diff options
| -rw-r--r-- | .estadao.com.br.txt | 15 | ||||
| -rw-r--r-- | applature.com.txt | 18 | ||||
| -rw-r--r-- | blog.renren.com.txt | 2 | ||||
| -rw-r--r-- | bloomberg.com.txt | 6 | ||||
| -rw-r--r-- | chomsky.info.txt | 8 | ||||
| -rw-r--r-- | christianpf.com.txt | 5 | ||||
| -rw-r--r-- | ciaosamin.com.txt | 2 | ||||
| -rw-r--r-- | counterpunch.org.txt | 7 | ||||
| -rw-r--r-- | fubiz.net.txt | 3 | ||||
| -rw-r--r-- | gov.ky.txt | 4 | ||||
| -rw-r--r-- | iolanguage.com.txt | 2 | ||||
| -rw-r--r-- | letemps.ch.txt | 3 | ||||
| -rw-r--r-- | lwn.net.txt | 39 | ||||
| -rw-r--r-- | medium.com.txt | 4 | ||||
| -rw-r--r-- | quora.com.txt | 3 | ||||
| -rw-r--r-- | ritholtz.com.txt | 5 | ||||
| -rw-r--r-- | staradvertiser.com.txt | 11 | ||||
| -rw-r--r-- | tagesschau.de.txt | 2 | ||||
| -rw-r--r-- | twitter.com.txt | 6 | ||||
| -rw-r--r-- | volkskrant.nl.txt | 4 |
20 files changed, 70 insertions, 79 deletions
diff --git a/.estadao.com.br.txt b/.estadao.com.br.txt deleted file mode 100644 index 00290c1..0000000 --- a/.estadao.com.br.txt +++ /dev/null @@ -1,15 +0,0 @@ -title: //span[@id='ctl00_ctl00_MainContent_MainContent_RecipeImage1_lblRecipeTitle'] -body: //div[@class='img_article'] | //div[@class='article']//div[@class='article_header' or @class='article_content'] -body: //div[@class='texto-noticia'] - -author: //div[@class='autor']//em -author: //div[@class='bb-md-noticia-autor'] - -strip_id_or_class: divulgar -strip_id_or_class: innerRight -strip: //div[@class='size' or @class='imprimir'] - -prune: no - -test_url: http://revistapiaui.estadao.com.br/edicao-62/carta-de-havana/la-vida-por-la-izquierda -test_url: http://economia.estadao.com.br/noticias/economia,pf-panamericano-tambem-irrigou-contas-de-executivos-do-grupo-silvio-santos,94648,0.htm
\ No newline at end of file diff --git a/applature.com.txt b/applature.com.txt deleted file mode 100644 index a820bba..0000000 --- a/applature.com.txt +++ /dev/null @@ -1,18 +0,0 @@ -title: //h1[contains(@class, 'title')# -body: //div[@id='mainContent']//div[contains(@class, 'section_content')] | //ul[@class='section_footer'] -date: //div[@class='date'] - -strip_id_or_class: sharethis -strip_id_or_class: stats -strip_id_or_class: apply_form -strip_id_or_class: job_map -strip_id_or_class: respond -strip: //h1//span[@class='type'] -strip: //li[@class='print' or @class='map'] - -replace_string(<ul class="section_footer" style="display): <ul class="section_footer" style="display-bla - -prune: no -tidy: no - -test_url: http://applature.com/mining-jobs/jobs/nickel-west-leinster-analytical-laboratory-technician/
\ No newline at end of file diff --git a/blog.renren.com.txt b/blog.renren.com.txt index 401d31e..0193842 100644 --- a/blog.renren.com.txt +++ b/blog.renren.com.txt @@ -8,4 +8,4 @@ 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 +test_url: http://blog.renren.com/share/224959024/14260739544 diff --git a/bloomberg.com.txt b/bloomberg.com.txt new file mode 100644 index 0000000..c8715c4 --- /dev/null +++ b/bloomberg.com.txt @@ -0,0 +1,6 @@ +date: //*[@itemprop='datePublished']/@datetime +author: //meta[@name="sailthru.author"]/@content +body: //*[@itemprop='articleBody' or @itemprop='description'] + +test_url: http://www.bloomberg.com/news/articles/2015-12-30/will-your-job-disappear-by-2024- +test_contains: Every week, hosts Tori Stilwell
\ No newline at end of file diff --git a/chomsky.info.txt b/chomsky.info.txt index 2645f11..21c945e 100644 --- a/chomsky.info.txt +++ b/chomsky.info.txt @@ -1,6 +1,6 @@ -title: //div[@class='title'] -author: //div[@class='author'] +title: //*[@class='title'] +author: //*[@class='author'] prune: no -test_url: http://www.chomsky.info/onchomsky/2002----.htm -test_contains: The propaganda model argues +test_url: https://chomsky.info/20150820-2/ +test_contains: The first prime-time Republican primary debate diff --git a/christianpf.com.txt b/christianpf.com.txt deleted file mode 100644 index fb5f342..0000000 --- a/christianpf.com.txt +++ /dev/null @@ -1,5 +0,0 @@ -title: //h1[@class="entry-title"] -author: //*[@class="author vcard fn"] -date: //*[@class="published"] -body: //div[(@class = "dd_content_wrap")] -test_url: http://christianpf.com/do-ibuys-lead-to-more-buying/
