20 files changed, 132 insertions, 50 deletions
diff --git a/.onliner.by.txt b/.onliner.by.txt
new file mode 100644
index 0000000..8447005
--- /dev/null
+++ b/.onliner.by.txt
@@ -0,0 +1,9 @@
+title: //*[contains(@class, 'b-posts-1-item__title')]
+body: //figure[contains(@class, 'b-posts-1-item__image')] | //div[contains(@class, 'b-posts-1-item__text')]
+date: //article//time/@datetime
+
+tidy: no
+prune: no
+
+test_url: http://tech.onliner.by/feed
+test_url: http://tech.onliner.by/2014/04/24/the-amazing-spider-man-2
+\ No newline at end of file
diff --git a/alternet.org.txt b/alternet.org.txt
new file mode 100644
index 0000000..e92252e
--- /dev/null
+++ b/alternet.org.txt
@@ -0,0 +1,4 @@
+single_page_link: //div[contains(@class, 'story_tools')]//a[contains(@href, '/print/')]
+
+test_url: http://www.alternet.org/civil-liberties/noam-chomsky-surveillance-state-beyond-imagination-being-created-one-freest
+test_url: http://feeds.feedblitz.com/alternet
+\ No newline at end of file
diff --git a/arstechnica.com.txt b/arstechnica.com.txt
index c2ffb6a..767f680 100644
--- a/arstechnica.com.txt
+++ b/arstechnica.com.txt
@@ -2,6 +2,7 @@ author: //p[@class='byline']/a
 body: //div[contains(@class,'article-content')]
 strip: //h2[@class='title']
 strip_id_or_class: byline
+strip_id_or_class: story-sidebar
 prune: no
 
 date: //div[@class='byline']/span[@class='posted']//abbr/@original-title
@@ -13,4 +14,4 @@ strip: //div[@class='pager']
 next_page_link: //nav//a[span/@class='next']/@href
 
 test_url: http://arstechnica.com/tech-policy/news/2012/02/gigabit-internet-for-80-the-unlikely-success-of-californias-sonicnet.ars
-test_url: http://arstechnica.com/apple/2005/04/macosx-10-4/
-\ No newline at end of file
+test_url: http://arstechnica.com/apple/2005/04/macosx-10-4/
diff --git a/brasil.elpais.com.txt b/brasil.elpais.com.txt
new file mode 100644
index 0000000..0b8feb6
--- /dev/null
+++ b/brasil.elpais.com.txt
@@ -0,0 +1,23 @@
+title: //meta[@name='DC.title']/@content
+title: //div[contains(@class, 'cabecera_noticia')]//h1
+date: //meta[@name='DC.date']/@content
+date: //meta[@name='date']/@content
+body: //div[@class='columna_texto']
+body: //div[@id='cuerpo_noticia']
+body: //div[@class='estructura_2col_1zq']//div[@class='margen_n']
+
+prune: no
+
+strip_id_or_class: disposicion_vertical
+strip_id_or_class: ampliar_foto
+strip_id_or_class: utilidades
+strip_id_or_class: info_relacionada
+strip_id_or_class: m-kiosko
+strip_id_or_class: info_complementa
+
+strip: //p[@class='nota_pie']
+strip: //div[starts-with(@id, 'sumario') and contains(., 'más información')]
+strip: //div[@id='coment' or @id='foros_not']
+
+test_url: http://elpais.com/elpais/2012/02/06/gente/1328526783_491687.html
+test_url: http://www.elpais.com/articulo/cultura/mano/retrato/materia/elpepicul/20120207elpepicul_2/Tes
diff --git a/businessinsider.com.txt b/businessinsider.com.txt
index f847687..39eb742 100644
--- a/businessinsider.com.txt
+++ b/businessinsider.com.txt
@@ -1,12 +1,16 @@
 title://div[@class="sl-layout-post"]/h1
-body: //div[contains(@class, 'post-content') or contains(@class, 'KonaBody')]
+body: //div[contains(@class, 'post-content') or contains(@class, 'slide-module') or contains(@class, 'KonaBody')]
 strip: //div[contains(@class, "post-sidebar")]
 strip: //div[@id='related-links']
+strip: //div[@class='related-links-container']
+strip: //p[@class='source']
 author://div[@class="byline"]/a
 date://div[@class="byline"]/span[@class="date"]
 prune: no
 
