diff options
37 files changed, 202 insertions, 168 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/.orf.at.txt b/.orf.at.txt new file mode 100644 index 0000000..ad3d7ce --- /dev/null +++ b/.orf.at.txt @@ -0,0 +1,25 @@ +single_page_link: //div[@id='ss-storyText']//p[@class='readMore']/a + +title: substring-before(//title,' - ') +body: //div[@id="ss-storyText"] +author: substring-before(//div[@id="ss-storyText"]//p[contains(text(), ', ORF.at')], ', ORF.at') +strip: //div[@id="ss-storyText"]//p[contains(text(), ', ORF.at')] +date: substring-after(//div[@class='storyMeta socialshare']//p[@class='date'],'Publiziert am') +strip: //p[@class='date'] + +strip: //p[@class='credit'] +strip: //p[@class='toplink'] +strip: //div[@id="ss-storyText"]/h1 +strip: //div[@class='socialButtons'] +strip: //div[@class='storyMeta socialshare'] +strip: //div[@class='socialShareWrapper'] +strip: //div[@id='socialshareprivacy'] + +prune: no +tidy: no + +test_url: http://orf.at/stories/2317355/ +test_url: http://orf.at/stories/2084731/ +test_url: http://orf.at/stories/2317313/2317311/ +test_url: http://wien.orf.at/news/stories/2746414/ +test_url: http://ooe.orf.at/news/stories/2750613/ 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/derstandard.at.txt b/derstandard.at.txt index 07db352..0bfeec0 100644 --- a/derstandard.at.txt +++ b/derstandard.at.txt @@ -1,13 +1,12 @@ -title: //div[@id='artikelHeader']/h1 +title: //div[@id='content-header']/h1 author: //span[@class='author'] -date: //span[@class='date'] body: //div[@class='copytext'] strip: //ul[@class='lookupLinksArtikel'] strip: //div[@id='pageTop'] strip: //div[@id='toolbar'] strip: //div[@id='articleTools'] -strip: //div[@id='weiterlesen'] +strip: //div[@id='weiterLesen'] strip: //div[@id='communityCanvas'] -test_url: http://derstandard.at/1318726018343/Breitband-LTE-Was-bringt-die-neue-Mobilfunk-Generation
\ No newline at end of file +test_url: http://derstandard.at/1318726018343/Breitband-LTE-Was-bringt-die-neue-Mobilfunk-Generation diff --git a/fm4.orf.at.txt b/fm4.orf.at.txt index 5db3e58..0c8bf57 100644 --- a/fm4.orf.at.txt +++ b/fm4.orf.at.txt @@ -1,7 +1,13 @@ author: //div[@class='authorDescription']/h2 body: //div[@id='story'] -date: substring-before(substring-after(//p[@class='date'],'Erstellt am:'), '-') title: //h1[@class='detail'] -strip: //div[@class='fact'] -test_url: http://fm4.orf.at/stories/1689156/
\ No newline at end of file +date: translate(translate(substring-before(substring-after(//p[@class='date'],'Erstellt am:'), ' Uhr'), '. ', '.'), '-', ' ') +strip: //p[@class='date'] + +strip: //p[@class='credit'] + +tidy: no +prune: no + +test_url: http://fm4.orf.at/stories/1689156/ 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/jdubuzz.com.txt b/jdubuzz.com.txt index 7fac576..ddae23f 100644 --- a/jdubuzz.com.txt +++ b/jdubuzz.com.txt @@ -3,9 +3,11 @@ # Source: http://siteconfig.fivefilters.org/grab.php?url=http://www.journaldugeek.com/2015/09/09/apple-ipad-pro/ date: //meta[@property="og:updated_time"]/@content +next_page_link: //div[contains(concat(' ',normalize-space(@class),' '),' pagination ')]/a[contains(concat(' ',normalize-space(@class),' '),' next ')] strip: //div[contains(concat(' ',normalize-space(@class),' '),' jdg-recommend ')] strip: //div[contains(concat(' ',normalize-space(@class),' '),' proofreader-bloc ')] body: //div[contains(concat(' ',normalize-space(@class),' '),' post-content ')] test_url: http://www.jdubuzz.com/2015/09/11/le-meilleur-du-jduzap-cest-maintenant/ +test_url: http://www.jdubuzz.com/tests/les-20-comptes-instagram-des-filles-les-plus-sexy-a-suivre-en-2016/
