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015', |
ed8648a3 | 43 | 'md5': '1e19b41231a02eba417839222ac9d58e', |
9933b574 | 44 | 'info_dict': { |
249efaf4 PH |
45 | 'id': '648719015', |
46 | 'ext': 'mp4', | |
611c1dd9 | 47 | 'title': 'Seductive Indian beauty strips down and fingers her pink pussy', |
ed8648a3 S |
48 | 'uploader': 'Babes', |
49 | 'duration': 361, | |
50 | 'view_count': int, | |
51 | 'like_count': int, | |
52 | 'dislike_count': int, | |
53 | 'comment_count': int, | |
54 | 'age_limit': 18, | |
6bb05b32 YCH |
55 | 'tags': list, |
56 | 'categories': list, | |
6c376029 S |
57 | }, |
58 | }, { | |
59 | # non-ASCII title | |
60 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002', | |
61 | 'info_dict': { | |
62 | 'id': '1331683002', | |
63 | 'ext': 'mp4', | |
64 | 'title': '重庆婷婷女王足交', | |
65 | 'uploader': 'cj397186295', | |
66 | 'duration': 1753, | |
67 | 'view_count': int, | |
68 | 'like_count': int, | |
69 | 'dislike_count': int, | |
70 | 'comment_count': int, | |
71 | 'age_limit': 18, | |
6bb05b32 YCH |
72 | 'tags': list, |
73 | 'categories': list, | |
6c376029 S |
74 | }, |
75 | 'params': { | |
76 | 'skip_download': True, | |
77 | }, | |
360075e2 S |
78 | }, { |
79 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d', | |
80 | 'only_matching': True, | |
272e4db5 | 81 | }, { |
eaaaaec0 | 82 | # removed at the request of cam4.com |
272e4db5 S |
83 | 'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862', |
84 | 'only_matching': True, | |
eaaaaec0 S |
85 | }, { |
86 | # removed at the request of the copyright owner | |
87 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=788152859', | |
88 | 'only_matching': True, | |
89 | }, { | |
90 | # removed by uploader | |
91 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph572716d15a111', | |
92 | 'only_matching': True, | |
195f0845 S |
93 | }, { |
94 | # private video | |
95 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7', | |
96 | 'only_matching': True, | |
bc4b2d75 S |
97 | }, { |
98 | 'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex', | |
99 | 'only_matching': True, | |
a99cc4ca S |
100 | }, { |
101 | 'url': 'http://www.pornhub.com/video/show?viewkey=648719015', | |
102 | 'only_matching': True, | |
360075e2 | 103 | }] |
125cfd78 | 104 | |
b52c9ef1 S |
105 | @staticmethod |
106 | def _extract_urls(webpage): | |
107 | return re.findall( | |
108 | r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)', | |
109 | webpage) | |
65d161c4 | 110 | |
0320ddc1 | 111 | def _extract_count(self, pattern, webpage, name): |
7700207e S |
112 | return str_to_int(self._search_regex( |
113 | pattern, webpage, '%s count' % name, fatal=False)) | |
0320ddc1 | 114 | |
125cfd78 | 115 | def _real_extract(self, url): |
249efaf4 | 116 | video_id = self._match_id(url) |
125cfd78 | 117 | |
9a372f14 S |
118 | def dl_webpage(platform): |
119 | return self._download_webpage( | |
120 | 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id, | |
121 | video_id, headers={ | |
122 | 'Cookie': 'age_verified=1; platform=%s' % platform, | |
123 | }) | |
124 | ||
125 | webpage = dl_webpage('pc') | |
125cfd78 | 126 | |
50789175 | 127 | error_msg = self._html_search_regex( |
add7d2a0 | 128 | r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>', |
3cb3b600 | 129 | webpage, 'error message', default=None, group='error') |
50789175 PH |
130 | if error_msg: |
131 | error_msg = re.sub(r'\s+', ' ', error_msg) | |
132 | raise ExtractorError( | |
133 | 'PornHub said: %s' % error_msg, | |
134 | expected=True, video_id=video_id) | |
135 | ||
9a372f14 S |
136 | tv_webpage = dl_webpage('tv') |
