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/fertigung.de.txt | 23 ++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/fertigung.de.txt (limited to 'inc/3rdparty/site_config/standard/fertigung.de.txt') diff --git a/inc/3rdparty/site_config/standard/fertigung.de.txt b/inc/3rdparty/site_config/standard/fertigung.de.txt new file mode 100755 index 00000000..90145e58 --- /dev/null +++ b/inc/3rdparty/site_config/standard/fertigung.de.txt @@ -0,0 +1,23 @@ +title: //title + +body: //div[@id='content'] + +strip: (//div[@id='content']/h2)[1] + +strip: //h2[contains(., 'mehr News')]/following::* +strip: //h2[contains(., 'mehr News')] + +strip: //div[contains(@class, 'indizar')]/following::* +strip: //div[contains(@class, 'indizar')] + +strip: //h1[contains(@class, 'single')]/preceding::* +strip: //h1[contains(@class, 'single')] + +strip_id_or_class: plista_widget + +prune: no + +next_page_link: //a[contains(., 'Weiter')] + +test_url: http://www.fertigung.de/2013/04/igus-neuer-energiekettenkatalog/ +test_url: http://www.fertigung.de/2013/04/dynamisch-und-hochpraezise/ \ No newline at end of file -- cgit v1.2.3