\ No newline at end of file diff --git a/journaldugamer.com.txt b/journaldugamer.com.txt index 1e1cabc..e3baaa1 100644 --- a/journaldugamer.com.txt +++ b/journaldugamer.com.txt @@ -3,6 +3,7 @@ # Source: http://siteconfig.fivefilters.org/grab.php?url=http://www.journaldugeek.com/2015/09/09/apple-ipad-pro/ date: //meta[@property="og:updated_time"]/@content +next_page_link: //div[contains(concat(' ',normalize-space(@class),' '),' pagination ')]/a[contains(concat(' ',normalize-space(@class),' '),' next ')] strip: //div[contains(concat(' ',normalize-space(@class),' '),' jdg-recommend ')] strip: //div[contains(concat(' ',normalize-space(@class),' '),' proofreader-bloc ')] diff --git a/journaldugeek.com.txt b/journaldugeek.com.txt index 776dbea..9af13b0 100644 --- a/journaldugeek.com.txt +++ b/journaldugeek.com.txt @@ -3,6 +3,7 @@ # Source: http://siteconfig.fivefilters.org/grab.php?url=http://www.journaldugeek.com/2015/09/09/apple-ipad-pro/ date: //meta[@property="og:updated_time"]/@content +next_page_link: //div[contains(concat(' ',normalize-space(@class),' '),' pagination ')]/a[contains(concat(' ',normalize-space(@class),' '),' next ')] strip: //div[contains(concat(' ',normalize-space(@class),' '),' jdg-recommend ')] strip: //div[contains(concat(' ',normalize-space(@class),' '),' proofreader-bloc ')] 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/moreintelligentlife.com.txt b/moreintelligentlife.com.txt deleted file mode 100644 index 780cca4..0000000 --- a/moreintelligentlife.com.txt +++ /dev/null @@ -1,7 +0,0 @@ -title: //h1[@class='print-title'] -body: //div[@class='print-submitted' or @class='print-created' or @class='print-content'] -prune: no - -single_page_link: //li[@class='print']/a - -test_url: http://moreintelligentlife.com/content/places/paul-markillie/they-trash-cars-dont-they
\ No newline at end of file diff --git a/mostpleasent.com.txt b/mostpleasent.com.txt new file mode 100644 index 0000000..26fff30 --- /dev/null +++ b/mostpleasent.com.txt @@ -0,0 +1,7 @@ +# Generated by FiveFilters.org's web-based selection tool +# Place this file inside your site_config/custom/ folder +# Source: http://siteconfig.fivefilters.org/grab.php?url=http%3A%2F%2Fwww.mostpleasent.com%2Fnew-sony-battery-reportedly-gets-40-better-life%2F + +body: //div[contains(concat(' ',normalize-space(@class),' '),' post_header single ')] + +test_url: http://www.mostpleasent.com/new-sony-battery-reportedly-gets-40-better-life/ diff --git a/nachrichten.at.txt b/nachrichten.at.txt new file mode 100644 index 0000000..64015ca --- /dev/null +++ b/nachrichten.at.txt @@ -0,0 +1,8 @@ +single_page_link: //a[@class="drucken"] + +body: //div[@class="artikeldruck"] + +strip: //div[@class="druckheadline"] +strip: //div[@class="druckfuss"] + +test_url: http://www.nachrichten.at/nachrichten/chronik/Silvester-in-der-Bundeshauptstadt-Anti-Terror-Einheiten-ruesten-sich;art58,2069166 diff --git a/news.orf.at.txt b/news.orf.at.txt deleted file mode 100644 index 3b1d3cc..0000000 --- a/news.orf.at.txt +++ /dev/null @@ -1,11 +0,0 @@ -single_page_link: //div[@id='content']//p[@class='readMore']/a - -title: //div[@class='hidden offscreen']/h2 -body: //div[@id="storyText"] -move_into(//div[@id='storyText']): //div[@class='fact'] -strip: //small[@class='credit'] -strip: //small[@class='caption'] -date: substring-after(//div[@id='storyMeta']//p[@class='date'],'Publiziert am') -strip: //p[@class='toplink'] - -test_url: http://news.orf.at/stories/2084731/
\ No newline at end of file diff --git a/news.pixelistes.com.txt b/news.pixelistes.com.txt index a2d2e9e..898eb06 100644 --- a/news.pixelistes.com.txt +++ b/news.pixelistes.com.txt @@ -3,6 +3,7 @@ # Source: http://siteconfig.fivefilters.org/grab.php?url=http://www.journaldugeek.com/2015/09/09/apple-ipad-pro/ date: //meta[@property="og:updated_time"]/@content +next_page_link: //div[contains(concat(' ',normalize-space(@class),' '),' pagination ')]/a[contains(concat(' ',normalize-space(@class),' '),' next ')] strip: //div[contains(concat(' ',normalize-space(@class),' '),' jdg-recommend ')] strip: //div[contains(concat(' ',normalize-space(@class),' '),' proofreader-bloc ')] @@ -1,11 +1,25 @@ -single_page_link: //div[@id='content']//p[@class='readMore']/a +single_page_link: //div[@id='ss-storyText']//p[@class='readMore']/a -title: //div[@class='hidden offscreen']/h2 -body: //div[@id="storyText"] -move_into(//div[@id='storyText']): //div[@class='fact'] -strip: //small[@class='credit'] -strip: //small[@class='caption'] -date: substring-after(//div[@id='storyMeta']//p[@class='date'],'Publiziert am') +title: substring-before(//title,' - ') +body: //div[@id="ss-storyText"] +author: substring-before(//div[@id="ss-storyText"]//p[contains(text(), ', ORF.at')], ', ORF.at') +strip: //div[@id="ss-storyText"]//p[contains(text(), ', ORF.at')] +date: substring-after(//div[@class='storyMeta socialshare']//p[@class='date'],'Publiziert am') +strip: //p[@class='date'] + +strip: //p[@class='credit'] strip: //p[@class='toplink'] +strip: //div[@id="ss-storyText"]/h1 +strip: //div[@class='socialButtons'] +strip: //div[@class='storyMeta socialshare'] +strip: //div[@class='socialShareWrapper'] +strip: //div[@id='socialshareprivacy'] + +prune: no +tidy: no -test_url: http://orf.at/stories/2084731/
\ No newline at end of file +test_url: http://orf.at/stories/2317355/ +test_url: http://orf.at/stories/2084731/ +test_url: http://orf.at/stories/2317313/2317311/ +test_url: http://wien.orf.at/news/stories/2746414/ +test_url: http://ooe.orf.at/news/stories/2750613/ 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/scraplab.net.txt b/scraplab.net.txt deleted file mode 100644 index ca7ec19..0000000 --- a/scraplab.net.txt +++ /dev/null @@ -1,3 +0,0 @@ -title: //h2 -body: //div[@class='body'] -test_url: http://scraplab.net/2010/10/26/please-keep-your-belongings-with-you-at-all-times/
\ 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/summify.com.txt b/summify.com.txt deleted file mode 100644 index 1128e1b..0000000 --- a/summify.com.txt +++ /dev/null @@ -1,2 +0,0 @@ -strip_id_or_class: toolbar -test_url: http://summify.com/story/Tmt1YQ0JBgKTAHwK/www.nybooks.com/articles/archives/2003/jan/16/fixed-opinions-or-the-hinge-of-history/?pagination=false
\ 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/tech.gilt.com.txt b/tech.gilt.com.txt deleted file mode 100644 index ab56460..0000000 --- a/tech.gilt.com.txt +++ /dev/null @@ -1,5 +0,0 @@ -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/themuseumofinnocence.com.txt b/themuseumofinnocence.com.txt deleted file mode 100644 index 80aba44..0000000 --- a/themuseumofinnocence.com.txt +++ /dev/null @@ -1,7 +0,0 @@ -body: single-review -strip_id_or_class: featured-review -strip_id_or_class: resources -strip_id_or_class: rate-the-book -strip_id_or_class: write-review - -test_url: http://themuseumofinnocence.com/review.php?id=1179
\ No newline at end of file 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 diff --git a/zeit.de.txt b/zeit.de.txt index 4e00894..0b6a837 100644 --- a/zeit.de.txt +++ b/zeit.de.txt @@ -1,48 +1,62 @@ -# 2015.07.08 [Marvin Dickhaus] fixed single_page_link -# 2013.10.30 [rezor92] fixed single_page_link -# 2012-12-23 [carlo@...] fixed half-assed headlines in articles, removed inline author profiles, adjusted picture captions -# 2012-03-17 [dkless@...] Cut metadata parts in the beginning and the ends of the content block; copyright entries for pictures removed; Author fixed, not sure if old entries still valid (I left them); Weird problems with some pages addressed (see last section for removing hidden section) -# 2011-12-09 [carlo@...] Removed "related articles" block -# 2011-08-23 [carlo@...] changed single page link to use print version: page works better, less ambiguity. Related cleanups and simplifications. -# 2011-08-20 [carlo@...] added author, fixed date - -single_page_link: //a[contains(@href, 'komplettansicht')] tidy: no +prune: no + +# Figures are wrapped in a