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/ynet.co.il.txt | 26 ++++++++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/ynet.co.il.txt (limited to 'inc/3rdparty/site_config/standard/ynet.co.il.txt') diff --git a/inc/3rdparty/site_config/standard/ynet.co.il.txt b/inc/3rdparty/site_config/standard/ynet.co.il.txt new file mode 100755 index 00000000..aa86566a --- /dev/null +++ b/inc/3rdparty/site_config/standard/ynet.co.il.txt @@ -0,0 +1,26 @@ +body: //span[@id='article_content' or @class='text16g'] + +# ads +strip: //div[.//div[contains(@id, 'ads.')]] +# related content heading +strip: //p[contains(., 'עוד בערוץ החדשות של ynet:')] +strip: //p[contains(., 'כותרות אחרונות מהעולם בחדשות ynet:')] +strip: //div[contains(., 'אינציקלופדיית ynet:')] +# related content links +strip: //a[@class='bluelink'] +# strip image bullets +strip_image_src: ynet_manual_bullet.png + +prune: no +tidy: no + +# prevent JS issues +find_string: +replace_string: + +test_url: http://www.ynet.co.il/articles/0,7340,L-4354266,00.html +test_url: http://www.ynet.co.il/articles/0,7340,L-4354268,00.html +#feed +test_url: http://www.ynet.co.il/Integration/StoryRss2.xml \ No newline at end of file -- cgit v1.2.3