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 --- .../site_config/standard/handelsblatt.com.txt | 31 ++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/handelsblatt.com.txt (limited to 'inc/3rdparty/site_config/standard/handelsblatt.com.txt') diff --git a/inc/3rdparty/site_config/standard/handelsblatt.com.txt b/inc/3rdparty/site_config/standard/handelsblatt.com.txt new file mode 100755 index 00000000..7d067aa6 --- /dev/null +++ b/inc/3rdparty/site_config/standard/handelsblatt.com.txt @@ -0,0 +1,31 @@ +#Single Page +single_page_link: //li[contains(@class,"hcf-print")]/a + +# Title hcf-headline +title: //span[@class='hcf-headline'] + +# Authors +author: //div[@class="hcf-author"]/a/text() +author: substring-after(//div[@class='hcf-author'], 'von ') + +# Date +date: //div[@class='hcf-article-date'] + +# Body +body: //div[@class='article'] + +# General removements +strip: //div[contains(@class,"hcf-smartbox")] +strip: //div[contains(@class,"hcf-stopper")] +strip: //div[contains(@class,"hcf-img-controls")] +strip: //span[@class='hcf-location-mark'] +strip: //span[@class='hcf-copyright'] +strip: //div[@class='hcf-copyright'] +strip: //div[@class='hcf-origin'] + + + + +# Fix picture captions +wrap_in(small): //div[@class="hcf-caption"] +test_url: http://www.handelsblatt.com/meinung/gastbeitraege/gastkommentar-zum-emissionshandel-kurskorrekturen-fuehren-zum-kentern/8044326.html \ No newline at end of file -- cgit v1.2.3