noscript tag which is itself wrapped in a +# conditional comment. Feed readers will fail to parse this correctly +# so get rid of the noscript tag altogether. +replace_string(<noscript): <foo -title: //title -date: substring-before( //li[@class="date"], " " ) -author: //li[@class="author"]/a/text() | //li[@class="author first"]/a/text() -author: substring-after(//li[@class='source first '], 'Quelle: ') +title: //meta[@property='og:title']/@content +date: //meta[@name='date']/@content -strip_id_or_class: articleheader -strip: //div[@id="comments"] | //div[@class="pagination block"] | //p[@class="ressortbacklink"] | //div[@id="relatedArticles"] | // div[@class="inline portrait"] +strip: //span[@class='figure__copyright'] -#Removes author and date from the start -strip: //ul[@class="tools"] -#Removes copyright statement - often disturb as first line of the news -strip: //p[@class="copyright"] -strip: //div[@class="copyright"] -#Removes pagination links at the end -strip: //div[@class="pagination"] -#Removes link to main page at the bottom of some articles (Zur Startseite) -strip: //a[@href='http://www.zeit.de'] +# Self advertisements +strip: //figure[@class='figure-stamp'] +strip: //a[contains(@title, 'Dieser Text ')] +strip: //a[contains(@title, 'Dieser Artikel ')] +strip: //span[@class='figure__text']/text()[contains(., 'Dieser Text ')] +strip: //span[@class='figure__text']/text()[contains(., 'Dieser Artikel ')] + +####################################### +# ZEIT: +####################################### + +single_page_link: //a[contains(@href, 'komplettansicht')] -# Fix picture captions -wrap_in(small): //p[@class="caption"]/text() +author: //a[@class='byline__author']/span +author: substring-after(//span[@class='metadata__source'], 'Quelle: ') -# Fix sub-headlines -wrap_in(h2): //p/strong -dissolve: //h2/strong +body: //main/article/div[@itemprop='articleBody'] -#Sometimes things are embedded in the print version that are not displayed on the web, but will be displayed in the mobilized versions and lead even to problems. These sections are removed here. -strip_id_or_class:"informatives" -strip_id_or_class:"bottom" -strip_id_or_class:"teasermosaic" -strip_id_or_class:"comments" -strip_id_or_class:"articlefooter af" -strip_id_or_class:"relateds" -strip_id_or_class:"pagination" +strip: //a[@href='#'] +strip: //form[@id='newsletter-teaser-form'] +strip_id_or_class: 'article-pagination article__item ' -footnotes: no test_url: http://www.zeit.de/kultur/film/2012-12/Kurzfilmtag -test_url: http://www.zeit.de/kultur/2015-07/kapitalismuskritik-selbstberuhigung-armin-nassehi +test_url: http://www.zeit.de/sport/2016-01/darts-wm-finale-anderson-lewis/komplettansicht +test_url: http://www.zeit.de/kultur/2015-12/selbstverwirklichung-optimierung-essay +test_url: http://www.zeit.de/2015/51/selbstdiagnose-gesundheit-zuhause-blut-urin-selbsttest +test_url: http://www.zeit.de/campus/2015/s2/nebenjob-master-studium-finanzierung +test_url: http://www.zeit.de/hamburg/politik-wirtschaft/2015-12/hamburg-wohnungsbau-fluechtlinge + +####################################### +# ZEIT MAGAZIN: +####################################### + +next_page_link: //meta[@rel='next']/@href + +author: //a[@class='article__head__meta__author']/span + +body: //main/article/div[@class='article__wrap'] + +strip: //div[@class='article__head-wrap']//h1 +strip_id_or_class: article__socialbox +strip_id_or_class: article__nextread nextread-base is-centered +strip_id_or_class: js-comments +strip_id_or_class: article__pagination is-constrained is-centered +strip_id_or_class: article__head__meta + +test_url: http://www.zeit.de/zeit-magazin/2015/51/daisy-ridley-traum +test_url: http://www.zeit.de/zeit-magazin/2015/52/cyberstalking-internet-stalker-familie-mierau +test_url: http://www.zeit.de/zeit-magazin/leben/2015-12/rueckblick-2015-magnum-fs |