From 41e3199b3fa8e49b362de214a51fb5ec11936410 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Mon, 13 May 2013 00:52:49 +0200 Subject: Mostly Instapaper changes --- webwereld.nl.txt | 8 ++++++++ 1 file changed, 8 insertions(+) create mode 100644 webwereld.nl.txt (limited to 'webwereld.nl.txt') diff --git a/webwereld.nl.txt b/webwereld.nl.txt new file mode 100644 index 0000000..40a5aa3 --- /dev/null +++ b/webwereld.nl.txt @@ -0,0 +1,8 @@ +strip: //*[@class="paginator"] +body: //*[@id="articleText"] +next_page_link: //a[@class="next"] + +# No author detection +# No publishing date detection +# No author and intro deduplication over multiple pages +test_url: http://webwereld.nl/analyse/111452/de-code-van-dorifel-nader-bekeken.html \ No newline at end of file -- cgit v1.3.1