diff options
104 files changed, 927 insertions, 50 deletions
diff --git a/.about.com.txt b/.about.com.txt index 9dec650..3953d3e 100644 --- a/.about.com.txt +++ b/.about.com.txt @@ -1,4 +1,3 @@ title: //*[@id='title']//h1 body: //*[(@id = "articlebody")] -date: //*[(@id = "date")] test_url: http://nutrition.about.com/od/changeyourdiet/qt/healthysnacks.htm
\ No newline at end of file diff --git a/abc.net.au.txt b/abc.net.au.txt index f864c97..2d99538 100644 --- a/abc.net.au.txt +++ b/abc.net.au.txt @@ -1,10 +1,13 @@ title: //h1 author: //div[@class="byline"]/a date: //span[@class="timestamp"] +body: //div[@class="page section"] +strip: //a[@class="inline-caption"] +strip: //p[@class="ticker section noprint"] strip: //p[@class="topics"] strip: //h1 strip: //div[@class="byline"] strip: //p[@class="published"] strip: //div[contains(@class,"featured-scroller")] -test_url: http://www.abc.net.au/news/2011-11-08/crabb-carbon-legislation-abbott-demolition/3652544
\ No newline at end of file +test_url: http://www.abc.net.au/news/2013-03-27/open-speed-highways-change-clp-giles/4597892
\ No newline at end of file diff --git a/aftenposten.no.txt b/aftenposten.no.txt new file mode 100644 index 0000000..8a69c35 --- /dev/null +++ b/aftenposten.no.txt @@ -0,0 +1,5 @@ +title: //h1[@class='articleTitle '] +body: //div[@class='bodyText widget storyContent'] +strip: //p/span[@class='quote']/.. +strip_id_or_class: 'pull1' +test_url: https://www.aftenposten.no/meninger/spaltister/Portrett-av-scenekunstneren-som-ung-mann-7167959.html
\ No newline at end of file diff --git a/alexduner.com.txt b/alexduner.com.txt new file mode 100644 index 0000000..bd9de9d --- /dev/null +++ b/alexduner.com.txt @@ -0,0 +1,4 @@ +body: //section[@class='content'] +date: //span[1] +author: //h1[@id='sitetitle'] +test_url: https://alexduner.com/blog/2013/1/something-i-learned-today
\ No newline at end of file diff --git a/alexduner.squarespace.com.txt b/alexduner.squarespace.com.txt new file mode 100644 index 0000000..875405e --- /dev/null +++ b/alexduner.squarespace.com.txt @@ -0,0 +1,4 @@ +body: //section[@class='content'] +date: //span[1] +author: //h1[@id='sitetitle'] +test_url: https://alexduner.squarespace.com/blog/2013/1/tech-culture-from-the-outside-looking-in
\ No newline at end of file diff --git a/amptoons.com.txt b/amptoons.com.txt new file mode 100644 index 0000000..87547c6 --- /dev/null +++ b/amptoons.com.txt @@ -0,0 +1,8 @@ +title: //title + +body: //div[@class="entry-content"] + +author: //span[@class="author vcard"] + +date: //span[@class="entry-date"] +test_url: http://www.amptoons.com/blog/2013/03/14/open-thread-and-link-farm-i-hate-being-sick-edition/
\ No newline at end of file diff --git a/baseballprospectus.com.txt b/baseballprospectus.com.txt new file mode 100644 index 0000000..1207b34 --- /dev/null +++ b/baseballprospectus.com.txt @@ -0,0 +1,13 @@ +title: //h1[@class='title'] +author: //p[@class="author"]/a[1] +body: //div[@class="article"] +date: //p[@class="date"] + +# remove user tools +strip: //div[@class='tools'] +strip: //h1 +strip: //h2[@class='subtitle'] +strip: //p[@class='author'] +strip: //p[@class='date'] + +test_url: http://www.baseballprospectus.com/article.php?articleid=18463
\ No newline at end of file diff --git a/blog.foreignpolicy.com.txt b/blog.foreignpolicy.com.txt new file mode 100644 index 0000000..719a3da --- /dev/null +++ b/blog.foreignpolicy.com.txt @@ -0,0 +1,10 @@ +title: //title +author: //span[@class="post_by"]/a/text() +date: //span[@class="post_date"] +body: //div[@class="translateBody"] + +#Strip article junk +strip: //div[@id="share-box"] +strip: //div[@id="fb-meta-like"] + +test_url: http://blog.foreignpolicy.com/posts/2013/04/01/us_is_running_out_of_fancy_planes_to_send_to_korea?wpisrc=obinsite
\ No newline at end of file diff --git a/blog.instapaper.com.txt b/blog.instapaper.com.txt new file mode 100644 index 0000000..fda01b1 --- /dev/null +++ b/blog.instapaper.com.txt @@ -0,0 +1,9 @@ +author: //a[@href="http://www.marco.org/about"] +date: //span[@class="date"] + +# Remove the date from article body. +strip: //span[@class="date"] + +# Remove pagination links from article body. +strip: //div[@id="pagination"] +test_url: http://blog.instapaper.com/post/31303984531
\ No newline at end of file diff --git a/blog.renren.com.txt b/blog.renren.com.txt new file mode 100644 index 0000000..401d31e --- /dev/null +++ b/blog.renren.com.txt @@ -0,0 +1,11 @@ +# This filter is tested on: +# http://blog.renren.com/share/224959024/14260739544 +# http://blog.renren.com/share/231323504/14261768898 +# http://blog.renren.com/share/230305019/1502806705 + +title://h1[contains(@class, 'title-article')] +author://span[contains(@class, 'name')] +body://div[contains(@class, 'content-body')] + +convert_double_br_tags:yes +test_url: http://blog.renren.com/share/230305019/1502806705
\ No newline at end of file diff --git a/bowdoinorient.com.txt b/bowdoinorient.com.txt new file mode 100644 index 0000000..932143d --- /dev/null +++ b/bowdoinorient.com.txt @@ -0,0 +1,6 @@ +title: //*[@class='articletitle'] +body: //*[(@id='articlebody')] +date: //*[(@class='articledate')] +author: //*[(@class='articleauthor')] +autodetect_next_page: no +test_url: http://bowdoinorient.com/article/8045
\ No newline at end of file diff --git a/bt.no.txt b/bt.no.txt new file mode 100644 index 0000000..200c2e4 --- /dev/null +++ b/bt.no.txt @@ -0,0 +1,12 @@ +title: //h1[contains(@class,'articleTitle')] +author: //span[@itemprop='name'] +date: //time[@class='published'] +body: //div[contains(@class,'bodyText')] + +strip_id_or_class: 'pull1' +strip_id_or_class: 'relationArticle' +strip: //span[@class='quote'] + +# strip h2 if at end of article (typically a request for comments) +strip: //div[contains(@class,'bodyText')]/node()[last()-1]/self::h2 +test_url: http://www.bt.no/meninger/debatt/Typisk-norsk-a-vare-god-nok-2884108.html
\ No newline at end of file diff --git a/chrisltd.com.txt b/chrisltd.com.txt new file mode 100644 index 0000000..86d0f5d --- /dev/null +++ b/chrisltd.com.txt @@ -0,0 +1,6 @@ +title: //header/h1/b[contains(@class, 'title')] +author: substring-after(//article/header/div, 'By ') +date: //header/h1/span[contains(@class, 'date')] +body: //div[@id='main]/article +strip: //header +test_url: http://chrisltd.com/blog/2012/03/fix-widows-indesign/
\ No newline at end of file diff --git a/ciaosamin.com.txt b/ciaosamin.com.txt new file mode 100644 index 0000000..02fd343 --- /dev/null +++ b/ciaosamin.com.txt @@ -0,0 +1,4 @@ +body://div[contains(@class, 'entry-content')] +date://h2[contains(@class, 'date-header')] +title://h3[contains(@class, 'post-title')] +test_url: http://www.ciaosamin.com/2013/04/how-this-happened.html
\ No newline at end of file diff --git a/classyllama.com.txt b/classyllama.com.txt new file mode 100644 index 0000000..1864eee --- /dev/null +++ b/classyllama.com.txt @@ -0,0 +1,6 @@ +date: //div[@id='content']//p[contains(@class, 'date')]/span +author: substring-after(//div[@id='content']//div[contains(@class, 'over-under-bars')]/p[last()]/text(), 'Posted by ') +body: //div[@id='content']//div[@class='pane-content'] +strip_id_or_class: trackback-url +strip_id_or_class: over-under-bars +test_url: http://www.classyllama.com/content/layout-caching
