diff options
Diffstat (limited to 'heise.de.txt')
| -rwxr-xr-x | heise.de.txt | 13 |
1 files changed, 12 insertions, 1 deletions
diff --git a/heise.de.txt b/heise.de.txt index 9433104..2c33208 100755 --- a/heise.de.txt +++ b/heise.de.txt @@ -11,10 +11,20 @@ body: //article | //div[@class='meldung_wrapper'] # General cleanup strip: //time +strip: //header strip: //h4[@class='author'] +strip: //div[@class='gallery compact']/h3 +strip: //div[@class='gallery compact']/figcaption strip: //p[@class='news_datum'] strip: //p[@class='artikel_datum'] +strip: //p[@class='news_navi'] +strip: //p[@class='printversion'] strip: //a[contains(@href, 'mailto')] +strip: //div[@class='gallery compact']/h2 +strip: //p[@class='themen_foren'] +strip: //style +strip: //span[@class='source'] +#strip: //div[@class='gallery compact']/figcaption strip_id_or_class: comments strip_id_or_class: ISI_IGNORE strip_id_or_class: clear @@ -23,6 +33,7 @@ strip_id_or_class: linkurl_grossbild strip_id_or_class: image-num strip_id_or_class: heisebox_right strip_id_or_class: dossier +strip_id_or_class: latest_posting_snippet # Strip Ads strip_id_or_class: ad_ @@ -30,7 +41,7 @@ strip_id_or_class: ad_ # Some optimizations replace_string(<h5>): <h2> replace_string(</h5>): </h2> -replace_string(<span class="bild_rechts"): <p +replace_string(<span class="bild_rechts" style="width:): <p " replace_string(<div class="heisebox">): <blockquote> |