137 | ||
e1e35d1a S |
138 | assignments = self._search_regex( |
139 | r'(var.+?mediastring.+?)</script>', tv_webpage, | |
140 | 'encoded url').split(';') | |
141 | ||
21fbf0f9 T |
142 | js_vars = {} |
143 | ||
144 | def parse_js_value(inp): | |
e1e35d1a S |
145 | inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp) |
146 | if '+' in inp: | |
147 | inps = inp.split('+') | |
148 | return functools.reduce( | |
149 | operator.concat, map(parse_js_value, inps)) | |
21fbf0f9 T |
150 | inp = inp.strip() |
151 | if inp in js_vars: | |
152 | return js_vars[inp] | |
e1e35d1a | 153 | return remove_quotes(inp) |
21fbf0f9 T |
154 | |
155 | for assn in assignments: | |
156 | assn = assn.strip() | |
e1e35d1a | 157 | if not assn: |
21fbf0f9 | 158 | continue |
e1e35d1a S |
159 | assn = re.sub(r'var\s+', '', assn) |
160 | vname, value = assn.split('=', 1) | |
21fbf0f9 T |
161 | js_vars[vname] = parse_js_value(value) |
162 | ||
e1e35d1a | 163 | video_url = js_vars['mediastring'] |
9a372f14 S |
164 | |
165 | title = self._search_regex( | |
166 | r'<h1>([^>]+)</h1>', tv_webpage, 'title', default=None) | |
167 | ||
6c376029 S |
168 | # video_title from flashvars contains whitespace instead of non-ASCII (see |
169 | # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying | |
170 | # on that anymore. | |
9a372f14 | 171 | title = title or self._html_search_meta( |
6c376029 S |
172 | 'twitter:title', webpage, default=None) or self._search_regex( |
173 | (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)', | |
174 | r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1', | |
175 | r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'), | |
176 | webpage, 'title', group='title') | |
177 | ||
ed8648a3 S |
178 | flashvars = self._parse_json( |
179 | self._search_regex( | |
03442072 | 180 | r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'), |
ed8648a3 S |
181 | video_id) |
182 | if flashvars: | |
ed8648a3 S |
183 | thumbnail = flashvars.get('image_url') |
184 | duration = int_or_none(flashvars.get('video_duration')) | |
185 | else: | |
6c376029 | 186 | title, thumbnail, duration = [None] * 3 |
ed8648a3 | 187 | |
0320ddc1 | 188 | video_uploader = self._html_search_regex( |
8fc642eb | 189 | r'(?s)From: .+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<', |
0320ddc1 | 190 | webpage, 'uploader', fatal=False) |
125cfd78 | 191 | |
7700207e S |
192 | view_count = self._extract_count( |
193 | r'<span class="count">([\d,\.]+)</span> views', webpage, 'view') | |
194 | like_count = self._extract_count( | |
195 | r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like') | |
196 | dislike_count = self._extract_count( | |
197 | r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike') | |
0320ddc1 | 198 | comment_count = self._extract_count( |
7700207e | 199 | r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment') |
0320ddc1 | 200 | |
6bb05b32 YCH |
201 | page_params = self._parse_json(self._search_regex( |
202 | r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})', | |
203 | webpage, 'page parameters', group='data', default='{}'), | |
204 | video_id, transform_source=js_to_json, fatal=False) | |
205 | tags = categories = None | |
206 | if page_params: | |
207 | tags = page_params.get('tags', '').split(',') | |
208 | categories = page_params.get('categories', '').split(',') | |
209 | ||
125cfd78 | 210 | return { |
211 | 'id': video_id, | |
9a372f14 | 212 | 'url': video_url, |
125cfd78 | 213 | 'uploader': video_uploader, |
6c376029 | 214 | 'title': title, |
125cfd78 | 215 | 'thumbnail': thumbnail, |
ed8648a3 | 216 | 'duration': duration, |