\ No newline at end of file diff --git a/codeproject.com.txt b/codeproject.com.txt new file mode 100644 index 0000000..d1191ac --- /dev/null +++ b/codeproject.com.txt @@ -0,0 +1,3 @@ +body: //div[@id="contentdiv"] +date: //span[@class="date"] +test_url: http://www.codeproject.com/Articles/499902/Profiling-Entity-Framework-5-in-code
\ No newline at end of file diff --git a/cooper.com.txt b/cooper.com.txt new file mode 100644 index 0000000..a424409 --- /dev/null +++ b/cooper.com.txt @@ -0,0 +1,4 @@ +body: //*[contains(@class,'body')] +date: //abbr[@class='published'] + +test_url: http://www.cooper.com/journal/2012/08/2-weeks-left-to-win-your-way-to-the-woodstock-of-ux-coopers-ux-boot-camp.html/
\ No newline at end of file diff --git a/css-tricks.com.txt b/css-tricks.com.txt new file mode 100644 index 0000000..3d8174a --- /dev/null +++ b/css-tricks.com.txt @@ -0,0 +1,6 @@ +title://article[contains(@id, "post-")]/h1 +date://article[contains(@id, "post-")]/p[@class="time"]/time +body://article[contains(@id, "post-")] +strip://article[contains(@id, "post-")]/p[@class="time"]/time +prune:yes +test_url: http://css-tricks.com/off-canvas-menu-with-css-target/
\ No newline at end of file diff --git a/cw.com.tw.txt b/cw.com.tw.txt new file mode 100644 index 0000000..6e3a91e --- /dev/null +++ b/cw.com.tw.txt @@ -0,0 +1,14 @@ +author://span[contains(@class,'reporter')] + +date://span[contains(@class,'date')] + +body://div[contains(@class,'mainContaner')] + +strip://div[contains(@class,'mainHeaer')] +strip://div[contains(@class,'keyW')] +strip://div[contains(@class,'wonderful')] +strip://div[contains(@class,'pages')] +strip://div[contains(@class,'Topics TopicsW3')] + +next_page_link://li[@class='pageNext']/a[contains(.,'下一頁')] +test_url: http://www.cw.com.tw/article/article.action?id=5032848
\ No newline at end of file diff --git a/dagogtid.no.txt b/dagogtid.no.txt new file mode 100644 index 0000000..1531472 --- /dev/null +++ b/dagogtid.no.txt @@ -0,0 +1,4 @@ +title: //span[@class = 'overskriftEkstrastor'] +author: //em/a + +test_url: http://dagogtid.no/nyhet.cfm?nyhetid=2414
\ No newline at end of file diff --git a/dailystar.com.lb.txt b/dailystar.com.lb.txt new file mode 100644 index 0000000..3b15304 --- /dev/null +++ b/dailystar.com.lb.txt @@ -0,0 +1,6 @@ +title: //div[@class='ec-blog-headline'] +body: //*[@id="divDetails"] +date: //*[@id="ctl00_ContentPlaceHolder1_tdDate"] +author: //*[@id="ctl00_ContentPlaceHolder1_anchorAuthor"]/a +autodetect_next_page: no +test_url: http://dailystar.com.lb/Opinion/Columnist/2012/Oct-10/190803-americas-new-modesty-in-the-mideast.ashx#axzz2928JP5xE
\ No newline at end of file diff --git a/danleech.com.txt b/danleech.com.txt new file mode 100644 index 0000000..1d4cec7 --- /dev/null +++ b/danleech.com.txt @@ -0,0 +1,6 @@ +tidy: no +prune: no +date: //article//time[@pubdate] +title: //article/h1//span[contains(@class, 'entry-title')] +body: //article/div[contains(@class, 'entry-content')] +test_url: http://danleech.com/post/36822126876/simple-icons
\ No newline at end of file diff --git a/defomicron.net.txt b/defomicron.net.txt new file mode 100644 index 0000000..9f11258 --- /dev/null +++ b/defomicron.net.txt @@ -0,0 +1,9 @@ +title: //article/h1 +author: //hgroup/h3/a +date: //time +body: //article +strip: //aside +footnotes: yes +prune: no +tidy: no +test_url: https://defomicron.net/2012/09/ios-6/
\ No newline at end of file diff --git a/dobreprogramy.pl.txt b/dobreprogramy.pl.txt new file mode 100644 index 0000000..972293b --- /dev/null +++ b/dobreprogramy.pl.txt @@ -0,0 +1,6 @@ +title: //*[@class="news"]//h1[@class="title"] +author: //*[@class="news"]//*[@class="newsInfo"]/a +date: substring-before(//*[@class="news"]//*[@class="newsInfo"]/text(), ',') +body: //*[@class="news"]//*[@class="newsContent"] +footnotes: no +test_url: http://www.dobreprogramy.pl/Sony-konczy-z-Foldinghome-na-PS3,Aktualnosc,36899.html
\ No newline at end of file diff --git a/dushumashang.com.txt b/dushumashang.com.txt new file mode 100644 index 0000000..6a50a77 --- /dev/null +++ b/dushumashang.com.txt @@ -0,0 +1,17 @@ +# This filter is tested on: +# http://www.dushumashang.com/2389 +# http://www.dushumashang.com/2415 +# http://www.dushumashang.com/2355 + +body://div[@class='main_content'] +#body://section[@class='entry_content fl'] +title://h2 +author://span[@class='article_author']/a +date://span[@class='pub_date']/time + +strip://span[@class='article_author'] +strip://span[@class='pub_date'] +strip://div[@class='page_turn'] +strip://span[@class='source_link']/em +wrap_in(strong)://span[@class='source_link']/a +test_url: http://www.dushumashang.com/2355
\ No newline at end of file diff --git a/economist.com.txt b/economist.com.txt index eb7ddd7..16c9ed6 100644 --- a/economist.com.txt +++ b/economist.com.txt @@ -1,8 +1,6 @@ -title: //div[@class='ec-blog-headline'] -body: //div[@class='ec-blog-body'] -body: //div[@class='ec-article-content clear'] -strip: //div[@class='related-items'] -date: substring-before(//p[@class='ec-article-info'], '|') +body: //div[@class='main-content'] +date: //time[@class='date-created'] +strip: //aside prune: no autodetect_next_page: no diff --git a/ericsuh.com.txt b/ericsuh.com.txt new file mode 100644 index 0000000..d25140c --- /dev/null +++ b/ericsuh.com.txt @@ -0,0 +1,4 @@ +date: //h6[@class='datetime']/child::text() +author: string("Eric J. Suh") +footnotes: yes +test_url: http://www.ericsuh.com/blog/posts/2012/8/strange-numbers.html
\ No newline at end of file diff --git a/escapistmagazine.com.txt b/escapistmagazine.com.txt index 7e17a04..fd453a1 100644 --- a/escapistmagazine.com.txt +++ b/escapistmagazine.com.txt @@ -1,2 +1,8 @@ +title: //h1[@class='headline']/div[@class='name'] + +strip_image_src: 'http://cdn.themis-media.com/media/global/images/library/deriv/115/115825.png' + +next_page_link: //a[@class='next_page'] + strip_comments: no -test_url: http://www.escapistmagazine.com/articles/view/columns/extraconsideration/8717-Extra-Consideration-The-Story
\ No newline at end of file +test_url: http://www.escapistmagazine.com/articles/view/columns/criticalintel/10302-I-Hate-Magic
\ No newline at end of file diff --git a/falter.at.txt b/falter.at.txt index 0dc9d80..2bfcc9b 100644 --- a/falter.at.txt +++ b/falter.at.txt @@ -1,18 +1,14 @@ -title: //h2[@class='related relatedTitle'] -author: //a[contains(@href, 'liste.php?author_id')] - -# can't think of a better way unfortunately, really bad markup on this site -date: substring-after(//td[@style='width:85%;'], 'vom') - -# not sure why, but instapaper seems to suck up the teaser paragraph -# not solved! -body: //div[contains(@class, 'teaser')] -body: //div[@id='content'] +title: //h1 +author: //a[contains(@href, '/kategorie/autoren')] +date: //a[contains(@href, '/falter/ausgabe')] +body: //article[@class='spanMain'] # cleanup +strip_id_or_class: 'respond' strip: //img[@src='http://www.falter.at/web/_pics/falterlogo_dblau.gif'] -strip: //div[@class='servicebox'] -strip: //h1 +strip_id_or_class: 'meta' +strip_id_or_class: 'servicebox' +strip_id_or_class: 'related' +strip_id_or_class: 'twitter-share-button' strip: //br -strip: //td[@id='adcol'] -test_url: http://www.falter.at/web/print/detail.php?id=1634
