From 82099bd04f96d1dfd8d5ac2f93f8b854e14bc500 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Fri, 29 May 2015 15:14:27 +0200 Subject: Bypass cookie walls (parool.nl and volkskrant.nl) --- parool.nl.txt | 7 +++++++ volkskrant.nl.txt | 15 +++++++++++++++ 2 files changed, 22 insertions(+) create mode 100644 parool.nl.txt create mode 100644 volkskrant.nl.txt diff --git a/parool.nl.txt b/parool.nl.txt new file mode 100644 index 0000000..2ceef94 --- /dev/null +++ b/parool.nl.txt @@ -0,0 +1,7 @@ +#bypass cookie check +single_page_link: //a[contains(@href, '/acceptCookieCheck.do?url=')] + +test_url: http://www.parool.nl/parool/nl/4/AMSTERDAM/article/detail/4042734/2015/05/29/MRSA-bacterie-niet-verder-verspreid-in-Bijlmerbajes.dhtml +test_contains: De twee gevangenen die + +test_url: http://www.parool.nl/amsterdam/rss.xml \ No newline at end of file diff --git a/volkskrant.nl.txt b/volkskrant.nl.txt new file mode 100644 index 0000000..c277034 --- /dev/null +++ b/volkskrant.nl.txt @@ -0,0 +1,15 @@ +#bypass cookie check +single_page_link: //a[contains(@href, '/cookiewall/accept.do?')] + +title: //h1[@itemprop="headline"] +body: //figure[contains(@class, 'article__top-image')] | //div[@itemprop="articleBody"] + +strip: //div[contains(@class, 'media-container') and contains(@class, 'pull-right')] + +tidy: no +prune: no + +test_url: http://www.volkskrant.nl/sport/dossier-wereldvoetbalbond-fifa-wankelt~a4042695/ +test_contains: De belangrijkste spil in het + +test_url: http://www.volkskrant.nl/nieuws/rss.xml \ No newline at end of file -- cgit v1.3.1