2 from __future__
import unicode_literals
10 from .common
import InfoExtractor
11 from ..compat
import (
13 # compat_urllib_parse_unquote,
14 # compat_urllib_parse_unquote_plus,
15 # compat_urllib_parse_urlparse,
31 class PornHubIE(InfoExtractor
):
32 IE_DESC
= 'PornHub and Thumbzilla'
36 (?:[a-z]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
37 (?:www\.)?thumbzilla\.com/video/
42 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
43 'md5': '1e19b41231a02eba417839222ac9d58e',
47 'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
60 'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002',
65 'uploader': 'cj397186295',
76 'skip_download': True,
79 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
80 'only_matching': True,
82 # removed at the request of cam4.com
83 'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
84 'only_matching': True,
86 # removed at the request of the copyright owner
87 'url': 'http://www.pornhub.com/view_video.php?viewkey=788152859',
88 'only_matching': True,
91 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph572716d15a111',
92 'only_matching': True,
95 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7',
96 'only_matching': True,
98 'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex',
99 'only_matching': True,
101 'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
102 'only_matching': True,
106 def _extract_urls(webpage
):
108 r
'<iframe[^>]+?src=["\'](?P
<url
>(?
:https?
:)?
//(?
:www\
.)?pornhub\
.com
/embed
/[\da
-z
]+)',
111 def _extract_count(self, pattern, webpage, name):
112 return str_to_int(self._search_regex(
113 pattern, webpage, '%s count
' % name, fatal=False))
115 def _real_extract(self, url):
116 video_id = self._match_id(url)
118 def dl_webpage(platform):
119 return self._download_webpage(
120 'http
://www
.pornhub
.com
/view_video
.php?viewkey
=%s' % video_id,
122 'Cookie
': 'age_verified
=1; platform
=%s' % platform,
125 webpage = dl_webpage('pc
')
127 error_msg = self._html_search_regex(
128 r'(?s
)<div
[^
>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
129 webpage, 'error message', default=None, group='error')
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)
136 tv_webpage = dl_webpage('tv')
138 assignments = self._search_regex(
139 r'(var.+?mediastring.+?)</script>', tv_webpage,
140 'encoded url').split(';')
144 def parse_js_value(inp):
145 inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
147 inps = inp.split('+')
148 return functools.reduce(
149 operator.concat, map(parse_js_value, inps))
153 return remove_quotes(inp)
155 for assn in assignments:
159 assn = re.sub(r'var\s+', '', assn)
160 vname, value = assn.split('=', 1)
161 js_vars[vname] = parse_js_value(value)
163 video_url = js_vars['mediastring']
165 title = self._search_regex(
166 r'<h1>([^>]+)</h1>', tv_webpage, 'title', default=None)
168 # video_title from flashvars contains whitespace instead of non-ASCII (see
169 # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
171 title = title or self._html_search_meta(
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')
178 flashvars = self._parse_json(
180 r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
183 thumbnail = flashvars.get('image_url')
184 duration = int_or_none(flashvars.get('video_duration'))
186 title, thumbnail, duration = [None] * 3
188 video_uploader = self._html_search_regex(
189 r'(?s)From: .+?<(?:a\b[^>]+\bhref=["\']/(?
:user|channel
)s
/|span
\b[^
>]+\bclass
=["\']username)[^>]+>(.+?)<',
190 webpage, 'uploader', fatal=False)
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')
198 comment_count = self._extract_count(
199 r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
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
207 tags = page_params.get('tags', '').split(',')
208 categories = page_params.get('categories', '').split(',')
213 'uploader': video_uploader,
215 'thumbnail': thumbnail,
216 'duration': duration,
217 'view_count': view_count,
218 'like_count': like_count,
219 'dislike_count': dislike_count,
220 'comment_count': comment_count,
221 # 'formats': formats,
224 'categories': categories,
228 class PornHubPlaylistBaseIE(InfoExtractor):
229 def _extract_entries(self, webpage):
230 # Only process container div with main playlist content skipping
231 # drop-down menu that uses similar pattern for videos (see
232 # https://github.com/rg3/youtube-dl/issues/11594).
233 container = self._search_regex(
234 r'(?s)(<div[^>]+class=["\']container
.+)', webpage,
235 'container
', default=webpage)
239 'http
://www
.pornhub
.com
/%s' % video_url,
240 PornHubIE.ie_key(), video_title=title)
241 for video_url, title in orderedSet(re.findall(
242 r'href
="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^
"]+)"',
246 def _real_extract(self, url):
247 playlist_id = self._match_id(url)
249 webpage = self._download_webpage(url, playlist_id)
251 entries = self._extract_entries(webpage)
253 playlist = self._parse_json(
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)
261 return self.playlist_result(
262 entries, playlist_id, title, playlist.get('description
'))
265 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
266 _VALID_URL = r'https?
://(?
:www\
.)?pornhub\
.com
/playlist
/(?P
<id>\d
+)'
268 'url
': 'http
://www
.pornhub
.com
/playlist
/4667351',
271 'title
': 'Nataly Hot
',
273 'playlist_mincount
': 2,
277 class PornHubUserVideosIE(PornHubPlaylistBaseIE):
278 _VALID_URL = r'https?
://(?
:www\
.)?pornhub\
.com
/users
/(?P
<id>[^
/]+)/videos
'
280 'url
': 'http
://www
.pornhub
.com
/users
/zoe_ph
/videos
/public
',
284 'playlist_mincount
': 171,
286 'url
': 'http
://www
.pornhub
.com
/users
/rushandlia
/videos
',
287 'only_matching
': True,
290 def _real_extract(self, url):
291 user_id = self._match_id(url)
294 for page_num in itertools.count(1):
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:
303 page_entries = self._extract_entries(webpage)
306 entries.extend(page_entries)
308 return self.playlist_result(entries, user_id)