\ No newline at end of file +test_url: http://www.falter.at/falter/2013/03/26/der-dandy-auf-der-sinkenden-galeere/
\ No newline at end of file diff --git a/faz.net.txt b/faz.net.txt index 6256b0b..d087d2a 100644 --- a/faz.net.txt +++ b/faz.net.txt @@ -20,6 +20,9 @@ strip: //div[@class='clear'] # General removements strip: //span[@class='Bildnachweis'] +strip: //img[@class='MediaIcon'] +strip: //div[@class='ArtikelMediaLink'] +dissolve: //a[img] # Removements after body text strip: //div[@class='ArtikelAbbinder'] @@ -27,4 +30,7 @@ strip: //div[@class='ArtikelKommentieren Artikelfuss GETS;tk;boxen.top-lesermein strip: //div[@class='FAZArtikelKommentare FAZArtikelContent'] strip: //div[@class='FAZArtikelFunktionen'] strip: //div[@id='FAZContentRight'] -test_url: http://www.faz.net/aktuell/gesellschaft/ehe-haltbarkeitsformel-verliebe-dich-oft-verlobe-dich-selten-heirate-vielleicht-11685306.html
\ No newline at end of file + +# Fix picture captions +wrap_in(small): //span[@class='Bildunterschrift']/text() +test_url: http://www.faz.net/aktuell/feuilleton/zum-tod-von-margaret-thatcher-die-reizfigur-12141919.html#Drucken
\ No newline at end of file diff --git a/flyingmachinestudios.com.txt b/flyingmachinestudios.com.txt new file mode 100644 index 0000000..2053f80 --- /dev/null +++ b/flyingmachinestudios.com.txt @@ -0,0 +1,2 @@ +strip_id_or_class: linenos +test_url: http://www.flyingmachinestudios.com/programming/whoops-dci-refactoring/
\ No newline at end of file diff --git a/folklore.org.txt b/folklore.org.txt new file mode 100644 index 0000000..ed23a0b --- /dev/null +++ b/folklore.org.txt @@ -0,0 +1,4 @@ +author: /html/body/table[3]/tbody/tr/td[1]/table[2]/tbody/tr[1]/td[2] +date: /html/body/table[3]/tbody/tr/td[1]/table[2]/tbody/tr[2]/td[2] +body: //div[@class='main'] +test_url: http://www.folklore.org/StoryView.py?story=Calculator_Construction_Set.txt
\ No newline at end of file diff --git a/forbes.com.txt b/forbes.com.txt index 74fc0e1..9e1d04c 100644 --- a/forbes.com.txt +++ b/forbes.com.txt @@ -10,7 +10,18 @@ date: substring-before(//hgroup//h6, '@') date: //span[@class='mainartdate'] prune: no +strip: //aside +strip_id_or_class: sticky_sharing +strip_id_or_class: pagination +strip_id_or_class: controlsbox +strip_id_or_class: storyboxes +strip_id_or_class: sponsoredlinks +strip_id_or_class: nextpage +strip_id_or_class: contextuallinks +strip_id_or_class: article_actions +strip_id_or_class: engagement_block single_page_link: //a[contains(@href, '/print/')] -test_url: http://www.forbes.com/forbes/2011/0509/technology-frog-design-jan-chipchase-ethnographer-birth-cool_print.html
\ No newline at end of file +test_url: http://www.forbes.com/forbes/2011/0509/technology-frog-design-jan-chipchase-ethnographer-birth-cool_print.html +test_url: http://www.forbes.com/sites/bruceupbin/2012/09/11/the-iphone-5-winners-and-losers/
\ No newline at end of file diff --git a/foreignaffairs.com.txt b/foreignaffairs.com.txt new file mode 100644 index 0000000..cf8b742 --- /dev/null +++ b/foreignaffairs.com.txt @@ -0,0 +1,34 @@ +# TIDY +#tidy: no +# PRUNE +#prune: no + +# SINGLE PAGE +single_page_link: //div[@class='showlinks']/a + +# TITLE +title: //h1[@class="title"] + +# AUTHOR +author: //div[contains(@class,"field-field-article-display-authors")]/div/div/a/text() + +# DATE +date: //div[contains(@class,"field-field-article-issue")]/div/div/a/text() | //span[@class="date-display-single"] + +# BODY +body: //div[contains(@class,"content-resize")] + +# Remove clutter +strip: //div[@class="article-sidebar"] +strip: //div[@class="showlinks"] +strip: //div[contains(@class,"premium-box")] +strip: //div[contains(@class,"premium-box")] +strip: //table[contains(@border,"2")] + +# Fix picture captions +wrap_in(small): //p/img/following-sibling::em +wrap_in(small): //p[img]/text() + +# Fix sub-headlines +wrap_in(h3): //div[contains(@class,"field-field-article-subtitle")]/div/div/text() +test_url: http://www.foreignaffairs.com/articles/138810/pierre-n-leval/the-long-arm-of-international-law
\ No newline at end of file diff --git a/foreignpolicy.com.txt b/foreignpolicy.com.txt index 6a02326..4e84b98 100644 --- a/foreignpolicy.com.txt +++ b/foreignpolicy.com.txt @@ -1,11 +1,15 @@ -title: //div[@id='art-mast']//h1 +title: //div[@class='translateHead']//h1 | //div[@id='art-mast']//h1 author: substring-after(//span[@id='by-line'], 'BY ') date: //span[@id='pub-date'] -body: //div[@id='art-mast']//h2 | //div[@id='art-mast']/h3 | //div[@id='art-body']//div[@class='translateBody'] +body: //div[@id='art-mast']/h2 | //div[@class='translateBody'] | //div[@id='art-body'] +#Strip inside article content strip: //div[@id='share-box'] +strip: //div[@id='special-box'] + prune: no single_page_link: //span[@id='controls']/a[contains(@href, 'print=yes')] +single_page_link: //a[text()='SINGLE PAGE'] test_url: http://www.foreignpolicy.com/articles/2011/08/01/a_murderers_manifesto_and_me -test_url: test_url: http://www.foreignpolicy.com/articles/2012/02/29/five_years_in_damascus
\ No newline at end of file +test_url: http://www.foreignpolicy.com/articles/2012/02/29/five_years_in_damascus
\ No newline at end of file diff --git a/ftchinese.com.txt b/ftchinese.com.txt new file mode 100644 index 0000000..5c94d9b --- /dev/null +++ b/ftchinese.com.txt @@ -0,0 +1,18 @@ +# Modified to define the single_page_link +# This filter is tested on: +# http://www.ftchinese.com/story/001047373 +# http://www.ftchinese.com/story/001047631 +# http://www.ftchinese.com/story/001047622/?print=y +# http://www.ftchinese.com/story/001049052 +# http://www.ftchinese.com/story/001049088 + +title:substring-before(//title, '-') +author: //div[@class='byline']/a +date: //a[@class='storytime'] +#Set date in print view +#date: //div[@class='byline']/a/following-sibling::a +body: //div[@id="bodytext"] +strip://div[@class='pagination'] +single_page_link://div[@class='pagination']/a[.='全文'] +#next_page_link: //div[@class='pagination']//a[.='下一页'] +test_url: http://www.ftchinese.com/story/001049088
\ No newline at end of file diff --git a/gamechurch.com.txt b/gamechurch.com.txt new file mode 100644 index 0000000..c9eea5f --- /dev/null +++ b/gamechurch.com.txt @@ -0,0 +1,10 @@ +title: //h1[@class='title'] + +date: substring-before(substring-after(//div[@class='comment-bubble']/.., 'Posted'), 'by') + +body: //div[@class='the-content'] + +strip: //div[@class='article-image responsive'] + +strip_id_or_class: 'pullquote' +test_url: http://gamechurch.com/virtual-gun-control-the-best-amendment/
\ No newline at end of file diff --git a/gamer.no.txt b/gamer.no.txt new file mode 100644 index 0000000..e76a59d --- /dev/null +++ b/gamer.no.txt @@ -0,0 +1,11 @@ +body: //div[@class='pageContent description'] +date: //div[@class='authorsAndDateTime']/span[@title] +single_page_link: //div[@class='pages']/a[last()-1] + +# fix images and captions +wrap_in(figure): //div[contains(concat(' ', @class, ' '), ' image')] +wrap_in(figcaption): //div[contains(concat(' ', @class, ' '), ' image')]/div[@class='text']/text() + +# get rid of videos +strip_id_or_class: 'video full' +test_url: http://www.gamer.no/artikler/142455/slik-blei-ambisiose-dragons-dogma-skapt/