\ No newline at end of file diff --git a/ciaosamin.com.txt b/ciaosamin.com.txt index 02fd343..ee09060 100644 --- a/ciaosamin.com.txt +++ b/ciaosamin.com.txt @@ -1,4 +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 +test_url: http://ciaosamin.com/ciao/2015/12/28/recipe-million-dollar-caramels diff --git a/counterpunch.org.txt b/counterpunch.org.txt index b6bd8be..12ca19f 100644 --- a/counterpunch.org.txt +++ b/counterpunch.org.txt @@ -1,6 +1,7 @@ title: //div[@class='main']//h1[contains(@class, 'article-title')] author: //div[@class='mainauthorstyle'] -body: //div[@class='main']//div[@class='main-text'] -strip: //td[@width='140'] +body: //div[@itemprop="articleBody"] +date: //meta[@itemprop="datePublished"]/@content +#strip: //td[@width='140'] -test_url: http://www.counterpunch.org/johnstone05172011.html
\ No newline at end of file +test_url: http://www.counterpunch.org/2011/09/28/the-dangerous-cult-of-the-guardian/ diff --git a/fubiz.net.txt b/fubiz.net.txt deleted file mode 100644 index 0dc3047..0000000 --- a/fubiz.net.txt +++ /dev/null @@ -1,3 +0,0 @@ -body: //div[@class = 'entry'] - -test_url: http://www.fubiz.net/2011/05/31/world-press-photo-2011/
\ No newline at end of file diff --git a/gov.ky.txt b/gov.ky.txt deleted file mode 100644 index 294ece3..0000000 --- a/gov.ky.txt +++ /dev/null @@ -1,4 +0,0 @@ -strip: //body//title - -test_url: http://www.gov.ky/pls/portal/PORTAL.wwv_media.show?p_id=7593947&p_settingssetid=1&p_settingssiteid=0&p_siteid=2425&p_type=basetext&p_textid=7593948 -test_url: http://www.rcips.ky/pls/portal/wlacomp.wlafeed.show_cignewsfeed_agency?p_sitecode=POL&p_agency=Police
\ No newline at end of file diff --git a/iolanguage.com.txt b/iolanguage.com.txt deleted file mode 100644 index 231875a..0000000 --- a/iolanguage.com.txt +++ /dev/null @@ -1,2 +0,0 @@ -body: //center/table -test_url: http://www.iolanguage.com/scm/io/docs/IoGuide.html
\ No newline at end of file diff --git a/letemps.ch.txt b/letemps.ch.txt deleted file mode 100644 index 49b019f..0000000 --- a/letemps.ch.txt +++ /dev/null @@ -1,3 +0,0 @@ -title: //h2 -strip_image_src: logo.gif -test_url: http://www.letemps.ch/Facet/print/Uuid/7c9f912c-07c9-11e0-9b50-4d96c9eca37f
\ No newline at end of file diff --git a/lwn.net.txt b/lwn.net.txt new file mode 100644 index 0000000..06a6dc6 --- /dev/null +++ b/lwn.net.txt @@ -0,0 +1,39 @@ +# HTML5 anyone? The 1980s called, they want their HTML4 back. +# LWN uses so little markup that you really have to be creative. + +tidy: yes +prune: no + +single_page_link: //div[@class='ArticleText']//a[contains(text(), 'Full Story')]/@href +single_page_link: concat(//div[@class='ArticleText']//a[contains(text(), 'Read more')]/@href, 'bigpage') + +title: //h1 + +# After tiding the document, <b> becomes <strong>. +author: //div[@class='FeatureByline']/strong +date: //div[@class='FeatureByline']/text()[preceding-sibling::br] +strip: //div[@class='FeatureByline'] +author: substring-after(//div[@class='GAByline']/p[2], 'by ') +date: //div[@class='GAByline']/p[1] +strip: //div[@class='GAByline'] + +# tidy will take care of fixing the tag mess that we make here. +replace_string(<p class="Cat1HL">): <h1> +replace_string(<h2 class="SummaryHL">): <h3> +replace_string(<p class="Cat2HL">): <h2> + +# Make extracting the content before "Log in to post comments" easier. +# And by "easier" I mean possible in all cases without going through +# a lot of XPath pain. +replace_string(<hr