From 10747376ab44fb193d282f804b561b890533fc60 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 18 Sep 2013 19:23:50 +0200 Subject: Swedish news sites --- dn.se.txt | 4 +++- fria.nu.txt | 8 ++++++++ friatidningen.se.txt | 7 +++++++ goteborgsfria.se.txt | 7 +++++++ gp.se.txt | 11 +++++++++++ landetsfria.se.txt | 7 +++++++ skanesfria.se.txt | 7 +++++++ stockholmsfria.nu.txt | 7 +++++++ sydsvenskan.se.txt | 13 ++++++++++--- uppsalafria.se.txt | 7 +++++++ 10 files changed, 74 insertions(+), 4 deletions(-) create mode 100644 fria.nu.txt create mode 100644 friatidningen.se.txt create mode 100644 goteborgsfria.se.txt create mode 100644 gp.se.txt create mode 100644 landetsfria.se.txt create mode 100644 skanesfria.se.txt create mode 100644 stockholmsfria.nu.txt create mode 100644 uppsalafria.se.txt diff --git a/dn.se.txt b/dn.se.txt index 05b1ee0..5283a0c 100644 --- a/dn.se.txt +++ b/dn.se.txt @@ -23,4 +23,6 @@ author: //div[@id="byline"]/div/p/strong # Date date: substring(substring-after(//p[@class="published"], 'Publicerad '), 0, 11) -test_url: http://www.dn.se/nyheter/varlden/landade-flygplan-mitt-i-villaomrade \ No newline at end of file + +test_url: http://www.dn.se/nyheter/varlden/landade-flygplan-mitt-i-villaomrade +test_url: http://www.dn.se/m/rss/senaste-nytt \ No newline at end of file diff --git a/fria.nu.txt b/fria.nu.txt new file mode 100644 index 0000000..9d8eff9 --- /dev/null +++ b/fria.nu.txt @@ -0,0 +1,8 @@ +body: //div[contains(@class, 'layout__inner')]//div[contains(@class, 'file-image') or contains(@class, 'node__content')] +author: //article//div[contains(@class, 'field-byline')] +strip_id_or_class: rekommenderade +strip_id_or_class: disqus +strip_id_or_class: annonser + +test_url: http://www.fria.nu/artikel/112079 +test_url: http://www.fria.nu/taxonomy/term/1928/all/feed \ No newline at end of file diff --git a/friatidningen.se.txt b/friatidningen.se.txt new file mode 100644 index 0000000..1e4abc5 --- /dev/null +++ b/friatidningen.se.txt @@ -0,0 +1,7 @@ +body: //div[contains(@class, 'layout__inner')]//div[contains(@class, 'file-image') or contains(@class, 'node__content')] +author: //article//div[contains(@class, 'field-byline')] +strip_id_or_class: rekommenderade +strip_id_or_class: disqus +strip_id_or_class: annonser + +test_url: http://www.friatidningen.se/artikel/112074 \ No newline at end of file diff --git a/goteborgsfria.se.txt b/goteborgsfria.se.txt new file mode 100644 index 0000000..c90aed0 --- /dev/null +++ b/goteborgsfria.se.txt @@ -0,0 +1,7 @@ +body: //div[contains(@class, 'layout__inner')]//div[contains(@class, 'file-image') or contains(@class, 'node__content')] +author: //article//div[contains(@class, 'field-byline')] +strip_id_or_class: rekommenderade +strip_id_or_class: disqus +strip_id_or_class: annonser + +test_url: http://www.goteborgsfria.se/artikel/112079 \ No newline at end of file diff --git a/gp.se.txt b/gp.se.txt new file mode 100644 index 0000000..158ae4e --- /dev/null +++ b/gp.se.txt @@ -0,0 +1,11 @@ +body: //div[@id='articleContainer'] +author: //div[@id='articleContent']//div[contains(@class, 'byline')]//span[contains(@class, 'name fn')] +strip_id_or_class: toolbar +strip_id_or_class: ADad +strip_id_or_class: articleSerieWrapper +strip_id_or_class: articleFloatContainer +strip: //div[contains(@class, 'byline')]//img +prune: no + +test_url: http://www.gp.se/nyheter/bohuslan/1.2045564-styckade-mannen-hade-mordat-hustrun +test_url: http://www.gp.se/1.16560 \ No newline at end of file diff --git a/landetsfria.se.txt b/landetsfria.se.txt new file mode 100644 index 0000000..e5317a5 --- /dev/null +++ b/landetsfria.se.txt @@ -0,0 +1,7 @@ +body: //div[contains(@class, 'layout__inner')]//div[contains(@class, 'file-image') or contains(@class, 'node__content')] +author: //article//div[contains(@class, 'field-byline')] +strip_id_or_class: rekommenderade +strip_id_or_class: disqus +strip_id_or_class: annonser + +test_url: http://www.landetsfria.se/artikel/112070 \ No newline at end of file diff --git a/skanesfria.se.txt b/skanesfria.se.txt new file mode 100644 index 0000000..a0ddac7 --- /dev/null +++ b/skanesfria.se.txt @@ -0,0 +1,7 @@ +body: //div[contains(@class, 'layout__inner')]//div[contains(@class, 'file-image') or contains(@class, 'node__content')] +author: //article//div[contains(@class, 'field-byline')] +strip_id_or_class: rekommenderade +strip_id_or_class: disqus +strip_id_or_class: annonser + +test_url: http://www.skanesfria.se/artikel/112045 \ No newline at end of file diff --git a/stockholmsfria.nu.txt b/stockholmsfria.nu.txt new file mode 100644 index 0000000..cc8c28b --- /dev/null +++ b/stockholmsfria.nu.txt @@ -0,0 +1,7 @@ +body: //div[contains(@class, 'layout__inner')]//div[contains(@class, 'file-image') or contains(@class, 'node__content')] +author: //article//div[contains(@class, 'field-byline')] +strip_id_or_class: rekommenderade +strip_id_or_class: disqus +strip_id_or_class: annonser + +test_url: http://www.stockholmsfria.nu/artikel/112068 \ No newline at end of file diff --git a/sydsvenskan.se.txt b/sydsvenskan.se.txt index 44ec8b9..24ba142 100644 --- a/sydsvenskan.se.txt +++ b/sydsvenskan.se.txt @@ -2,10 +2,17 @@ title: //h1 author: //a[contains(@href, '/sok/?')]/text() -date: substring-after(//span[@class='date'], 'Publicerad ') +date: //meta[@name='bi3dPubDate']/@content -body: //div[@class='two_column_left'] +body: (//div[contains(@class, 'slider_wrapper')])[1] | //div[@id='article_image' or @class='two_column_left'] strip_id_or_class: story +strip_id_or_class: article_body_ad strip: //div[@class='leadText saplo:lead']/h5 -test_url: http://www.sydsvenskan.se/kultur-och-nojen/-jag-vill-garna--stanna-- \ No newline at end of file +replace_string(
):

+ +prune: no + +test_url: http://www.sydsvenskan.se/malmo/allt-jag-ager-ligger-pa-botten/ +test_url: http://www.sydsvenskan.se/kultur-och-nojen/-jag-vill-garna--stanna-- +test_url: http://www.sydsvenskan.se/rss.xml \ No newline at end of file diff --git a/uppsalafria.se.txt b/uppsalafria.se.txt new file mode 100644 index 0000000..79c59ec --- /dev/null +++ b/uppsalafria.se.txt @@ -0,0 +1,7 @@ +body: //div[contains(@class, 'layout__inner')]//div[contains(@class, 'file-image') or contains(@class, 'node__content')] +author: //article//div[contains(@class, 'field-byline')] +strip_id_or_class: rekommenderade +strip_id_or_class: disqus +strip_id_or_class: annonser + +test_url: http://www.uppsalafria.se/artikel/97167 \ No newline at end of file -- cgit v1.3.1