From 71a1f61700789fb0d61fc6ad9681b6f0899d2f51 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 23 Jan 2019 04:12:06 +0700 Subject: [PATCH] [pornhub] Apply scrape detection bypass for all extractors --- youtube_dl/extractor/pornhub.py | 46 +++++++++++++++++---------------- 1 file changed, 24 insertions(+), 22 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index f5f3e6593..be93d5d48 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -24,7 +24,29 @@ ) -class PornHubIE(InfoExtractor): +class PornHubBaseIE(InfoExtractor): + def _download_webpage_handle(self, *args, **kwargs): + def dl(*args, **kwargs): + return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs) + + webpage, urlh = dl(*args, **kwargs) + + if any(re.search(p, webpage) for p in ( + r']+\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 + + +class PornHubIE(PornHubBaseIE): IE_DESC = 'PornHub and Thumbzilla' _VALID_URL = r'''(?x) https?:// @@ -128,26 +150,6 @@ class PornHubIE(InfoExtractor): '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']+\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 def _extract_urls(webpage): return re.findall( @@ -329,7 +331,7 @@ def parse_js_value(inp): } -class PornHubPlaylistBaseIE(InfoExtractor): +class PornHubPlaylistBaseIE(PornHubBaseIE): def _extract_entries(self, webpage, host): # Only process container div with main playlist content skipping # drop-down menu that uses similar pattern for videos (see