diff options
| author | FiveFilters.org <fivefilters@fivefilters.org> | 2013-02-27 23:43:10 +0100 |
|---|---|---|
| committer | FiveFilters.org <fivefilters@fivefilters.org> | 2013-02-27 23:43:10 +0100 |
| commit | 9a69161c8646f63b4d9fa17c6ac3ab922d625859 (patch) | |
| tree | 62a446347e1279f00383fdd7f9637cfd58a50879 /cicero.de.txt | |
| download | ftr-site-config-9a69161c8646f63b4d9fa17c6ac3ab922d625859.tar.gz ftr-site-config-9a69161c8646f63b4d9fa17c6ac3ab922d625859.zip | |
Initial commit
Diffstat (limited to 'cicero.de.txt')
| -rw-r--r-- | cicero.de.txt | 33 |
1 files changed, 33 insertions, 0 deletions
diff --git a/cicero.de.txt b/cicero.de.txt new file mode 100644 index 0000000..b891363 --- /dev/null +++ b/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 |