\ No newline at end of file diff --git a/gamereactor.no.txt b/gamereactor.no.txt new file mode 100644 index 0000000..6f7c1b9 --- /dev/null +++ b/gamereactor.no.txt @@ -0,0 +1,11 @@ +title: //div[@id='content']/div/h1 + +author: //a[@itemprop='reviewer'] + +date: //time[@itemprop='dtreviewed']/@datetime + +body: //div[@id='breadtext'] + +# fix for NOT magically removing anchors with text identical to title +dissolve: //a[text()=//div[@id='content']/div/h1/text()] +test_url: http://www.gamereactor.no/previews/177481/The+Evil+Within/?sid=38b5bd30f56f1b7214de4ff5bed4b76f
\ No newline at end of file diff --git a/gigaom.com.txt b/gigaom.com.txt index dd86f29..cc8fdfa 100644 --- a/gigaom.com.txt +++ b/gigaom.com.txt @@ -1,17 +1,12 @@ -date: //meta[@name='DC.date.issued']/@content -date: //span[@class='post-meta the-date'] - +date: //meta[@name='dcterms.created']/@content title: //meta[@property='og:title']/@content +author: //section[@class="post-meta"]//a[@rel="author"] -author: //meta[@name='DC.creator']/@content - -body: //div[contains(@class, 'post-sub-head') or starts-with(@id, 'post-content-')] - -find_string: id="content" -replace_string: id="content-ignore" +body: //div[starts-with(@id, 'post-content-')] strip_id_or_class: sharedaddy prune: no -test_url: http://gigaom.com/2011/10/24/groupon-google-lawsuit/
\ No newline at end of file +test_url: http://gigaom.com/2011/10/24/groupon-google-lawsuit/ +test_url: http://gigaom.com/2012/12/26/snapchat-rises-why-pokes-decline-shows-facebooks-inability-to-invent/
\ No newline at end of file diff --git a/gloswielkopolski.pl.txt b/gloswielkopolski.pl.txt new file mode 100644 index 0000000..1648795 --- /dev/null +++ b/gloswielkopolski.pl.txt @@ -0,0 +1,8 @@ +title: //article[@id='material']/header/h1 +author: //article[@id='material']/header/div[2]/p +date: //article[@id='material']/header/p/time[1] +body: //section[@id='tresc'] +next_page_link: .//section[@id='tresc']/div[@class='stronicowanie']/a[@rel='next'] +strip://div[@class='podobneSonda'] + +test_url: http://www.gloswielkopolski.pl/artykul/803547,abc-telemarketingu-praca-ktora-zwalnia-z-myslenia,id,t.html
\ No newline at end of file diff --git a/goodfil.ms.txt b/goodfil.ms.txt new file mode 100644 index 0000000..f8bbbc6 --- /dev/null +++ b/goodfil.ms.txt @@ -0,0 +1,2 @@ +strip_id_or_class: gutter +test_url: http://goodfil.ms/blog/posts/2012/08/13/angularjs-and-the-goodfilms-mobile-site-part-1/
\ No newline at end of file diff --git a/hackmake.org.txt b/hackmake.org.txt new file mode 100644 index 0000000..9814011 --- /dev/null +++ b/hackmake.org.txt @@ -0,0 +1,7 @@ +date: //article//time[@pubdate] +body: //article/div[@id="post-wide"] +title: //article/header/h2 +strip: /div[@id="comment"] +strip: //footer +author: substring-after(//footer/p[@class='byline'] , 'By') +test_url: http://hackmake.org/2012/12/21/mindfulness-of-concentration
\ No newline at end of file diff --git a/handelsblatt.com.txt b/handelsblatt.com.txt new file mode 100644 index 0000000..7d067aa --- /dev/null +++ b/handelsblatt.com.txt @@ -0,0 +1,31 @@ +#Single Page +single_page_link: //li[contains(@class,"hcf-print")]/a + +# Title hcf-headline +title: //span[@class='hcf-headline'] + +# Authors +author: //div[@class="hcf-author"]/a/text() +author: substring-after(//div[@class='hcf-author'], 'von ') + +# Date +date: //div[@class='hcf-article-date'] + +# Body +body: //div[@class='article'] + +# General removements +strip: //div[contains(@class,"hcf-smartbox")] +strip: //div[contains(@class,"hcf-stopper")] +strip: //div[contains(@class,"hcf-img-controls")] +strip: //span[@class='hcf-location-mark'] +strip: //span[@class='hcf-copyright'] +strip: //div[@class='hcf-copyright'] +strip: //div[@class='hcf-origin'] + + + + +# Fix picture captions +wrap_in(small): //div[@class="hcf-caption"] +test_url: http://www.handelsblatt.com/meinung/gastbeitraege/gastkommentar-zum-emissionshandel-kurskorrekturen-fuehren-zum-kentern/8044326.html
\ No newline at end of file diff --git a/hardware.no.txt b/hardware.no.txt new file mode 100644 index 0000000..38ea9f1 --- /dev/null +++ b/hardware.no.txt @@ -0,0 +1,16 @@ +title: //h1[@class='headline'] +title: //h2[@itemprop='alternativeHeadline'] +title: //h1[@itemprop='headline'] +author: //span[@itemprop='name'] +date: //time[@itemprop='datePublished'] +body: //div[@itemprop='reviewBody'] + +wrap_in(blockquote): //div[@class='factBox'] + +next_page_link: //a[@rel='next'] + +strip_id_or_class: 'product-box' +strip: //a[@rel='next'] +strip: //a[text()='Del p Facebook'] +strip: //a[text()='Del p Twitter'] +test_url: http://www.hardware.no/artikler/asus-vg248qe/132792
\ No newline at end of file diff --git a/hbr.org.txt b/hbr.org.txt index 990b417..c2f292e 100644 --- a/hbr.org.txt +++ b/hbr.org.txt @@ -2,5 +2,6 @@ title: //div[@id='article-title'] author: //div[@id='articleAuthors'] body: //div[@id='article'] strip: //div[@class='module wide'] -next_page_link: //a[@title='Next Page'] -test_url: http://hbr.org/2012/04/the-real-leadership-lessons-of-steve-jobs/ar/
\ No newline at end of file +#single_page_link: //a[@class='social-print'] +test_url: http://hbr.org/2012/04/the-real-leadership-lessons-of-steve-jobs/ar/ +test_url: http://hbr.org/2013/03/big-bang-disruption/ar/
\ No newline at end of file diff --git a/headrush.typepad.com.txt b/headrush.typepad.com.txt new file mode 100644 index 0000000..a314677 --- /dev/null +++ b/headrush.typepad.com.txt @@ -0,0 +1,14 @@ +title://div[@class='content']/h3[1] +body://div[@class='content'] + +# Article nav +strip://div[@class='content']/p[1] + +# Comments and trackbacks +strip://h2/following-sibling::p +strip://h2 + +# Posted on +strip://b/p +strip://div[@class='content']/p[@class='posted'] +test_url: http://headrush.typepad.com/creating_passionate_users/2005/05/the_case_for_ea.html
\ No newline at end of file diff --git a/icannabis.tumblr.com.txt b/icannabis.tumblr.com.txt new file mode 100644 index 0000000..3bda753 --- /dev/null +++ b/icannabis.tumblr.com.txt @@ -0,0 +1,9 @@ +tidy:no +prune:no + +body://div[contains(@id,'content')] + +strip_id_or_class:meta +strip_id_or_class:notes +strip_id_or_class:pagination +test_url: http://icannabis.tumblr.com/post/28660592471/reviewmswireless3000
\ No newline at end of file diff --git a/idealog.co.nz.txt b/idealog.co.nz.txt new file mode 100644 index 0000000..ca88f60 --- /dev/null +++ b/idealog.co.nz.txt @@ -0,0 +1,12 @@ +body: //div[@class='content'] + +strip: //p[@class='dateline'] +strip: //hr +strip_id_or_class: share +strip_id_or_class: comments +strip_id_or_class: tags + +title: substring-before(//title,' ::') +author: substring-before(//p[@class='dateline'],',') +date: //p[@class='dateline']/time +test_url: http://www.idealog.co.nz/blog/2012/12/geeks-plane-help-kiwis-take-san-francisco
\ No newline at end of file diff --git a/lifeweek.com.cn.txt b/lifeweek.com.cn.txt new file mode 100644 index 0000000..e09f669 --- /dev/null +++ b/lifeweek.com.cn.txt @@ -0,0 +1,23 @@ +# This filter is tested on: +# http://www.lifeweek.com.cn/2012/1211/39439.shtml +# http://www.lifeweek.com.cn/2013/0308/40213.shtml + +title:substring-before(//h1, '（') +title://h1 +date://ul[@class='authorbox']/li +author: substring-after(//ul[@class='authorbox']/li/following-sibling::li, '作者：') + +next_page_link: //div[@class='pageturn_list']/a[@class='pagedown'] +body: //div[@class='original '] + +strip://h1 +strip://ul[@class='authorbox'] +strip://span[@class='app_p'] +strip://div[@style='text-align:right;'] +strip://div[@class='pageturn_list'] +strip://div[@class='lifespeaks'] +strip://div[@class='vright fr'] +strip://div[@class='copyrt mg20'] +strip://div[@class='keyabout mg20'] +strip://ul[@class='readabout mg20'] +test_url: http://www.lifeweek.com.cn/2013/0308/40213.shtml