width="60%" align="left">): <div class="ftrss-strip"> +replace_string(to post comments)): </div> +strip: //div[@class='ftrss-strip'] +body: //div[@class='ArticleText'] + +test_url: http://lwn.net/Articles/668318/ +test_url: http://lwn.net/Articles/668695/ +test_url: http://lwn.net/Articles/669114/ +test_url: http://lwn.net/Articles/670209/ +test_url: http://lwn.net/Articles/670209/rss +test_url: http://lwn.net/Articles/668318/rss +test_url: http://lwn.net/Articles/670062/ diff --git a/medium.com.txt b/medium.com.txt index cc373f3..2c969c0 100644 --- a/medium.com.txt +++ b/medium.com.txt @@ -1,7 +1,11 @@ body: //main[contains(@class, 'postArticle-content')] body: //div[contains(@class, 'postArticle-content')] +body: //div[contains(@class, 'section-inner')] strip_id_or_class: supplementalPostContent +parser: html5php + +tidy: no prune: no test_url: https://medium.com/@savolai/kaytettavyyden-haasteet-keskustelukulttuurista-2-3-6844c0d7893b diff --git a/quora.com.txt b/quora.com.txt index f2b75a9..cfa7bd6 100644 --- a/quora.com.txt +++ b/quora.com.txt @@ -22,8 +22,7 @@ find_string: <div class="Answer" replace_string: <hr /><div class="Answer" test_url: http://www.quora.com/What-everyday-habit-do-you-wish-you-had-developed-earlier-in-life -test_contains: Please provide a specific practical/measurable action-based everyday -test_contains: Exercise every day +test_contains: Exercising every day test_url: http://www.quora.com/What-is-the-greatest-illusion-in-life test_contains: What is the greatest illusion in life? diff --git a/ritholtz.com.txt b/ritholtz.com.txt deleted file mode 100644 index d598479..0000000 --- a/ritholtz.com.txt +++ /dev/null @@ -1,5 +0,0 @@ -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/staradvertiser.com.txt b/staradvertiser.com.txt deleted file mode 100644 index 254e2c2..0000000 --- a/staradvertiser.com.txt +++ /dev/null @@ -1,11 +0,0 @@ -title: //h1[@id='storyTitle'] -author: substring-after(//span[@class='hsa_postCredit'], 'By ') -date://span[@class='hsa_dateStamp'] -body: //div[@class='storytext'] -strip_id_or_class: insideStoryAd -strip_id_or_class: printDesc -strip_id_or_class: sb_2010_story_tools -strip_id_or_class: FBConnectButton_Text -strip_id_or_class: breadcrumbs -prune: no -test_url: http://www.staradvertiser.com/news/20111112_World_leaders_step_onto_isle_stage.html
\ No newline at end of file diff --git a/tagesschau.de.txt b/tagesschau.de.txt index ba3b1d3..507aab2 100644 --- a/tagesschau.de.txt +++ b/tagesschau.de.txt @@ -1,4 +1,4 @@ -body: //div[contains(@class, 'sectionArticle')]//div[contains(concat(' ',normalize-space(@class),' '),' box ')] +body: //div[contains(@class, 'sectionArticle') and contains(@class, 'sectionZ')] strip_id_or_class: infokasten strip_id_or_class: teaserImTeaser diff --git a/twitter.com.txt b/twitter.com.txt index 0e5b748..0a010a4 100644 --- a/twitter.com.txt +++ b/twitter.com.txt @@ -3,6 +3,12 @@ body: (//p[contains(@class, 'js-tweet-text')])[1] author: (//strong[contains(@class, 'fullname')])[1] date: //span[contains(@class, 'js-short-timestamp')]/@data-time +# mobile site (automatic redirect - noscript meta refresh) +author: (//div[contains(@class, 'fullname')])[1] +body: (//div[contains(@class, 'TweetDetail-text')])[1] + +parser: html5php + prune: no tidy: no diff --git a/volkskrant.nl.txt b/volkskrant.nl.txt index 8c311f1..72a3dfa 100644 --- a/volkskrant.nl.txt +++ b/volkskrant.nl.txt @@ -9,7 +9,9 @@ strip: //div[contains(@class, 'media-container') and contains(@class, 'pull-righ tidy: no prune: no +parser: html5php + test_url: http://www.volkskrant.nl/sport/dossier-wereldvoetbalbond-fifa-wankelt~a4042695/ test_contains: De belangrijkste spil in het -test_url: http://www.volkskrant.nl/nieuws/rss.xml
\ No newline at end of file +test_url: http://www.volkskrant.nl/nieuws/rss.xml |