X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fpornhub.py;h=4118ee9560e03d2fa1eea171766ef4893e274aa5;hb=8c778adc39fbaa79a6e885532b933364c9952817;hp=6d1ffe6761300e07101ad1326e56bc7e84fd526c;hpb=75d06db9fcddb184f1011c4aad8a6e02dda0f314;p=youtube-dl
diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
index 6d1ffe676..4118ee956 100644
--- a/youtube_dl/extractor/pornhub.py
+++ b/youtube_dl/extractor/pornhub.py
@@ -8,6 +8,7 @@ from ..utils import (
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
+ str_to_int,
)
from ..aes import (
aes_decrypt_text
@@ -27,6 +28,12 @@ class PornHubIE(InfoExtractor):
}
}
+ def _extract_count(self, pattern, webpage, name):
+ count = self._html_search_regex(pattern, webpage, '%s count' % name, fatal=False)
+ if count:
+ count = str_to_int(count)
+ return count
+
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
@@ -37,14 +44,22 @@ class PornHubIE(InfoExtractor):
webpage = self._download_webpage(req, video_id)
video_title = self._html_search_regex(r'
]+>([^<]+)', webpage, 'title')
- video_uploader = self._html_search_regex(r'From: (?:\s|<[^>]*>)*(.+?)<', webpage, 'uploader', fatal=False)
+ video_uploader = self._html_search_regex(
+ r'(?s)From: .+?<(?:a href="/users/|([\d,\.]+) views', webpage, 'view')
+ like_count = self._extract_count(r'([\d,\.]+)', webpage, 'like')
+ dislike_count = self._extract_count(r'([\d,\.]+)', webpage, 'dislike')
+ comment_count = self._extract_count(
+ r'All comments \(', 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 = compat_urllib_request.unquote(self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password').replace('+', ' '))
+ password = compat_urllib_parse.unquote_plus(self._html_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 = []
@@ -77,6 +92,10 @@ class PornHubIE(InfoExtractor):
'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,
}