\ No newline at end of file diff --git a/m.douban.com.txt b/m.douban.com.txt new file mode 100644 index 0000000..ce9a316 --- /dev/null +++ b/m.douban.com.txt @@ -0,0 +1,13 @@ +# This filter is tested on: +# http://m.douban.com/note/240776310/?session=6ac86d1e +# http://m.douban.com/note/208270705/?session=e00ec732_3433229 + +title: //h2 +author: //a[@class='founder'] +date: substring-after(//span[@class='info'],' | ') +body: //div[contains(@class,'entry item')] + +strip://span[contains(@class,'info')] + +convert_double_br_tags: yes +test_url: http://m.douban.com/note/240776310/?session=6ac86d1e
\ No newline at end of file diff --git a/m.vanityfair.com.txt b/m.vanityfair.com.txt new file mode 100644 index 0000000..e47ce2c --- /dev/null +++ b/m.vanityfair.com.txt @@ -0,0 +1,11 @@ +# Article Metadata +title: //h1 +author: //span[@class="name"]/a +date: //time + +# Content Pruning +strip: //h5 +strip: //time +strip: //div[@class="byline"] +strip: //h2[@class="headline "] +test_url: http://m.vanityfair.com/politics/2012/10/michael-lewis-profile-barack-obama
\ No newline at end of file diff --git a/manager.co.th.txt b/manager.co.th.txt new file mode 100644 index 0000000..cd6c5c0 --- /dev/null +++ b/manager.co.th.txt @@ -0,0 +1,26 @@ +title: //td[@class="headline"] +author: //font[@color="#003366"] +date: //td[@class="date"] + +strip: //td[@class="headline"] +strip: //font[@color="#003366"] +strip: //td[@class="date"] + +strip: //img[@src="images/2009/logo_en.gif"] + +body: //tbody[@class="body"] +convert_double_br_tags:yes + +strip: //img[@src="/images/TabOver.gif"] +strip: //td[@width="160"] +strip: //img[@src="/images/TabUnder.gif"] + +strip: //td[@class="small"] +strip: //td[@height="47"] + +strip: //td[@valign="middle"] +strip: //td[@background="/images/menu_bottombg.gif"] +strip: //img[@src="/images/sc_footer_l.gif"] +strip: //img[@src="/images/sc_footer_m.gif"] +strip: //img[@src="/images/sc_footer_r.gif"] +test_url: http://www.manager.co.th/Entertainment/ViewNews.aspx?NewsID=9550000101979
\ No newline at end of file diff --git a/matt.might.net.txt b/matt.might.net.txt new file mode 100644 index 0000000..30d585c --- /dev/null +++ b/matt.might.net.txt @@ -0,0 +1,5 @@ +title: //h1 +author: string("Matt Might") +strip: //h1/following-sibling::div + +test_url: http://matt.might.net/articles/oo-cesk/
\ No newline at end of file diff --git a/movie.douban.com.txt b/movie.douban.com.txt new file mode 100644 index 0000000..b727315 --- /dev/null +++ b/movie.douban.com.txt @@ -0,0 +1,11 @@ +# This filter is tested on: +# http://movie.douban.com/review/1062013/ + +title: //span[contains(@property, 'v:summary')] +author: //span[contains(@property, 'v:reviewer')] +date://span[contains(@property, 'v:dtreviewed')] +body://div[contains(@class, 'note')]|//div[contains(@class, 'topic-content')] + +strip://img[contains(@class,'rating')]|//img[contains(@class,'review-stat')] +convert_double_br_tags: yes +test_url: http://movie.douban.com/review/1062013/
\ No newline at end of file diff --git a/newrepublic.com.txt b/newrepublic.com.txt new file mode 100644 index 0000000..039f038 --- /dev/null +++ b/newrepublic.com.txt @@ -0,0 +1,8 @@ +author: //span[@class="authors"] +date: //span[@class="date"] +body: //div[@class="primary"] + +strip: //div[@id="controls"] +strip: //div[@id="read-next"] + +test_url: http://www.newrepublic.com/article/112731/moocs-will-online-education-ruin-university-experience
\ No newline at end of file diff --git a/news.zing.vn.txt b/news.zing.vn.txt new file mode 100644 index 0000000..af81e90 --- /dev/null +++ b/news.zing.vn.txt @@ -0,0 +1,3 @@ +body://div[@class="newsdetail_wrapper"] +strip://div[@class="more_news"] +test_url: http://news.zing.vn/xa-hoi/s-phat-nang-xe-may-di-duong-tren-cao-ha-noi/a280838.html#home_noibat1
\ No newline at end of file diff --git a/newyorker.com.txt b/newyorker.com.txt index f1e2ffa..950324a 100644 --- a/newyorker.com.txt +++ b/newyorker.com.txt @@ -1,10 +1,11 @@ title: //h1[@id='articlehed'] | //h2[@id="articleintro"] body: //div[@id='articletext'] -strip: //ul[@id="bc"] | //div[@id="yrail"] | //div[@class="entry-keywords"] | //div[@class="entry-categories"] | //div[@class="socialUtils"] | //div[@id="footer"] +strip: //ul[@id="bc"] | //div[@id="yrail"] | //div[@class="entry-keywords"] | //div[@class="entry-categories"] | //div[@class="socialUtils"] | //div[@id="footer"] | //div[@class="cartoon"] date: //h4[@id='articleauthor']/span[@class='dd dds'] date: //div[@id="pagebody"]/div[@class='hentry entry']/div[@class='published'] single_page_link: //div[@class='paginationViewSinglePage']/a -test_url: http://www.newyorker.com/online/blogs/culture/2012/06/mug-shot-web-sites.html
\ No newline at end of file +test_url: http://www.newyorker.com/online/blogs/culture/2012/06/mug-shot-web-sites.html +test_url: http://www.newyorker.com/reporting/2013/04/22/130422fa_fact_bilger?currentPage=all&mobify=0
\ No newline at end of file diff --git a/omm.hk.txt b/omm.hk.txt new file mode 100644 index 0000000..c6dd29b --- /dev/null +++ b/omm.hk.txt @@ -0,0 +1,19 @@ +# 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 diff --git a/ontologicalgeek.com.txt b/ontologicalgeek.com.txt new file mode 100644 index 0000000..a9bf71e --- /dev/null +++ b/ontologicalgeek.com.txt @@ -0,0 +1,8 @@ +title: //h1[@class='entry-title'] + +author: //a[@rel='author'] + +date: substring-before(//aside[@class='entry-meta'], '|') + +body: //div[@class='entry-content'] +test_url: http://ontologicalgeek.com/change-or-live-final-fantasy-x-as-catholic-dystopia/
\ No newline at end of file diff --git a/oschina.net.txt b/oschina.net.txt new file mode 100644 index 0000000..5645153 --- /dev/null +++ b/oschina.net.txt @@ -0,0 +1,3 @@ +title: //h1 +strip_id_or_class: syntaxhighlighter +test_url: http://www.oschina.net/translate/event-based-programming-what-async-has-over-sync?print
\ No newline at end of file diff --git a/papodehomem.com.br.txt b/papodehomem.com.br.txt new file mode 100644 index 0000000..2c522da --- /dev/null +++ b/papodehomem.com.br.txt @@ -0,0 +1,6 @@ +title: //h2[@class="page_title"] +body: //div[@class="entry arquivo"] +author: //span[@class="author"] +footnotes: yes +prune: yes +test_url: http://papodehomem.com.br/um-relato-confessional-sobre-a-maioridade-penal/
\ No newline at end of file diff --git a/planetvita.de.txt b/planetvita.de.txt new file mode 100644 index 0000000..bfc3342 --- /dev/null +++ b/planetvita.de.txt @@ -0,0 +1,5 @@ +title: //div[@id='frnRahmen']/div/div[@id='content']/div[2]/h2 +author: //div[@id='content']/div[1]/div/a +body: //div[@id='content']/div[2]/span +strip: //div[@id='commenthead'] +test_url: http://www.planetvita.de/news/10389-psn-store-update-vom-03-april-neue-inhalte-fuer-psvita.html
