From a336c98fd3cf2bcc0850e7fc292effe70e741aa2 Mon Sep 17 00:00:00 2001 From: Tom Taylor Date: Tue, 1 Jul 2014 20:13:51 +0100 Subject: Convert asymco.com.txt from latin1. --- asymco.com.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/asymco.com.txt b/asymco.com.txt index 9093875..f639b04 100644 --- a/asymco.com.txt +++ b/asymco.com.txt @@ -1,4 +1,4 @@ -# Johannes Stühler +# Johannes Stühler title://h2 author://span[@class='meta-content'] -- cgit v1.3.1 From 57407a51792c696516d3722dedaed785b82ba113 Mon Sep 17 00:00:00 2001 From: Tom Taylor Date: Tue, 1 Jul 2014 20:16:11 +0100 Subject: Fix test URL in dailykos.com.txt. --- dailykos.com.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/dailykos.com.txt b/dailykos.com.txt index e56ee58..6d4cb82 100644 --- a/dailykos.com.txt +++ b/dailykos.com.txt @@ -7,4 +7,4 @@ strip_id_or_class: divider-doodle prune: no -test_url: http://www.dailykos.com/story/2012/01/26/1058790/-Newt-Gingrichs-campaign-admits-he-lied-during-debate-about-ABC-News-interview-with-his ex-wife \ No newline at end of file +test_url: http://www.dailykos.com/story/2012/01/26/1058790/-Newt-Gingrich-s-campaign-admits-he-lied-during-debate-about-ABC-News-interview-with-his-ex-wife -- cgit v1.3.1 From 05999f636c85ebde61854a069dd6ca268f906391 Mon Sep 17 00:00:00 2001 From: Tom Taylor Date: Tue, 1 Jul 2014 20:17:14 +0100 Subject: Convert hardware.no.txt from latin1. --- hardware.no.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hardware.no.txt b/hardware.no.txt index 38ea9f1..cbbcf84 100644 --- a/hardware.no.txt +++ b/hardware.no.txt @@ -11,6 +11,6 @@ next_page_link: //a[@rel='next'] strip_id_or_class: 'product-box' strip: //a[@rel='next'] -strip: //a[text()='Del på Facebook'] -strip: //a[text()='Del på Twitter'] +strip: //a[text()='Del pÃ¥ Facebook'] +strip: //a[text()='Del pÃ¥ Twitter'] test_url: http://www.hardware.no/artikler/asus-vg248qe/132792 \ No newline at end of file -- cgit v1.3.1 From d90b6a33d113c86f352a5b70d5285ba30171a425 Mon Sep 17 00:00:00 2001 From: Tom Taylor Date: Tue, 1 Jul 2014 20:18:21 +0100 Subject: Convert macdrifter.com.txt from latin1. --- macdrifter.com.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/macdrifter.com.txt b/macdrifter.com.txt index fd1ede7..e57bd64 100644 --- a/macdrifter.com.txt +++ b/macdrifter.com.txt @@ -1,2 +1,2 @@ -title: substring-before(//title,' « Macdrifter') +title: substring-before(//title,' « Macdrifter') test_url: http://www.macdrifter.com/2012/03/instacast-on-my-mac/ \ No newline at end of file -- cgit v1.3.1 From 5f117de9242e41a374b1d9cb25625a3d0214d0f9 Mon Sep 17 00:00:00 2001 From: Tom Taylor Date: Tue, 1 Jul 2014 20:22:02 +0100 Subject: Removing omm.hk.txt. I was going to fix the encoding on this file, but then I looked at the site and it looks like it's shut down. --- omm.hk.txt | 19 ------------------- 1 file changed, 19 deletions(-) delete mode 100644 omm.hk.txt diff --git a/omm.hk.txt b/omm.hk.txt deleted file mode 100644 index c6dd29b..0000000 --- a/omm.hk.txt +++ /dev/null @@ -1,19 +0,0 @@ -# This filter is tested on: -# http://omm.hk/time-after-japan-will-china-scale-back-its-nuclear-ambitions.html -# http://omm.hk/usa-today-china-invites-world-to-6-month-party.html -# http://omm.hk/%E6%96%B0%E9%97%BB%E7%9C%8B%E4%B8%96%E5%8D%9A.html - -body://div[@class='entry'] - -title:substring-after(//h2, ':') -title:substring-after(//h2, ':') -title://h2 - -author:substring-before(//h2, ':') -author:substring-before(//h2, ':') -author:substring-after(//title, '»') - -date:concat(//div[@class='postdate']/br/preceding-sibling::text(), '-', //div[@class='postdate']/br/following-sibling::text()) - -strip://div[contains(@class, 'post-ratings')] -test_url: http://omm.hk/%E4%B8%AD%E5%9B%BD%E9%9D%92%E5%B9%B4%E6%8A%A5%EF%BC%9A%E5%AE%AA%E6%B3%95%E8%AF%BE.html \ No newline at end of file -- cgit v1.3.1 From b07fab43a2cc1afde06be6e1c31ab06043a4ea3a Mon Sep 17 00:00:00 2001 From: Tom Taylor Date: Tue, 1 Jul 2014 20:23:31 +0100 Subject: Convert politiken.dk.txt from latin1. --- politiken.dk.