summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--anandtech.com.txt1
-rw-r--r--computerbase.de.txt17
-rw-r--r--golem.de.txt5
-rw-r--r--hardware-infos.com.txt10
-rw-r--r--hardwareluxx.de.txt19
-rwxr-xr-xheise.de.txt13
-rw-r--r--omgubuntu.co.uk.txt12
-rw-r--r--phoronix.com.txt8
-rw-r--r--planet3dnow.de.txt16
-rw-r--r--pro-linux.de.txt19
-rw-r--r--sueddeutsche.de.txt37
-rw-r--r--sz.de.txt38
-rw-r--r--teamliquid.net.txt20
-rw-r--r--vr-zone.com.txt14
-rw-r--r--webupd8.org.txt12
15 files changed, 204 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/hardware-infos.com.txt b/hardware-infos.com.txt
new file mode 100644
index 0000000..1d63b6c
--- /dev/null
+++ b/hardware-infos.com.txt
@@ -0,0 +1,10 @@
+tidy: no
+prune: no
+
+title: //div[@class='content post']/h1
+body: //div[@class='post']
+
+next_page_link: //a[preceding::div[@class='pages']]
+
+test_url: http://www.hardware-infos.com/news/5646/amd-bei-next-gen-api-mit-besserer-gpu-auslastung.html
+test_url: http://www.hardware-infos.com/tests/grafikkarten/sapphire-r9-280x-vapor-x-tri-x-oc.html
diff --git a/hardwareluxx.de.txt b/hardwareluxx.de.txt
new file mode 100644
index 0000000..3775d79
--- /dev/null
+++ b/hardwareluxx.de.txt
@@ -0,0 +1,19 @@
+tidy: no
+prune: no
+
+title: //span[@itemprop='title']
+author: //span[@itemprop='author']//span[@itemprop='name']
+body: //article
+date: //time
+
+strip: //header
+strip: //div[@id='bcr']
+strip: //footer
+strip: //section
+strip: //figure[@class='dynbench']
+strip: //div[@class='pagenavbar']
+
+next_page_link: //span[@class='next']/a
+
+test_url: http://www.hardwareluxx.de/index.php/news/allgemein/netzpolitik/35169-creator-space-youtube-eroeffnet-neues-studio-in-berlin.html
+test_url: http://www.hardwareluxx.de/index.php/artikel/hardware/komplettsysteme/35020-caseking-king-mod-titan-oc-gaming-pc-im-test.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/omgubuntu.co.uk.txt b/omgubuntu.co.uk.txt
new file mode 100644
index 0000000..d685c01
--- /dev/null
+++ b/omgubuntu.co.uk.txt
@@ -0,0 +1,12 @@
+tidy: no
+prune: no
+
+title: //h2[@class='entry-title']
+author: //a[@rel='author']
+
+body: //article
+
+strip: //div[@class='entry-share']
+strip: //div[@class='entry-meta']
+
+test_url: http://www.omgubuntu.co.uk/2015/04/facebook-chat-api-empathy-pidgin-stop-working
diff --git a/phoronix.com.txt b/phoronix.com.txt
new file mode 100644
index 0000000..e7dd21c
--- /dev/null
+++ b/phoronix.com.txt
@@ -0,0 +1,8 @@
+# based on the grabber rules of picofeed
+
+body: //div[@class="content"]/child::node()
+test_url: http://www.phoronix.com/scan.php?page=article&item=amazon_ec2_bare&num=1
+
+# replace_string(<h5>): <h2>
+
+next_page_link: //a[@title='Go To Next Page']
diff --git a/planet3dnow.de.txt b/planet3dnow.de.txt
new file mode 100644
index 0000000..23db6b0
--- /dev/null
+++ b/planet3dnow.de.txt
@@ -0,0 +1,16 @@
+# Author: Jan Lukas Gernert
+
+tidy: no
+prune: no
+
+title: //title
+author: //span[@class='author vcard']/a
+
+body: //article
+next_page_link: //span[@class='multipage-navlink nav-next']/a
+
+strip: //div[@id='pagination_top']
+strip: //header[@class='entry-header']
+strip: //span[@class='multipage-navlink nav-previous']
+
+test_url: http://www.planet3dnow.de/cms/14809-test-fractal-design-node-804/
diff --git a/pro-linux.de.txt b/pro-linux.de.txt
new file mode 100644
index 0000000..57bf701
--- /dev/null
+++ b/pro-linux.de.txt
@@ -0,0 +1,19 @@
+tidy: no
+prune: no
+
+title: //h2[@class='title']
+date: //div[@class='tidescr']
+
+body: //div[@id='article']
+body: //div[@id='news']
+
+next_page_link: //a[@title='nächste']
+
+strip: //div[@class='topic']
+strip: //h2[@class='title']
+strip: //div[a[contains(@href,'/user/')]]
+strip: //div[@class='picto']
+strip: //p[@class='addinfo']
+strip: //h3[@class='topic']
+
+test_url: http://www.pro-linux.de/artikel/2/1762/ubuntu-und-kubuntu-1504.html
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
diff --git a/sz.de.txt b/sz.de.txt
index f194271..e659bdb 100644
--- a/sz.de.txt
+++ b/sz.de.txt
@@ -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
diff --git a/teamliquid.net.txt b/teamliquid.net.txt
new file mode 100644
index 0000000..7cfea15
--- /dev/null
+++ b/teamliquid.net.txt
@@ -0,0 +1,20 @@
+# Author: Jan Lukas Gernert
+
+tidy: no
+prune: no
+
+title: //div[@class='Newsheader']/h1
+#date: //time
+#author: //a[@rel='author']
+
+body: //div[@id='Newswrap']
+body: //div[@class='text']
+body: //article
+
+strip: //div[@id='Newscontents']
+strip: //div[@class='Newsbanner']
+strip: //style
+
+
+
+test_url: http://www.teamliquid.net/forum/starcraft-2/484380-code-s-ro32-group-c-on-the-way-back-s2-2015
diff --git a/vr-zone.com.txt b/vr-zone.com.txt
new file mode 100644
index 0000000..3d773f4
--- /dev/null
+++ b/vr-zone.com.txt
@@ -0,0 +1,14 @@
+tidy: no
+prune: no
+
+title: //title
+date: //time
+
+body: //div[@class='post-content entry-content']
+
+strip: //a[@id='dd_start']
+strip: //iframe
+strip: //div[@class='dd_outer']
+strip: //comments
+
+test_url: http://vr-zone.com/articles/amd-take-intel-8-core-fm3-socket-zen-desktop-cpus-next-year/91057.html
diff --git a/webupd8.org.txt b/webupd8.org.txt
new file mode 100644
index 0000000..b5c165d
--- /dev/null
+++ b/webupd8.org.txt
@@ -0,0 +1,12 @@
+tidy: no
+prune: no
+
+title: //h1[@class='post-title entry-title']/a
+date: //time
+author: //a[@rel='fn author']/span
+
+body: //div[@class='post-body']
+
+strip: //iframe
+
+test_url: http://www.webupd8.org/2015/04/organize-your-unity-launcher-based-on.html