\ No newline at end of file diff --git a/polygon.com.txt b/polygon.com.txt new file mode 100644 index 0000000..a561c67 --- /dev/null +++ b/polygon.com.txt @@ -0,0 +1,6 @@ +body: //article[@id='entry-top']/div[@class='float_wrapper'] +author: //header/p[@class='byline']/em/a +date: //header/p[@class='byline']/span[@class='timestamp'] + +strip: //div[@class='float_wrapper']/header +test_url: http://www.polygon.com/2013/4/5/4189028/donkey-kong-country-returns-3d-new-content
\ No newline at end of file diff --git a/portertech.ca.txt b/portertech.ca.txt new file mode 100644 index 0000000..2897cb5 --- /dev/null +++ b/portertech.ca.txt @@ -0,0 +1,3 @@ +author: //*[(@class = "author")] +date: //*[(@class = "date")] +test_url: http://portertech.ca/2012/12/10/iac-morning-market/
\ No newline at end of file diff --git a/publico.pt.txt b/publico.pt.txt new file mode 100644 index 0000000..bb6a05e --- /dev/null +++ b/publico.pt.txt @@ -0,0 +1,12 @@ +title: //h1[@class="entry-title"] +author: //span[@class="author"] +body: //article[@itemtype="http://schema.org/Article"] +date: //time[@itemprop="dateCreated"] + +strip: //header[@class="entry-header single-header"] +strip: //aside[@class="entry-assets"] +strip: //div[@class="entry-options entry-options-above group"] +strip: //div[@class="entry-options entry-options-below group"] + +convert_double_br_tags: yes +test_url: http://www.publico.pt/politica/noticia/passos-diz-que-se-limitacao-de-mandatos-fosse-para-todos-os-concelhos-estaria-claro-na-lei-1577691
\ No newline at end of file diff --git a/qctimes.com.txt b/qctimes.com.txt new file mode 100644 index 0000000..3c3edfe --- /dev/null +++ b/qctimes.com.txt @@ -0,0 +1,5 @@ +# this site seems to work OK in the web view, but only occasionally in the instapaper app itself. + +body: //div[@class='entry-content'] +author: //span[@class='byline'] +test_url: http://qctimes.com/news/local/woman-faces-perjury-charges-in-meth-case/article_83f4c470-956a-11e2-a921-001a4bcf887a.html
\ No newline at end of file diff --git a/racjonalista.pl.txt b/racjonalista.pl.txt new file mode 100644 index 0000000..19c719d --- /dev/null +++ b/racjonalista.pl.txt @@ -0,0 +1,5 @@ +author: /html/body/center/b +date: /html/body/table/tr[2]/td/i +single_page_link: //*[@id='oTxt']/table[3]/tr[2]/td/a[1] + +test_url: http://www.racjonalista.pl/kk.php/s,7214/q,Geneza.szubrawstwa
\ No newline at end of file diff --git a/ritholtz.com.txt b/ritholtz.com.txt new file mode 100644 index 0000000..d598479 --- /dev/null +++ b/ritholtz.com.txt @@ -0,0 +1,5 @@ +title: //div[@class='post']/h2 +author: substring-before(substring-after(//div[@class='alignright']/small, 'By '),'-') +date: substring-after(//div[@class='alignright']/small, '-') +strip: //div[@class='alignleft'] +test_url: http://www.ritholtz.com/blog/2012/09/situational-awareness/
\ No newline at end of file diff --git a/robertsspaceindustries.com.txt b/robertsspaceindustries.com.txt new file mode 100644 index 0000000..b0b90fb --- /dev/null +++ b/robertsspaceindustries.com.txt @@ -0,0 +1,4 @@ +strip_id_or_class: 'sharedaddy' +strip_id_or_class: 'respond' +strip_id_or_class: 'meta' +test_url: http://www.robertsspaceindustries.com/news-update-ai-pilots/
\ No newline at end of file diff --git a/robots.thoughtbot.com.txt b/robots.thoughtbot.com.txt new file mode 100644 index 0000000..da5b7bd --- /dev/null +++ b/robots.thoughtbot.com.txt @@ -0,0 +1,5 @@ +body: //section[@class='post text'] +title: //h1[@class='title'] +date: //p[@class='post-date'] +strip: //section[@class='meta-info'] +test_url: http://robots.thoughtbot.com/post/32455387133/four-phase-test
\ No newline at end of file diff --git a/scilogs.de.txt b/scilogs.de.txt new file mode 100644 index 0000000..99d45c0 --- /dev/null +++ b/scilogs.de.txt @@ -0,0 +1,15 @@ +title: //h1 +author: //div[@class='date']/a +date: substring-after(//div[@class='date'], ',') +body: //div[@class='entrybody'] + +strip_id_or_class: socialshareprivacy +strip: //div[@class='entrybody']/br[1] + +# Strip related articles +# 'p'-Tag strips 'hnliche Artikel: ' (<br> tags become <p>) +strip: //div[@class='entrybody']/p[last()] +strip: //div[@class='entrybody']/ul[last()] + +convert_double_br_tags: yes +test_url: http://www.scilogs.de/wblogs/blog/formbar/fusion/2012-10-08/rundgang-durch-deutschlands-gr-tes-fusionsexperiment
\ No newline at end of file diff --git a/select.yeeyan.org.txt b/select.yeeyan.org.txt new file mode 100644 index 0000000..6e98b14 --- /dev/null +++ b/select.yeeyan.org.txt @@ -0,0 +1,18 @@ +# This filter is tested on: +# http://select.yeeyan.org/view/18312/332365 +# http://select.yeeyan.org/view/365295/333788 +# http://select.yeeyan.org/view/174464/332336 + +tidy:no +prune:no +title://h1 +author: //div[@class='sa_author']/span/a +date: substring-after(//div[@class='sa_author']/span/following-sibling::span, '：') +body: //div[@class='sa_left closetag'] +wrap_in(b)://div[@class='sa_abstract'] + +strip://ul[@class='sa_next clearfix'] +strip: //div[@class='sa_author'] +strip: //div[@class='sa_title_box'] + +test_url: http://select.yeeyan.org/view/258033/333481
\ No newline at end of file diff --git a/sivers.org.txt b/sivers.org.txt new file mode 100644 index 0000000..a88f30d --- /dev/null +++ b/sivers.org.txt @@ -0,0 +1,6 @@ +title: //article[@class='post']/header[@class='wrapper']//h1/a +author: //header[@id='masthead']//h1/a +date: //article[@class='post']/header[@class='wrapper']//p[@class='postdate'] +body: //div[@id='body-content'] + +test_url: http://sivers.org/delegate/
\ No newline at end of file diff --git a/somethingawful.com.txt b/somethingawful.com.txt new file mode 100644 index 0000000..4854794 --- /dev/null +++ b/somethingawful.com.txt @@ -0,0 +1,17 @@ +title: //h1 +body: //div[@id = 'content-area'] +author: //p[contains(@class, 'byline')]/a +autodetect_next_page: yes +tidy: no + +strip_id_or_class: articleid +strip_id_or_class: logo +strip_id_or_class: pagebar +strip_id_or_class: featurenavlinks +strip_id_or_class: featured_frontpage +strip_id_or_class: sidebar +strip_id_or_class: footer +strip_id_or_class: byline +strip_id_or_class: logo +strip_id_or_class: nav_network +test_url: http://www.somethingawful.com/d/dungeons-and-dragons/wtf-monster-manual.php
\ No newline at end of file diff --git a/songshuhui.net.txt b/songshuhui.net.txt new file mode 100644 index 0000000..51a7ac7 --- /dev/null +++ b/songshuhui.net.txt @@ -0,0 +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'),' |')
+body://div[@class='entry'] +test_url: http://songshuhui.net/archives/74819
\ No newline at end of file diff --git a/sz.de.txt b/sz.de.txt new file mode 100644 index 0000000..51a30b4 --- /dev/null +++ b/sz.de.txt @@ -0,0 +1,18 @@ +# 2012-12-04: complete rewrite after Sddeutsche.de relaunch - carlo@... + +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 + +strip: //figure[ not( contains(@class, "zoomimage" ) ) ] +strip: //div[@data-onlineonly="true"] +strip: //address[@class="author"] + +test_url: http://sz.de/1.1556693
\ No newline at end of file diff --git a/tcmanila.tk.txt b/tcmanila.tk.txt new file mode 100644 index 0000000..f6032ec --- /dev/null +++ b/tcmanila.tk.txt @@ -0,0 +1,7 @@ +title: //h2 +body: //div[@class="post_content"] +author: //span[@class="fn"] +date: //time[@class="updated"] +strip_comments: //yes +footnotes: //yes +test_url: http://tcmanila.tk/post/29189064358/my-2012-roadmap-is-almost-complete-look-at-the