+single_page_link: //a[contains(text(), 'View as one page')]
+
 strip://*[contains(@class,'sponsored-text')]
 strip: //div[@id='post_footer']
 
-test_url: http://www.businessinsider.com/microsoft-just-put-one-of-its-hardcore-technical-geniuses-on-xbox-2012-1
-\ No newline at end of file
+test_url: http://www.businessinsider.com/microsoft-just-put-one-of-its-hardcore-technical-geniuses-on-xbox-2012-1
diff --git a/dantri.com.vn.txt b/dantri.com.vn.txt
new file mode 100644
index 0000000..f19fee7
--- /dev/null
+++ b/dantri.com.vn.txt
@@ -0,0 +1,7 @@
+title: //h1[contains(@class, 'fon31 mt2')]
+body: //h2[contains(@class, 'fon33 mt1')] | //div[contains(@class, 'fon34 mt3')]
+
+prune: no
+
+test_url: http://dantri.com.vn/su-kien/chang-trai-mot-minh-dap-xe-vuot-450km-de-vieng-mo-dai-tuong-869763.htm
+test_url: http://dantri.com.vn/trangchu.rss
+\ No newline at end of file
diff --git a/heroturko.me.txt b/heroturko.me.txt
new file mode 100644
index 0000000..07b6adf
--- /dev/null
+++ b/heroturko.me.txt
@@ -0,0 +1,6 @@
+title: //div[contains(@class, 'title')]//h1
+body: //div[contains(@class, 'story')]
+
+prune: no
+
+test_url: http://www.heroturko.me/5223034-ds-catia-p3-v5-6r2014-gasp0-x86x64-multilanguage-english-docs.html
+\ No newline at end of file
diff --git a/hiamag.com.txt b/hiamag.com.txt
new file mode 100644
index 0000000..3c7ba5a
--- /dev/null
+++ b/hiamag.com.txt
@@ -0,0 +1,3 @@
+body: (//div[contains(@class, 'gallery-slides')]//img)[1] | //div[contains(@class, 'node_body_inner')]
+
+test_url: http://www.hiamag.com/rss.xml
+\ No newline at end of file
diff --git a/macrumors.com.txt b/macrumors.com.txt
index f211319..83cfb4a 100644
--- a/macrumors.com.txt
+++ b/macrumors.com.txt
@@ -3,8 +3,10 @@ date: substring-before(//div[@class='byline'], " by ")
 
 # set body
 body: //div[@class='content']
+strip_id_or_class: commentsContainer
+strip_id_or_class: linkback
 
 # set title
 title: //h3
 #strip: //div[@class='content']/h3
-test_url: http://www.macrumors.com/2010/11/10/apple-debuts-new-apple-tv-and-itunes-movie-content-in-japan/
-\ No newline at end of file
+test_url: http://www.macrumors.com/2010/11/10/apple-debuts-new-apple-tv-and-itunes-movie-content-in-japan/
diff --git a/mobile.nytimes.com.txt b/mobile.nytimes.com.txt
new file mode 100644
index 0000000..c60252e
--- /dev/null
+++ b/mobile.nytimes.com.txt
@@ -0,0 +1,4 @@
+title: //h1[contains(@class, 'headline')]
+body: //article[contains(@class, 'full-art')]
+strip_id_or_class: image-credit
+test_url: http://mobile.nytimes.com/2014/06/19/opinion/gail-collins-romney-and-the-2016-contenders-huddle.html
+\ No newline at end of file
diff --git a/newsweek.com.txt b/newsweek.com.txt
index 5a5f6b9..565648b 100644
--- a/newsweek.com.txt
+++ b/newsweek.com.txt
@@ -1,3 +1,6 @@
-tidy: no
+body: //div[@class = 'article-body']
+title: //h1[@class = 'article-title']
+strip: //aside
 
