diff options
| -rw-r--r-- | spiegel.de.txt | 9 |
1 files changed, 8 insertions, 1 deletions
diff --git a/spiegel.de.txt b/spiegel.de.txt index 84809eb..f9040f2 100644 --- a/spiegel.de.txt +++ b/spiegel.de.txt @@ -18,6 +18,7 @@ tidy: no body: //div[@id="spArticleContent"] # body in default view body: //div[@id="spArticleSection"] +body: //div[contains(@class, 'column-both')] | //div[contains(@class, 'article-section')] # body in "Fotostrecke" body: //div[@id="spBigaContent"] @@ -28,6 +29,8 @@ strip: //div[@id="spArticleContent"]/h3 # set date in "Fotostrecke" date: //div[@id="spBigaDatum"] +# title in default view +title: //h2[contains(@class, 'article-title')] #set title in single page view title: //div[@id='spArticleContent']/h2 # strip title @@ -75,7 +78,11 @@ strip: //div[@class='article-copyright'] # Use link to print article for single page view single_page_link: //a[contains(@href, '-druck')] +if_page_contains: //div[contains(@class, 'multi-pager-control')] # use next link in "Fotostrecke" next_page_link: //a[@class='spBigaControlForw'] -test_url: http://www.spiegel.de/politik/deutschland/0,1518,787602,00.html
\ No newline at end of file +test_url: http://www.spiegel.de/politik/deutschland/0,1518,787602,00.html + +# multipage article +test_url: http://www.spiegel.de/spiegel/a-710880.html
\ No newline at end of file |