\ No newline at end of file diff --git a/tech.gilt.com.txt b/tech.gilt.com.txt new file mode 100644 index 0000000..ab56460 --- /dev/null +++ b/tech.gilt.com.txt @@ -0,0 +1,5 @@ +title: //div[@class="title"]/h1 +title: //div[@class="caption"]/h1 +author: substring-after(//div[@class="metadata"]/div[@class="date"]/a[2], 'by ') +date: //div[@class="metadata"]/div[@class="date"]/a +test_url: http://tech.gilt.com/post/46359463184/26-3-13-todays-noon-outage-and-what-were-doing-to
\ No newline at end of file diff --git a/techhive.com.txt b/techhive.com.txt new file mode 100644 index 0000000..29720b0 --- /dev/null +++ b/techhive.com.txt @@ -0,0 +1,18 @@ +title: //div[@class='articleHead']//h1 +author: //div[@class="author-name"]/a[1] +body: //div[@class="main"] + +# remove 'From the Lab' and 'Recent posts' text +strip: //div[@class='blogLabel'] + +# remove byline and meta info +strip: //div[@class="article-meta"] +strip: //div[@class="author-info"] + +#strip tags and categories +strip: //div[@class="department"] + +#strip product cap links +strip: //div[@class="cap-main"] +strip: //div[@id="compare-lede"] +test_url: http://www.techhive.com/article/2010549/up-close-with-blackberry-10.html
\ No newline at end of file diff --git a/technologizer.com.txt b/technologizer.com.txt new file mode 100644 index 0000000..179bf5a --- /dev/null +++ b/technologizer.com.txt @@ -0,0 +1,5 @@ +next_page_link: //a[contains(., 'NEXT PAGE')] +# following::node() selects text nodes too whereas following::* selects only elements. +strip: //span[@class='pageo']/following::node() +strip: //span[@class='pageo'] +test_url: http://technologizer.com/2010/03/08/the-secret-origin-of-windows/
\ No newline at end of file diff --git a/thanhnien.com.vn.txt b/thanhnien.com.vn.txt new file mode 100644 index 0000000..596ecc9 --- /dev/null +++ b/thanhnien.com.vn.txt @@ -0,0 +1,4 @@ +body://div[@id="print-news"] +strip://a +strip://span[@class="date-line"] +test_url: http://www.thanhnien.com.vn/pages/20121006/hon-90-trieu-usd-nang-cap-do-thi-can-tho.aspx
\ No newline at end of file diff --git a/the-magazine.org.txt b/the-magazine.org.txt new file mode 100644 index 0000000..0886465 --- /dev/null +++ b/the-magazine.org.txt @@ -0,0 +1,3 @@ +tidy: no + +test_url: http://the-magazine.org/1/alone-together-again
\ No newline at end of file diff --git a/theage.com.au.txt b/theage.com.au.txt new file mode 100644 index 0000000..ea27c31 --- /dev/null +++ b/theage.com.au.txt @@ -0,0 +1,5 @@ +author: //h3[@class='authorName'] +date: //time +body: //div[@class='articleBody'] +strip_id_or_class: adspot +test_url: http://www.theage.com.au/victoria/top-cops-warns-outlaw-bikies-we-have-a-gang-too-20130331-2h1l8.html
\ No newline at end of file diff --git a/theamericanscholar.org.txt b/theamericanscholar.org.txt new file mode 100644 index 0000000..38b9667 --- /dev/null +++ b/theamericanscholar.org.txt @@ -0,0 +1,13 @@ +# Article Metadata +title: //meta[@property="og:title"]/@content +author: substring-after(//h3, 'By ') +date: //h4/a[2] + +# Content Pruning +strip: //h4 +strip: //a[@id="print_button"] +strip: //p[@class="excerpt"] +strip: //h3 +strip: //div[@class="caption"] +strip: //center/a/img +test_url: http://theamericanscholar.org/too-big-to-fail-and-too-risky-to-exist/
\ No newline at end of file diff --git a/theatlantic.com.txt b/theatlantic.com.txt index 061f872..410cf0f 100644 --- a/theatlantic.com.txt +++ b/theatlantic.com.txt @@ -10,6 +10,9 @@ author: //*[@class='author']/span prune: no strip: //div[@class='moreOnBoxWithImages'] +strip: //p[contains(., 'This article available online at:')] +strip: //p[contains(., 'This article available online at:')]/following::* +strip: //div[@class='earthbox'] single_page_link: //a[@class='print'] diff --git a/theatlanticcities.com.txt b/theatlanticcities.com.txt new file mode 100644 index 0000000..880f207 --- /dev/null +++ b/theatlanticcities.com.txt @@ -0,0 +1,17 @@ +# To administrator: +# Please replace the hostname with "*.theatlanticcities.com" + +# This filter is tested on: +# http://m.theatlanticcities.com/arts-and-lifestyle/2012/04/invisible-borders-define-american-culture/1839/ +# http://www.theatlanticcities.com/housing/2012/11/chinas-holdouts/3981/ +# http://www.theatlanticcities.com/arts-and-lifestyle/2012/12/christmas-time-here/4133/ + +title://h1 +author: //ul[@class='meta']/li/a +date: //ul[@class='meta']/li/following-sibling::li +body://article[@class='post'] + +strip://h1 +strip://ul[@class='meta'] +strip://div[@class='newsletter-slug'] +test_url: http://www.theatlanticcities.com/arts-and-lifestyle/2012/12/christmas-time-here/4133/
\ No newline at end of file diff --git a/thecable.foreignpolicy.com.txt b/thecable.foreignpolicy.com.txt new file mode 100644 index 0000000..6672f36 --- /dev/null +++ b/thecable.foreignpolicy.com.txt @@ -0,0 +1,11 @@ +title: //title +author: //span[@class="post_by"]/a/text() +date: //span[@class="post_date"] +body: //div[@class="translateBody"] + +#Strip article junk +strip: //div[@id="share-box"] +strip: //div[@id="fb-meta-like"] + + +test_url: http://thecable.foreignpolicy.com/posts/2013/04/12/will_the_magnitsky_list_spoil_donilon_s_russia_trip
\ No newline at end of file diff --git a/thedisneyblog.com.txt b/thedisneyblog.com.txt new file mode 100644 index 0000000..57b3254 --- /dev/null +++ b/thedisneyblog.com.txt @@ -0,0 +1,7 @@ +title: //h1[contains(@class, 'entry-title')] +author: //span[contains(@class, 'author vcard')] +date: //span[@class = 'entry-date'] +body: //div[@class='entry-content'] +strip_id_or_class: bottomcontainerBox +strip_id_or_class: lightsocial_container +test_url: http://thedisneyblog.com/2012/11/17/videopolis-one-woman-disney-musical-beauty-and-the-beast/
\ No newline at end of file diff --git a/theeuropean-magazine.com.txt b/theeuropean-magazine.com.txt new file mode 100644 index 0000000..a19bae1 --- /dev/null +++ b/theeuropean-magazine.com.txt @@ -0,0 +1,17 @@ +# Tested on: +# http://theeuropean-magazine.com/352-dyson-george/353-evolution-and-innovation +# http://theeuropean-magazine.com/522-casertano-stefano/919-morsi-and-the-future-of-egypt + +title://h2[@class='article-title'] +author:substring-before(substring-after(//p[@class='article-meta'], 'by'), '—') +date:substring-after(//p[@class='article-meta'], '—') +body://div[@class='article'] + +wrap_in(strong)://p[@class='article-teaser'] +move_into(//div[@class='article-head'])://li/img + +strip://h2[@class='article-title'] +strip://p[@class='article-meta'] +strip://div[@class='copyright'] +strip://div[@class='opinions-of-readers'] +test_url: http://theeuropean-magazine.com/522-casertano-stefano/919-morsi-and-the-future-of-egypt
\ No newline at end of file diff --git a/thegamedesignforum.com.txt b/thegamedesignforum.com.txt new file mode 100644 index 0000000..849ede7 --- /dev/null +++ b/thegamedesignforum.com.txt @@ -0,0 +1,14 @@ +## ERROR: Removes all images. Please fix, have no idea why (bad HTML?) + +title: //h1[@class='featuretitle'] +body: //div[@id='nobordercontentarea'] + +# remove Twitter badge +strip: //img[@alt='Follow tgdfweb on Twitter'] + +# fix for headers not showing for some reason +wrap_in(h2): //h2[@class='sectionheader'] +dissolve: //h2[@class='sectionheader'] + +tidy: yes +test_url: http://thegamedesignforum.com/features/acceleration_flow_1.html
