[pornhub] Bypass scrape detection (closes #5930)

This commit is contained in:
Sergey M․ 2019-01-23 03:51:29 +07:00
parent 503b604a31
commit 278d061a0c
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 22 additions and 0 deletions

View File

@ -10,7 +10,9 @@ from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_HTTPError, compat_HTTPError,
compat_str, compat_str,
compat_urllib_request,
) )
from .openload import PhantomJSwrapper
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
@ -126,6 +128,26 @@ class PornHubIE(InfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
def _download_webpage_handle(self, *args, **kwargs):
def dl(*args, **kwargs):
return super(PornHubIE, self)._download_webpage_handle(*args, **kwargs)
webpage, urlh = dl(*args, **kwargs)
if any(re.search(p, webpage) for p in (
r'<body\b[^>]+\bonload=["\']go\(\)',
r'document\.cookie\s*=\s*["\']RNKEY=',
r'document\.location\.reload\(true\)')):
url_or_request = args[0]
url = (url_or_request.get_full_url()
if isinstance(url_or_request, compat_urllib_request.Request)
else url_or_request)
phantom = PhantomJSwrapper(self, required_version='2.0')
phantom.get(url, html=webpage)
webpage, urlh = dl(*args, **kwargs)
return webpage, urlh
@staticmethod @staticmethod
def _extract_urls(webpage): def _extract_urls(webpage):
return re.findall( return re.findall(