From f73d881c91ceb97fb81c86391401e84e708e1bd4 Mon Sep 17 00:00:00 2001 From: Stefan Siegl Date: Sun, 5 Jul 2015 16:09:15 +0000 Subject: spiegel.de: remove copyright & print more box --- spiegel.de.txt | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/spiegel.de.txt b/spiegel.de.txt index 413e015..84809eb 100644 --- a/spiegel.de.txt +++ b/spiegel.de.txt @@ -8,6 +8,9 @@ # - Fixed single_page_link # - Included intro text in single page view # - Added body in default view +# stesie@ +# - removed copyright box +# - removed "print more" box # set body tidy: no @@ -67,6 +70,9 @@ strip: //div[@id='spBigaLatestEntries'] strip: //div[contains(@class, 'spBigaNavi')] strip: //div[@class='spDottedLine'] +strip: //div[@class='asset-box article-print-more'] +strip: //div[@class='article-copyright'] + # Use link to print article for single page view single_page_link: //a[contains(@href, '-druck')] -- cgit v1.3.1 From 1e7b752493b873a28c30a11a29f4cff36579447e Mon Sep 17 00:00:00 2001 From: Stefan Siegl Date: Sun, 5 Jul 2015 16:13:11 +0000 Subject: sueddeutsche.de (sz.de): fix single_page_link --- sueddeutsche.de.txt | 2 +- sz.de.txt | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/sueddeutsche.de.txt b/sueddeutsche.de.txt index 74b8d45..26e0560 100644 --- a/sueddeutsche.de.txt +++ b/sueddeutsche.de.txt @@ -1,6 +1,6 @@ # 2012-12-04: complete rewrite after Süddeutsche.de relaunch - carlo@... -single_page_link: //a[ contains( @href, "/2.220/" ) ] +single_page_link: //li[@id="article-sidebar-action-print"]/@data-clickurl body: //article[@id="sitecontent"]/section[@class="body"] author: //address[@class="author"] diff --git a/sz.de.txt b/sz.de.txt index f67637d..f194271 100644 --- a/sz.de.txt +++ b/sz.de.txt @@ -1,6 +1,6 @@ # 2012-12-04: complete rewrite after Süddeutsche.de relaunch - carlo@... -single_page_link: //a[ contains( @href, "/2.220/" ) ] +single_page_link: //li[@id="article-sidebar-action-print"]/@data-clickurl body: //article[@id="sitecontent"]/section[@class="body"] author: //address[@class="author"] -- cgit v1.3.1 From 87ed057bf5863c2eb9e8c00529538bda869223f0 Mon Sep 17 00:00:00 2001 From: Stefan Siegl Date: Sun, 5 Jul 2015 16:14:21 +0000 Subject: taz.de: pick first body only + strip ads --- taz.de.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/taz.de.txt b/taz.de.txt index cf85366..a336856 100644 --- a/taz.de.txt +++ b/taz.de.txt @@ -1,8 +1,9 @@ date: //div[@class='secthead'] -body: //div[@class='sectbody'] +body: (//div[@class='sectbody'])[1] title: concat(//div[@class='sectbody']/h4,': ',//div[@class='sectbody']/h1) author: //span[@class='author'] strip: //p[@class='caption'] +strip_id_or_class: ad_bin strip_id_or_class: rack test_url: http://www.taz.de/Protestbewegung-Occupy/!80188/ \ No newline at end of file -- cgit v1.3.1 From 2a8fed0a6a86bd7c100eb182d78a9de6e7baed84 Mon Sep 17 00:00:00 2001 From: Stefan Siegl Date: Sun, 5 Jul 2015 16:16:46 +0000 Subject: brandeins.de: rewrite --- brandeins.de.txt | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/brandeins.de.txt b/brandeins.de.txt index 36aa2ef..be32634 100644 --- a/brandeins.de.txt +++ b/brandeins.de.txt @@ -1,7 +1,9 @@ -# set body -body: //div[@id='theContent'] -# set title -title: //div[@id='theContent']/h3 -strip: //div[@id='theContent']/h3 -test_url: http://www.brandeins.de/archiv/magazin/gegessen-wird-immer/artikel/hunger.html \ No newline at end of file +body: //div[@class="articleTeaser"] | //section[@class="contentSection"] + +strip: //section[@class="greenBox italic"] + +author: //div[@class="articleAuthor"] +# no publish date on page (the articles are from a monthly periodical) + +test_url: http://www.brandeins.de/archiv/2015/fuehrung/ministry-group-mach-doch-mal-ne-ansage/ -- cgit v1.3.1 From 5b50e59f662e2afd860b0c121a877f88ca1586bd Mon Sep 17 00:00:00 2001 From: Stefan Siegl Date: Sun, 5 Jul 2015 16:17:20 +0000 Subject: entwickler.de --- entwickler.de.txt | 7 +++++++ 1 file changed, 7 insertions(+) create mode 100644 entwickler.de.txt diff --git a/entwickler.de.txt b/entwickler.de.txt new file mode 100644 index 0000000..316f399 --- /dev/null +++ b/entwickler.de.txt @@ -0,0 +1,7 @@ +title: //h1[@class="post-title"] +body: //section[@class="article-content"] +author: //div[@class="post-bottom-meta"]/span[@class="post-author"] +date: //div[@class="post-date"]/time/@datetime + +test_url: https://entwickler.de/online/mobile-welt-offline-welt-was-der-offline-first-ansatz-fuer-app-entwickler-heisst-140602.html +test_url: https://entwickler.de/online/development/plex-docker-joomla-165345.html -- cgit v1.3.1 From 74632a099ab3d15ec521fdd18a6fac7a20ef96e8 Mon Sep 17 00:00:00 2001 From: Stefan Siegl Date: Sun, 5 Jul 2015 16:17:39 +0000 Subject: truongtx.me --- truongtx.me.txt | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 truongtx.me.txt diff --git a/truongtx.me.txt b/truongtx.me.txt new file mode 100644 index 0000000..6b10adc --- /dev/null +++ b/truongtx.me.txt @@ -0,0 +1,9 @@ +prune: false +tidy: false + +body: //div[@class='col-md-9'] +author: //meta[@name='author'] +date: //i[@class='fa fa-calendar']/../span +title: //div[@class='page-header']/h1 + +test_url: https://truongtx.me/2014/04/20/emacs-javascript-completion-and-refactoring/ -- cgit v1.3.1