\ No newline at end of file diff --git a/thegreatdiscontent.com.txt b/thegreatdiscontent.com.txt new file mode 100644 index 0000000..12442b4 --- /dev/null +++ b/thegreatdiscontent.com.txt @@ -0,0 +1,6 @@ +title: //h1[@id='headline'] +author: substring-after(//section[@class="credits"]/ul/li[1],"Interview by ") +date: //time[@pubdate] +body: //article[@class='interview'] +strip: //article[@class='interview']/footer +test_url: http://thegreatdiscontent.com/jeffrey-zeldman
\ No newline at end of file diff --git a/thenation.com.txt b/thenation.com.txt index 5d75321..dab17f0 100644 --- a/thenation.com.txt +++ b/thenation.com.txt @@ -1,11 +1,13 @@ -title: //h1[@class='print-title'] -body: //div[@class='print-content'] +title: //h2[@property='dc:title'] +#body: //div[@class='print-content'] +body: //div[@id='wysiwyg'] author: //a[contains(@href, '/authors')] author: substring-before(//div[@class='print-created'], '|') date: //span[@class='article-date'] date: substring-after(//div[@class='print-created'], '|') prune: no -single_page_link: //ul[contains(@class, 'article-actions-bar')]//a[contains(@href, '/print/article/')] +#single_page_link: //ul[contains(@class, 'article-actions-bar')]//a[contains(@href, '/print/article/')] +single_page_link: //ul[contains(@class, 'article-actions-bar')]//a[contains(@href, '?page=full')] test_url: http://www.thenation.com/article/162331/hard-against-time-roy-fisher
\ No newline at end of file diff --git a/thenextgeneration.org.txt b/thenextgeneration.org.txt new file mode 100644 index 0000000..dedd989 --- /dev/null +++ b/thenextgeneration.org.txt @@ -0,0 +1,8 @@ +title: //h1[@class='interior-page-title'] +author: //span[@class='author']/a +date: //div[@class='byline']/time +body: //div[@class='rich-text-body'] + +strip: //div[@class='byline'] +strip: //div[@class='offscreen-menu'] +test_url: http://thenextgeneration.org/blog/post/rebrand-announce/
\ No newline at end of file diff --git a/tracks.ranea.org.txt b/tracks.ranea.org.txt new file mode 100644 index 0000000..5a38647 --- /dev/null +++ b/tracks.ranea.org.txt @@ -0,0 +1,14 @@ +# Metadata +title: substring-after(//title, 'Coyote Tracks - ') +author: //meta[@name="author"]/@content +date: //div[@class="post_header"]/a + +# Content Pruning +strip: //div[@class="column left"] +strip: //div[@class="pages"] +strip: //a[@class="text_title"] +strip: //ol[@class="notes"] + +dissolve: //div[@class='column right']/ul +dissolve: //li[@class='post'] +test_url: http://tracks.ranea.org/post/31431060205/the-next-big-uh-slightly-taller-thing
\ No newline at end of file diff --git a/unwinnable.com.txt b/unwinnable.com.txt new file mode 100644 index 0000000..05ad86a --- /dev/null +++ b/unwinnable.com.txt @@ -0,0 +1,9 @@ +title: //h1[@class='postTitle'] +author: //a[@rel='author'] +date: substring-before(//h4[@class='postAuthor'], '|') +body: //div[@class='postContent'] + +strip: //div[@class='simplePullQuote'] + +wrap_in(figure): //img +test_url: http://www.unwinnable.com/2013/04/23/gratifying-play/
\ No newline at end of file diff --git a/utdailybeacon.com.txt b/utdailybeacon.com.txt new file mode 100644 index 0000000..d37911b --- /dev/null +++ b/utdailybeacon.com.txt @@ -0,0 +1,5 @@ +title: //h1 +author: //*[@class='byline'] +date: substring-after(//*[@class='pubdatetime'], 'Published: ') +body: //*[@class='body-block'] +test_url: http://utdailybeacon.com/news/2012/oct/8/energy-forum-continues/
\ No newline at end of file diff --git a/vea.gov.vn.txt b/vea.gov.vn.txt new file mode 100644 index 0000000..9c8420c --- /dev/null +++ b/vea.gov.vn.txt @@ -0,0 +1,7 @@ +title://div[@class="detail-new-title"] +body://div[@class="innerpad"] +strip://div[@class="ArticleUtility"] +strip://div[@class="commentPost"] +strip://div[@class="comment-box"] +strip://div[@id="TinLienQuan"] +test_url: http://vea.gov.vn/vn/tintuc/tintuchangngay/Pages/T%C4%83ng-c%C6%B0%E1%BB%9Dng-b%E1%BA%A3o-t%E1%BB%93n-%C4%91%E1%BB%99ng-v%E1%BA%ADt-hoang-d%C3%A3-%E1%BB%9F-Vi%E1%BB%87t-Nam.aspx
\ No newline at end of file diff --git a/webwereld.nl.txt b/webwereld.nl.txt new file mode 100644 index 0000000..40a5aa3 --- /dev/null +++ b/webwereld.nl.txt @@ -0,0 +1,8 @@ +strip: //*[@class="paginator"] +body: //*[@id="articleText"] +next_page_link: //a[@class="next"] + +# No author detection +# No publishing date detection +# No author and intro deduplication over multiple pages +test_url: http://webwereld.nl/analyse/111452/de-code-van-dorifel-nader-bekeken.html
\ No newline at end of file diff --git a/wyborcza.pl.txt b/wyborcza.pl.txt index f99467c..a622291 100644 --- a/wyborcza.pl.txt +++ b/wyborcza.pl.txt @@ -1,6 +1,6 @@ title:h1 -author: //*[@class = 'author'] -date: //*[@class = 'date'] +author: //*[@id = 'gazeta_article_author'] +date: //*[@id = 'gazeta_article_date'] body: //*[@id = 'art'] next_page_link: //*[@id='Str']/a[contains(text(), 'nastepne')] strip: //*[@class = 'rel_zdjTOP'] diff --git a/xfgjls.com.txt b/xfgjls.com.txt new file mode 100644 index 0000000..919d416 --- /dev/null +++ b/xfgjls.com.txt @@ -0,0 +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")]
+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/zerodistraction.com.txt b/zerodistraction.com.txt deleted file mode 100644 index 80ac6c1..0000000 --- a/zerodistraction.com.txt +++ /dev/null @@ -1,4 +0,0 @@ -author: //span[@class='author']//a -date: //span[@class='date'] -test_url: http://zerodistraction.com/blog/2012/3/11/retina-ipad-that-means-i-am-going-digital-only-for-comic-boo.html -test_url: http://zerodistraction.com/notes/unreasonably-grumpy
\ No newline at end of file diff --git a/zerohedge.com.txt b/zerohedge.com.txt new file mode 100644 index 0000000..7e76aee --- /dev/null +++ b/zerohedge.com.txt @@ -0,0 +1,10 @@ +author: //span[@class='submitted']/a +strip: //div[@class='clear-block clr'] +strip: //div[@class='picture'] +strip: //span[@class='submitted'] +strip: //div[@class='breadcrumb'] +strip: //div[@class='fivestar-static-form-item'] +strip: //div[@class='js-links'] +strip: //div[@class='links clear-block clear'] +strip: //div[@class='block block-block'] +test_url: http://www.zerohedge.com/news/bernankes-columbus-voyage-end-monetary-policy-world
\ No newline at end of file diff --git a/zhihu.com.txt b/zhihu.com.txt new file mode 100644 index 0000000..3c9d8c1 --- /dev/null +++ b/zhihu.com.txt @@ -0,0 +1,19 @@ +# This filter is tested on: +# http://www.zhihu.com/question/19587406 +# http://www.zhihu.com/question/20649035 +# http://www.zhihu.com/question/20637942 + +author: //h3[@class='zm-item-answer-author-wrap'] +title://h2[@class='zm-item-title'] +date://a[@class='answer-date-link meta-item'] +convert_double_br_tags: yes + +wrap_in(blockquote)://div[@class='zm-editable-content'] +wrap_in(blockquote)://sup/text() +dissolve://sup + +strip://div[@class='zh-answers-title'] +strip:///div[@class='zm-item-vote-info '] +strip://div[@class='zm-item-answer-author-info'] +strip://div[@class='zu-blue-info-board zg-r3px'] +test_url: http://www.zhihu.com/question/20637942
\ No newline at end of file |