+from __future__ import unicode_literals
+
import os
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
+ compat_urllib_parse,
compat_urllib_parse_urlparse,
compat_urllib_request,
- compat_urllib_parse,
+)
+from ..utils import (
+ ExtractorError,
+ str_to_int,
)
from ..aes import (
aes_decrypt_text
)
+
class PornHubIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9]+))'
+ _VALID_URL = r'https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)'
_TEST = {
- u'url': u'http://www.pornhub.com/view_video.php?viewkey=648719015',
- u'file': u'648719015.mp4',
- u'md5': u'882f488fa1f0026f023f33576004a2ed',
- u'info_dict': {
- u"uploader": u"BABES-COM",
- u"title": u"Seductive Indian beauty strips down and fingers her pink pussy",
- u"age_limit": 18
+ 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
+ 'md5': '882f488fa1f0026f023f33576004a2ed',
+ 'info_dict': {
+ 'id': '648719015',
+ 'ext': 'mp4',
+ "uploader": "Babes",
+ "title": "Seductive Indian beauty strips down and fingers her pink pussy",
+ "age_limit": 18
}
}
+ def _extract_count(self, pattern, webpage, name):
+ return str_to_int(self._search_regex(
+ pattern, webpage, '%s count' % name, fatal=False))
+
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('videoid')
- url = 'http://www.' + mobj.group('url')
+ video_id = self._match_id(url)
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
- video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, u'title')
- video_uploader = self._html_search_regex(r'<b>From: </b>(?:\s|<[^>]*>)*(.+?)<', webpage, u'uploader', fatal=False)
- thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, u'thumbnail', fatal=False)
+ error_msg = self._html_search_regex(
+ r'(?s)<div class="userMessageSection[^"]*".*?>(.*?)</div>',
+ webpage, 'error message', default=None)
+ if error_msg:
+ error_msg = re.sub(r'\s+', ' ', error_msg)
+ raise ExtractorError(
+ 'PornHub said: %s' % error_msg,
+ expected=True, video_id=video_id)
+
+ video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
+ video_uploader = self._html_search_regex(
+ r'(?s)From: .+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<',
+ webpage, 'uploader', fatal=False)
+ thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
if thumbnail:
thumbnail = compat_urllib_parse.unquote(thumbnail)
- video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
+ view_count = self._extract_count(
+ r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
+ like_count = self._extract_count(
+ r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
+ dislike_count = self._extract_count(
+ r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
+ comment_count = self._extract_count(
+ r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
+
+ video_urls = list(map(compat_urllib_parse.unquote, re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
if webpage.find('"encrypted":true') != -1:
- password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password').replace('+', ' ')
+ password = compat_urllib_parse.unquote_plus(
+ self._search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
formats = []
extension = os.path.splitext(path)[1][1:]
format = path.split('/')[5].split('_')[:2]
format = "-".join(format)
+
+ m = re.match(r'^(?P<height>[0-9]+)P-(?P<tbr>[0-9]+)K$', format)
+ if m is None:
+ height = None
+ tbr = None
+ else:
+ height = int(m.group('height'))
+ tbr = int(m.group('tbr'))
+
formats.append({
'url': video_url,
'ext': extension,
'format': format,
'format_id': format,
+ 'tbr': tbr,
+ 'height': height,
})
- formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-'))))
+ self._sort_formats(formats)
return {
'id': video_id,
'uploader': video_uploader,
'title': video_title,
'thumbnail': thumbnail,
+ 'view_count': view_count,
+ 'like_count': like_count,
+ 'dislike_count': dislike_count,
+ 'comment_count': comment_count,
'formats': formats,
'age_limit': 18,
}
+
+
+class PornHubPlaylistIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)'
+ _TESTS = [{
+ 'url': 'http://www.pornhub.com/playlist/6201671',
+ 'info_dict': {
+ 'id': '6201671',
+ 'title': 'P0p4',
+ },
+ 'playlist_mincount': 35,
+ }]
+
+ def _real_extract(self, url):
+ playlist_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, playlist_id)
+
+ entries = [
+ self.url_result('http://www.pornhub.com/%s' % video_url, 'PornHub')
+ for video_url in set(re.findall('href="/?(view_video\.php\?viewkey=\d+[^"]*)"', webpage))
+ ]
+
+ playlist = self._parse_json(
+ self._search_regex(
+ r'playlistObject\s*=\s*({.+?});', webpage, 'playlist'),
+ playlist_id)
+
+ return self.playlist_result(
+ entries, playlist_id, playlist.get('title'), playlist.get('description'))
Rapsys Git / youtubedl / blobdiff