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/cicero.de.txt | 62 ++++++++++++------------- 1 file changed, 31 insertions(+), 31 deletions(-) mode change 100644 => 100755 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 old mode 100644 new mode 100755 index b9f9a12b..b8913639 --- a/inc/3rdparty/site_config/standard/cicero.de.txt +++ b/inc/3rdparty/site_config/standard/cicero.de.txt @@ -1,33 +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 +# 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