diff options
| -rw-r--r-- | anandtech.com.txt | 1 | ||||
| -rw-r--r-- | computerbase.de.txt | 17 | ||||
| -rw-r--r-- | golem.de.txt | 5 | ||||
| -rwxr-xr-x | heise.de.txt | 13 | ||||
| -rw-r--r-- | sueddeutsche.de.txt | 37 | ||||
| -rw-r--r-- | sz.de.txt | 38 |
6 files changed, 74 insertions, 37 deletions
diff --git a/anandtech.com.txt b/anandtech.com.txt index fc95c5d..faba9fb 100644 --- a/anandtech.com.txt +++ b/anandtech.com.txt @@ -9,6 +9,7 @@ strip: //h2 prune: no single_page_link: concat('http://www.anandtech.com/print/', substring-after(//meta[@property='og:url']/@content, '/show/')) +next_page_link: //div[@class='article_links']/a[@class='fl-rt'] test_url: http://www.anandtech.com/show/8370/gigabyte-am1m-s2h-review test_url: http://www.anandtech.com/show/8402/sandisk-releases-ultra-ii-ssd-the-second-tlc-nand-ssd-in-the-market diff --git a/computerbase.de.txt b/computerbase.de.txt index 214fcce..c6957c3 100644 --- a/computerbase.de.txt +++ b/computerbase.de.txt @@ -1,18 +1,15 @@ title://h1 -author://div[@id="news-meta"]/a +author://span[@class="article-authornames"]/a -body: //div[contains(@class, 'text-content')] +body: //div[@class='article-view__content'] -strip://*[@id="main"]/div[2] -strip://*[@id="main"]/div[3] -strip://*[@id="page"]//footer +replace_string("padding-bottom:): " -#date: didn't manage to parse it -#Images have to be stripped because the page does it with overlay -strip://img +strip://div[@class='adbox-wrapper__label'] +strip://div[@class='adbox-rectangle'] +strip://div[@class='adbox-rectangle'] +strip://div[contains(@class,'article-view__share-links-top')] -#figures are not displayed in instapaper... -strip://figure | //figcaption test_url: http://www.computerbase.de/news/2012-06/verbraucherzentrale-mahnt-blizzard-fuer-diablo-3-ab/ diff --git a/golem.de.txt b/golem.de.txt index c64860c..6954168 100644 --- a/golem.de.txt +++ b/golem.de.txt @@ -8,6 +8,7 @@ prune: no title: //h1 date: //time +author: //a[@rel='author'] # Content is here body: //article @@ -28,6 +29,10 @@ strip_id_or_class: footer # Tidy up galleries (could still be improved, though) strip: //img[@src=''] +strip: //li[not(*)] +strip: //div[contains(@style,'margin')] +strip: //figure[contains(@id,'gvideo')] + # Try yourself test_url: http://www.golem.de/news/intel-core-i7-5960x-im-test-die-pc-revolution-beginnt-mit-octacore-und-ddr4-1408-108893.html 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> diff --git a/sueddeutsche.de.txt b/sueddeutsche.de.txt index 26e0560..71ec5aa 100644 --- a/sueddeutsche.de.txt +++ b/sueddeutsche.de.txt @@ -1,18 +1,29 @@ # 2012-12-04: complete rewrite after Süddeutsche.de relaunch - carlo@... -single_page_link: //li[@id="article-sidebar-action-print"]/@data-clickurl +#single_page_link: //a[ contains( @href, "/2.220/" ) ] -body: //article[@id="sitecontent"]/section[@class="body"] -author: //address[@class="author"] -date: //div[@class="header"]//h1//span[@class="updated"] -wrap_in(small): //div[@class="footer"] -wrap_in(i): //figcaption/h3 -dissolve: //figcaption//h3 -dissolve: //figure/div[@class="body"] -dissolve: //figure/a +#body: //article[@id="sitecontent"]/section[@class="body"] +#author: //address[@class="author"] +#date: //div[@class="header"]//h1//span[@class="updated"] +#wrap_in(small): //div[@class="footer"] +#wrap_in(i): //figcaption/h3 +#dissolve: //figcaption//h3 +#dissolve: //figure/div[@class="body"] +#dissolve: //figure/a -strip: //figure[ not( contains(@class, "zoomimage" ) ) ] -strip: //div[@data-onlineonly="true"] -strip: //address[@class="author"] +#strip: //figure[ not( contains(@class, "zoomimage" ) ) ] +#strip: //div[@data-onlineonly="true"] +#strip: //address[@class="author"] + +#test_url: http://www.sueddeutsche.de/muenchen/mietshaus-am-gaertnerplatz-alles-muss-raus-1.1556693 + + + +body: //article[@id="sitecontent"] +author: //meta[@name="author"]/@content + +strip: //section[@class="header"] +strip: //div[@id="article-sidebar-wrapper"] +strip: //p[@class="anzeige"] +strip: //section[@class="authors"] -test_url: http://www.sueddeutsche.de/muenchen/mietshaus-am-gaertnerplatz-alles-muss-raus-1.1556693
\ No newline at end of file @@ -1,18 +1,30 @@ # 2012-12-04: complete rewrite after Süddeutsche.de relaunch - carlo@... -single_page_link: //li[@id="article-sidebar-action-print"]/@data-clickurl +#single_page_link: //a[ contains( @href, "/2.220/" ) ] -body: //article[@id="sitecontent"]/section[@class="body"] -author: //address[@class="author"] -date: //div[@class="header"]//h1//span[@class="updated"] -wrap_in(small): //div[@class="footer"] -wrap_in(i): //figcaption/h3 -dissolve: //figcaption//h3 -dissolve: //figure/div[@class="body"] -dissolve: //figure/a +#body: //article[@id="sitecontent"]/section[@class="body"] +#author: //address[@class="author"] +#date: //div[@class="header"]//h1//span[@class="updated"] +#wrap_in(small): //div[@class="footer"] +#wrap_in(i): //figcaption/h3 +#dissolve: //figcaption//h3 +#dissolve: //figure/div[@class="body"] +#dissolve: //figure/a -strip: //figure[ not( contains(@class, "zoomimage" ) ) ] -strip: //div[@data-onlineonly="true"] -strip: //address[@class="author"] +#strip: //figure[ not( contains(@class, "zoomimage" ) ) ] +#strip: //div[@data-onlineonly="true"] +#strip: //address[@class="author"] + +#test_url: http://www.sueddeutsche.de/muenchen/mietshaus-am-gaertnerplatz-alles-muss-raus-1.1556693 + + + +body: //article[@id="sitecontent"] +author: //meta[@name="author"]/@content + +strip: //section[@class="header"] +strip: //div[@id="article-sidebar-wrapper"] +strip: //p[@class="anzeige"] +strip: //section[@class="authors"] +strip: //div[contains(@class, "embed")] -test_url: http://sz.de/1.1556693
\ No newline at end of file |