0320ddc1 S |
217 | 'view_count': view_count, |
218 | 'like_count': like_count, | |
219 | 'dislike_count': dislike_count, | |
220 | 'comment_count': comment_count, | |
9a372f14 | 221 | # 'formats': formats, |
750e9833 | 222 | 'age_limit': 18, |
6bb05b32 YCH |
223 | 'tags': tags, |
224 | 'categories': categories, | |
125cfd78 | 225 | } |
e66e1a00 S |
226 | |
227 | ||
40e146aa S |
228 | class PornHubPlaylistBaseIE(InfoExtractor): |
229 | def _extract_entries(self, webpage): | |
230 | return [ | |
3a23bae9 S |
231 | self.url_result( |
232 | 'http://www.pornhub.com/%s' % video_url, | |
233 | PornHubIE.ie_key(), video_title=title) | |
234 | for video_url, title in orderedSet(re.findall( | |
235 | r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"', | |
236 | webpage)) | |
40e146aa | 237 | ] |
e66e1a00 S |
238 | |
239 | def _real_extract(self, url): | |
240 | playlist_id = self._match_id(url) | |
241 | ||
242 | webpage = self._download_webpage(url, playlist_id) | |
243 | ||
96d315c2 S |
244 | # Only process container div with main playlist content skipping |
245 | # drop-down menu that uses similar pattern for videos (see | |
246 | # https://github.com/rg3/youtube-dl/issues/11594). | |
247 | container = self._search_regex( | |
248 | r'(?s)(<div[^>]+class=["\']container.+)', webpage, | |
249 | 'container', default=webpage) | |
250 | ||
251 | entries = self._extract_entries(container) | |
e66e1a00 S |
252 | |
253 | playlist = self._parse_json( | |
254 | self._search_regex( | |
cd138d8b S |
255 | r'(?:playlistObject|PLAYLIST_VIEW)\s*=\s*({.+?});', webpage, |
256 | 'playlist', default='{}'), | |
257 | playlist_id, fatal=False) | |
258 | title = playlist.get('title') or self._search_regex( | |
259 | r'>Videos\s+in\s+(.+?)\s+[Pp]laylist<', webpage, 'title', fatal=False) | |
e66e1a00 S |
260 | |
261 | return self.playlist_result( | |
cd138d8b | 262 | entries, playlist_id, title, playlist.get('description')) |
40e146aa S |
263 | |
264 | ||
265 | class PornHubPlaylistIE(PornHubPlaylistBaseIE): | |
266 | _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)' | |
267 | _TESTS = [{ | |
96d315c2 | 268 | 'url': 'http://www.pornhub.com/playlist/4667351', |
40e146aa | 269 | 'info_dict': { |
96d315c2 S |
270 | 'id': '4667351', |
271 | 'title': 'Nataly Hot', | |
40e146aa | 272 | }, |
96d315c2 | 273 | 'playlist_mincount': 2, |
40e146aa S |
274 | }] |
275 | ||
276 | ||
277 | class PornHubUserVideosIE(PornHubPlaylistBaseIE): | |
278 | _VALID_URL = r'https?://(?:www\.)?pornhub\.com/users/(?P<id>[^/]+)/videos' | |
279 | _TESTS = [{ | |
34541395 | 280 | 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public', |
40e146aa | 281 | 'info_dict': { |
34541395 | 282 | 'id': 'zoe_ph', |
40e146aa | 283 | }, |
34541395 S |
284 | 'playlist_mincount': 171, |
285 | }, { | |
286 | 'url': 'http://www.pornhub.com/users/rushandlia/videos', | |
287 | 'only_matching': True, | |
40e146aa S |
288 | }] |
289 | ||
290 | def _real_extract(self, url): | |
291 | user_id = self._match_id(url) | |
292 | ||
34541395 S |
293 | entries = [] |
294 | for page_num in itertools.count(1): | |
295 | try: | |
296 | webpage = self._download_webpage( | |
297 | url, user_id, 'Downloading page %d' % page_num, | |
298 | query={'page': page_num}) | |
299 | except ExtractorError as e: | |
300 | if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: | |
301 | break | |
9edcdac9 | 302 | raise |
34541395 S |
303 | page_entries = self._extract_entries(webpage) |
304 | if not page_entries: | |
305 | break | |
306 | entries.extend(page_entries) | |
307 | ||
308 | return self.playlist_result(entries, user_id) |