X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fpornhub.py;h=3a474c17970bbd087de187bf6059e9900551f61f;hb=77d95677b7ab4a9840ef142b14627b07a9a31120;hp=281a4f05e4600829a42bce31de8271f588aeae46;hpb=f66df20ccd1092e8b1ac4c22982238a2e9fcb657;p=youtube-dl diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 281a4f05e..3a474c179 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -4,36 +4,53 @@ from __future__ import unicode_literals import functools import itertools import operator -# import os import re from .common import InfoExtractor from ..compat import ( compat_HTTPError, - # compat_urllib_parse_unquote, - # compat_urllib_parse_unquote_plus, - # compat_urllib_parse_urlparse, + compat_str, + compat_urllib_request, ) +from .openload import PhantomJSwrapper from ..utils import ( ExtractorError, int_or_none, - js_to_json, orderedSet, - # sanitized_Request, remove_quotes, str_to_int, + url_or_none, ) -# from ..aes import ( -# aes_decrypt_text -# ) -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?:// (?: - (?:[a-z]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| + (?:[^/]+\.)?(?P