-test_url: http://www.newsweek.com/day-steve-mcqueen-met-his-new-nazi-neighbor-keith-moon-229741
-\ No newline at end of file
+test_url: http://www.newsweek.com/day-steve-mcqueen-met-his-new-nazi-neighbor-keith-moon-229741
+test_url: http://www.newsweek.com/2014/06/13/how-greylock-partners-finds-next-facebook-253329.html
diff --git a/nytimes.com.txt b/nytimes.com.txt
index 5712b64..23c9ad1 100644
--- a/nytimes.com.txt
+++ b/nytimes.com.txt
@@ -33,6 +33,7 @@ replace_string: </div>
 date: substring-after(//*[contains(@class, 'dateline')], 'Published:')
 
 single_page_link: //link[contains(@href, 'pagewanted=all')]
+single_page_link: //link[@rel='alternate' and contains(@href, 'mobile.nytimes.com')]/@href
 single_page_link: concat(substring-before(//div[@id='pageLinks']//a[contains(@href, 'pagewanted=')]/@href, 'pagewanted='), 'pagewanted=all') 
 #single_page_link: //a[contains(@href, 'pagewanted=all') and not(contains(@href, 'login'))]
 
@@ -44,4 +45,5 @@ test_url: http://www.nytimes.com/2011/07/24/books/review/an-academic-authors-uni
 test_url: http://www.nytimes.com/2012/06/10/arts/television/the-newsroom-aaron-sorkins-return-to-tv.html
 test_url: http://www.nytimes.com/2013/03/25/world/middleeast/israeli-military-responds-after-patrols-come-under-fire-from-syria.html
 test_url: http://www.nytimes.com/2013/08/15/nyregion/when-the-new-york-city-subway-ran-without-rails.html
-test_url: http://www.nytimes.com/2004/02/29/weekinreview/correspondence-class-consciousness-china-s-wealthy-live-creed-hobbes-darwin-meet.html
-\ No newline at end of file
+test_url: http://www.nytimes.com/2004/02/29/weekinreview/correspondence-class-consciousness-china-s-wealthy-live-creed-hobbes-darwin-meet.html
+test_url: http://www.nytimes.com/2014/06/19/opinion/gail-collins-romney-and-the-2016-contenders-huddle.html
+\ No newline at end of file
diff --git a/online.wsj.com.txt b/online.wsj.com.txt
index e0f91ac..448bb7e 100644
--- a/online.wsj.com.txt
+++ b/online.wsj.com.txt
@@ -19,6 +19,7 @@ strip: //div[contains(@class, 'carousel')]
 prune: no
 tidy: no
 
