From 4e067ceabd705201a16b4c92cf4b23f3b990326c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Sun, 13 Jul 2014 10:15:40 +0200 Subject: updated specific configuration for parsing --- inc/3rdparty/site_config/standard/webwereld.nl.txt | 8 ++++++++ 1 file changed, 8 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/webwereld.nl.txt (limited to 'inc/3rdparty/site_config/standard/webwereld.nl.txt') diff --git a/inc/3rdparty/site_config/standard/webwereld.nl.txt b/inc/3rdparty/site_config/standard/webwereld.nl.txt new file mode 100755 index 00000000..40a5aa36 --- /dev/null +++ b/inc/3rdparty/site_config/standard/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 v1.2.3