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/politiken.dk.txt b/politiken.dk.txt index de5889a..b13f8f8 100644 --- a/politiken.dk.txt +++ b/politiken.dk.txt @@ -1,7 +1,7 @@ # 21/10-2011: # Added Author+Date # Remove fakta-boks if found -# Deleted 'Læs også...' filter +# Deleted 'Læs ogsÃ¥...' filter # - Change in markup caused it to strip too much. author://span[@class='autor-name'] -- cgit v1.3.1 From 6940be388707e514ce4783ec9eda231a43a3d3b7 Mon Sep 17 00:00:00 2001 From: Tom Taylor Date: Tue, 1 Jul 2014 20:24:24 +0100 Subject: Convert scilogs.de.txt from latin1. --- scilogs.de.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scilogs.de.txt b/scilogs.de.txt index 99d45c0..b24d784 100644 --- a/scilogs.de.txt +++ b/scilogs.de.txt @@ -7,7 +7,7 @@ strip_id_or_class: socialshareprivacy strip: //div[@class='entrybody']/br[1] # Strip related articles -# 'p'-Tag strips 'Ähnliche Artikel: ' (
tags become

) +# 'p'-Tag strips 'Ähnliche Artikel: ' (
tags become

) strip: //div[@class='entrybody']/p[last()] strip: //div[@class='entrybody']/ul[last()] -- cgit v1.3.1 From ccd9e4241d48adcc5d77301f2c68415e7c4bfbfb Mon Sep 17 00:00:00 2001 From: Tom Taylor Date: Tue, 1 Jul 2014 20:25:26 +0100 Subject: Convert sebbo.net.txt from latin1. --- sebbo.net.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sebbo.net.txt b/sebbo.net.txt index 308a351..b6d9c92 100644 --- a/sebbo.net.txt +++ b/sebbo.net.txt @@ -1,4 +1,4 @@ -title: substring-before(//title, '«') +title: substring-before(//title, '«') body: //div[@class = 'entry'] strip_id_or_class: 'postmetabox' test_url: http://sebbo.net/2010/12/akkus/ \ No newline at end of file -- cgit v1.3.1 From ecdb94ad1806eecb12644617030f9260ca0c1276 Mon Sep 17 00:00:00 2001 From: Tom Taylor Date: Tue, 1 Jul 2014 20:25:56 +0100 Subject: Convert sueddeutsche.de.txt from latin1. --- sueddeutsche.de.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sueddeutsche.de.txt b/sueddeutsche.de.txt index 85e24b3..74b8d45 100644 --- a/sueddeutsche.de.txt +++ b/sueddeutsche.de.txt @@ -1,4 +1,4 @@ -# 2012-12-04: complete rewrite after Süddeutsche.de relaunch - carlo@... +# 2012-12-04: complete rewrite after Süddeutsche.de relaunch - carlo@... single_page_link: //a[ contains( @href, "/2.220/" ) ] -- cgit v1.3.1 From c59b2f4bae46e2a0647c59cbe321c7afb65d3c79 Mon Sep 17 00:00:00 2001 From: Tom Taylor Date: Tue, 1 Jul 2014 20:26:29 +0100 Subject: Convert sz.de.txt from latin1. --- sz.de.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sz.de.txt b/sz.de.txt index 51a30b4..f67637d 100644 --- a/sz.de.txt +++ b/sz.de.txt @@ -1,4 +1,4 @@ -# 2012-12-04: complete rewrite after Süddeutsche.de relaunch - carlo@... +# 2012-12-04: complete rewrite after Süddeutsche.de relaunch - carlo@... single_page_link: //a[ contains( @href, "/2.220/" ) ] -- cgit v1.3.1 From 73931f6f6c2df8e289ae5bf9261bcf0db9f814d2 Mon Sep 17 00:00:00 2001 From: Tom Taylor Date: Tue, 1 Jul 2014 20:27:17 +0100 Subject: Convert tbray.org.txt from latin1. --- tbray.org.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tbray.org.txt b/tbray.org.txt index b61effa..558dc9c 100644 --- a/tbray.org.txt +++ b/tbray.org.txt @@ -1,5 +1,5 @@ body: //div[@id='centercontent'] strip: //div[@id='rightcontent'] -date: substring-before( //div[@id='cats'], '·') +date: substring-before( //div[@id='cats'], '·') title: //h1 test_url: http://www.tbray.org/ongoing/When/201x/2012/03/04/Mobile-Money \ No newline at end of file -- cgit v1.3.1 From 730178be3e24c3d4db8c01652ecc57d3cf22bec1 Mon Sep 17 00:00:00 2001 From: Tom Taylor Date: Tue, 1 Jul 2014 20:27:45 +0100 Subject: Convert westhamtillidie.com.txt from latin1. --- westhamtillidie.com.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/westhamtillidie.com.txt b/westhamtillidie.com.txt index 6af1820..3132e98 100644 --- a/westhamtillidie.com.txt +++ b/westhamtillidie.com.txt @@ -1,4 +1,4 @@ -title: substring-before(//title, '«') +title: substring-before(//title, '«') body: //div[@class='entry'] strip: //div[@class='sharing_label'] -- cgit v1.3.1