+test_url: http://online.wsj.com/news/articles/SB10001424052702304626304579509100018004342
 test_url: http://online.wsj.com/article/SB10001424052970203363504577185322849515102.html
 # slide show
 test_url: http://online.wsj.com/article/SB10001424052970204791104577110550376458164.html
diff --git a/sayidaty.net.txt b/sayidaty.net.txt
new file mode 100644
index 0000000..2d9f188
--- /dev/null
+++ b/sayidaty.net.txt
@@ -0,0 +1,4 @@
+date: //meta[@property='article:published_time']/@content
+body: (//div[contains(@class, 'article-slider')]//img)[1] | //div[contains(@class, 'bottom-article-con')]
+
+test_url: http://www.sayidaty.net/taxonomy/term/10/all/feed
+\ No newline at end of file
diff --git a/songshuhui.net.txt b/songshuhui.net.txt
index 51a7ac7..a923359 100644
--- a/songshuhui.net.txt
+++ b/songshuhui.net.txt
@@ -1,7 +1,7 @@
-# This filter is tested on:
-# http://songshuhui.net/archives/65522
-# http://songshuhui.net/archives/75760
-title://h2/span/a
-date:substring-before(substring-after(//div[@class='atrctitle']/div, '发表于'),' |')
+# This filter is tested on:
+# http://songshuhui.net/archives/65522
+# http://songshuhui.net/archives/75760
+title://h2/span/a
+date:substring-before(substring-after(//div[@class='atrctitle']/div, '发表于'),' |')
 body://div[@class='entry']
 test_url: http://songshuhui.net/archives/74819
 \ No newline at end of file
diff --git a/theguardian.com.txt b/theguardian.com.txt
index 068b7d2..c803e4e 100644
--- a/theguardian.com.txt
+++ b/theguardian.com.txt
@@ -3,10 +3,11 @@ body: //div[@id='article-wrapper']
 date: //li[@class='publication']//time[@pubdate] | //li[@class='publication']//data[@pubdate]
 strip: //div[contains(@class, 'email-subscription')]
 strip: //div[contains(@class, 'kindleWidget')]
-strip: //a[not(text())]
+#strip: //a[not(text())]
 strip_id_or_class: pocket-btn
 author: //li[@class='byline']
 prune: no
 tidy: no
 test_url: http://www.theguardian.com/world/2013/oct/04/nsa-gchq-attack-tor-network-encryption
-test_url: http://www.theguardian.com/world/2013/oct/03/edward-snowden-files-john-lanchester
-\ No newline at end of file
+test_url: http://www.theguardian.com/world/2013/oct/03/edward-snowden-files-john-lanchester
+test_url: http://www.theguardian.com/commentisfree/2014/jun/15/britishness-search-identity-my-part-in-camerons-odyssey
+\ No newline at end of file
diff --git a/theverge.com.txt b/theverge.com.txt
index dfa6b03..8cb9cd2 100644
--- a/theverge.com.txt
+++ b/theverge.com.txt
@@ -12,6 +12,7 @@ strip: //article/header
 strip: //*[@id='sticky-menu']
 strip: //aside
 strip: //nav
+strip: //img[contains(@class, 'vox-lazy-load')]
 
 strip_id_or_class: gallery
 strip_id_or_class: article-meta
@@ -26,8 +27,11 @@ strip_id_or_class: social-sharing
 strip_id_or_class: m-video-entry__excerpt
 strip_id_or_class: hidden
 
+replace_string(<noscript>): <div>
+replace_string(</noscript>): </div>
+
 find_string: <script
-replace_string: <div style="display:none"
+replace_string: <div style="display:none" 
 find_string: </script>
 replace_string: </div>
 
diff --git a/wired.com.txt b/wired.com.txt
index e06ad0e..f5a72d1 100644
--- a/wired.com.txt
+++ b/wired.com.txt
@@ -3,9 +3,13 @@ author: //meta[@name='Author']/@content
 date: //meta[@name='DisplayDate']/@content
 body: //div[@class='entry']
 strip: //p[contains(., 'Pages:') and contains(., 'View All')]
+strip: //p[@class='caption']
+strip: //div[@class='desc' or @class='slide' or @id='slide-info']
 
 strip_id_or_class: pullquote
 strip_id_or_class: left_rail
+strip_id_or_class: related-container
+strip_id_or_class: radvert-caption-wrap
 
