From ac4d114214d820b20e18518a2dbc809337e39043 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Fri, 6 Dec 2013 10:13:03 +0100 Subject: [add] new specific configuration files --- inc/3rdparty/site_config/standard/cicero.de.txt | 33 +++++++++++++++++++++++++ 1 file changed, 33 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/cicero.de.txt (limited to 'inc/3rdparty/site_config/standard/cicero.de.txt') diff --git a/inc/3rdparty/site_config/standard/cicero.de.txt b/inc/3rdparty/site_config/standard/cicero.de.txt new file mode 100644 index 00000000..b9f9a12b --- /dev/null +++ b/inc/3rdparty/site_config/standard/cicero.de.txt @@ -0,0 +1,33 @@ +# fforst@... + +# Use link to print article for single page view +single_page_link: //a[@class="print"] + +# set body +tidy: no +body: //div[@class='artikel-content'] + +# strip title and subtitle since we got it already +strip: //div[@class='issue'] +strip: //div[@class='artikel-content']/h2 + +# some authors are known and have a link, others don't +author: //a[contains(@href, 'autor?')] + +#date +date: //span[@class='article-date'] + +# Strip author since we got him +strip_id_or_class: author + +#strip captions +strip_id_or_class: field-name-field-image-credit +strip_id_or_class: field-name-field-article-image-subtitle + +# remove community functions +strip: //div[@class='meta'] +strip: //div[@id='comments'] + +# remove "continue on the next page" text +strip: //p[text()="[SEITE]"] +test_url: http://www.cicero.de/weltbuehne/ihre-wut-ist-global-krise-jugend-revolten-aufstaende-zelte/43049 \ No newline at end of file -- cgit v1.2.3