aboutsummaryrefslogtreecommitdiffhomepage
path: root/inc/3rdparty/site_config/standard/cicero.de.txt
diff options
context:
space:
mode:
Diffstat (limited to 'inc/3rdparty/site_config/standard/cicero.de.txt')
-rw-r--r--inc/3rdparty/site_config/standard/cicero.de.txt33
1 files changed, 33 insertions, 0 deletions
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 @@
1# fforst@...
2
3# Use link to print article for single page view
4single_page_link: //a[@class="print"]
5
6# set body
7tidy: no
8body: //div[@class='artikel-content']
9
10# strip title and subtitle since we got it already
11strip: //div[@class='issue']
12strip: //div[@class='artikel-content']/h2
13
14# some authors are known and have a link, others don't
15author: //a[contains(@href, 'autor?')]
16
17#date
18date: //span[@class='article-date']
19
20# Strip author since we got him
21strip_id_or_class: author
22
23#strip captions
24strip_id_or_class: field-name-field-image-credit
25strip_id_or_class: field-name-field-article-image-subtitle
26
27# remove community functions
28strip: //div[@class='meta']
29strip: //div[@id='comments']
30
31# remove "continue on the next page" text
32strip: //p[text()="[SEITE]"]
33test_url: http://www.cicero.de/weltbuehne/ihre-wut-ist-global-krise-jugend-revolten-aufstaende-zelte/43049 \ No newline at end of file