 # Remove gallery?
 strip_id_or_class: wpgallery
@@ -18,4 +22,4 @@ single_page_link: //a[.='View All' and contains(@href, '/all/')]
 
 test_url: http://www.wired.com/cloudline/2011/10/meet-arms-cortex-a15-the-future-of-the-ipad-and-possibly-the-macbook-air/
 test_url: http://www.wired.com/wiredenterprise/2013/09/docker/
-test_url: http://www.wired.com/threatlevel/2012/05/ff_counterfeiter/all/
-\ No newline at end of file
+test_url: http://www.wired.com/threatlevel/2012/05/ff_counterfeiter/all/
diff --git a/xfgjls.com.txt b/xfgjls.com.txt
index 919d416..2dc247a 100644
--- a/xfgjls.com.txt
+++ b/xfgjls.com.txt
@@ -1,11 +1,11 @@
-# This filter is tested on:
-# http://www.xfgjls.com/magazine/html/?131.html
-# http://www.xfgjls.com/magazine/html/?170.html
-
-body://h3/following-sibling::div
-title: //h3
-date: substring-before(//h3/following-sibling::div/p, ' ')
-author: substring-before(substring-after(//h3/following-sibling::div/p, '作者:'), '来源')
-wrap_in(strong)://span[contains(@style, "FONT-WEIGHT: bold")]
+# This filter is tested on:
+# http://www.xfgjls.com/magazine/html/?131.html
+# http://www.xfgjls.com/magazine/html/?170.html
+
+body://h3/following-sibling::div
+title: //h3
+date: substring-before(//h3/following-sibling::div/p, ' ')
+author: substring-before(substring-after(//h3/following-sibling::div/p, '作者:'), '来源')
+wrap_in(strong)://span[contains(@style, "FONT-WEIGHT: bold")]
 dissolve://span[@style="FONT-FAMILY: '宋体'; FONT-SIZE: 10.5pt; FONT-WEIGHT: bold; mso-spacerun: 'yes'"]
 test_url: http://www.xfgjls.com/magazine/html/?170.html
 \ No newline at end of file
diff --git a/ynet.co.il.txt b/ynet.co.il.txt
index 195eebf..aa86566 100644
--- a/ynet.co.il.txt
+++ b/ynet.co.il.txt
@@ -1,26 +1,26 @@
-body: //span[@id='article_content' or @class='text16g']
-
-# ads
-strip: //div[.//div[contains(@id, 'ads.')]]
-# related content heading
-strip: //p[contains(., 'עוד בערוץ החדשות של ynet:')]
-strip: //p[contains(., 'כותרות אחרונות מהעולם בחדשות ynet:')]
-strip: //div[contains(., 'אינציקלופדיית ynet:')]
-# related content links
-strip: //a[@class='bluelink']
-# strip image bullets
-strip_image_src: ynet_manual_bullet.png
-
-prune: no
-tidy: no
-
-# prevent JS issues
-find_string: <script type='text/javascript'>
-replace_string: <div style="display:none;">
-find_string: </script>
-replace_string: </div>
-
-test_url: http://www.ynet.co.il/articles/0,7340,L-4354266,00.html
-test_url: http://www.ynet.co.il/articles/0,7340,L-4354268,00.html
-#feed
+body: //span[@id='article_content' or @class='text16g']
+
+# ads
+strip: //div[.//div[contains(@id, 'ads.')]]
+# related content heading
+strip: //p[contains(., 'עוד בערוץ החדשות של ynet:')]
+strip: //p[contains(., 'כותרות אחרונות מהעולם בחדשות ynet:')]
+strip: //div[contains(., 'אינציקלופדיית ynet:')]
+# related content links
+strip: //a[@class='bluelink']
+# strip image bullets
+strip_image_src: ynet_manual_bullet.png
+
+prune: no
+tidy: no
+
+# prevent JS issues
+find_string: <script type='text/javascript'>
+replace_string: <div style="display:none;">
+find_string: </script>
+replace_string: </div>
+
+test_url: http://www.ynet.co.il/articles/0,7340,L-4354266,00.html
+test_url: http://www.ynet.co.il/articles/0,7340,L-4354268,00.html
+#feed
 test_url: http://www.ynet.co.il/Integration/StoryRss2.xml
 \ No newline at end of file