]> git.immae.eu Git - github/wallabag/wallabag.git/blame - inc/3rdparty/site_config/standard/cicero.de.txt
minimum of control on server side added
[github/wallabag/wallabag.git] / inc / 3rdparty / site_config / standard / cicero.de.txt
CommitLineData
ac4d1142
NL
1# fforst@...\r
2\r
3# Use link to print article for single page view\r
4single_page_link: //a[@class="print"]\r
5\r
6# set body\r
7tidy: no\r
8body: //div[@class='artikel-content']\r
9\r
10# strip title and subtitle since we got it already\r
11strip: //div[@class='issue']\r
12strip: //div[@class='artikel-content']/h2\r
13\r
14# some authors are known and have a link, others don't\r
15author: //a[contains(@href, 'autor?')]\r
16\r
17#date\r
18date: //span[@class='article-date']\r
19\r
20# Strip author since we got him\r
21strip_id_or_class: author\r
22\r
23#strip captions\r
24strip_id_or_class: field-name-field-image-credit\r
25strip_id_or_class: field-name-field-article-image-subtitle\r
26\r
27# remove community functions\r
28strip: //div[@class='meta']\r
29strip: //div[@id='comments']\r
30\r
31# remove "continue on the next page" text\r
32strip: //p[text()="[SEITE]"]
33test_url: http://www.cicero.de/weltbuehne/ihre-wut-ist-global-krise-jugend-revolten-aufstaende-zelte/43049