Merge remote-tracking branch 'upstream/master'

.blog.hu.txt

@@ -0,0 +1,17 @@
+# First catch with wallbag sometimes fails,
+# just reload article within wallabag then
+
+http_header(user-agent): Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:132.0) Gecko/20100101 Firefox/132.0
+
+body: //article[1]
+
+strip_id_or_class: blh_share_cont
+strip_id_or_class: comments
+strip_id_or_class: tags
+strip_id_or_class: article-bottom
+
+prune: no
+tidy: no
+
+test_url: https://passport.blog.hu/2020/03/13/a_cia_lopott_muholdja
+test_url: https://mpt-it.blog.hu/2024/10/27/_itt_van_a_varos_vagyunk_lakoi

.nasa.gov.txt

@@ -0,0 +1,14 @@
+body: //article[1]/section[1]/div[contains(@class, 'grid-container')]
+title: substring-before( //meta[@property='og:title']/@content , ' - NASA Science')
+author: //div[contains(@class, 'SideboxAuthor')]//p[contains(@class, 'hds-meta-subheading')]
+author: //div[contains(@class, 'SideboxAuthor')]//p[contains(@class, 'hds-meta-heading')]
+date: //meta[@name='parsely-pub-date']/@content
+
+strip_id_or_class: article-header
+
+strip: //aside
+
+prune: no
+tidy: no
+
+test_url: https://science.nasa.gov/missions/hubble/new-clues-to-trappist-1-planet-compositions-atmospheres

antigone21.com.txt

@@ -0,0 +1,12 @@
+body: //div[contains(@class, 'post-entry')]
+title: substring-before( //meta[@property='og:title']/@content , ' | Antigone XXI')
+
+strip: //span[text()='*']
+strip: //p[text()='*']
+
+strip_id_or_class: post-tags
+
+prune: no
+tidy: no
+
+test_url: https://antigone21.com/2014/04/03/falafels-hummus-maison-vegan-sans-gluten/

arstechnica.com.txt

@@ -1,41 +1,25 @@
-author: //p[@class='byline']/span[@class='author']
-author: //p[@class='byline']/a
+body: //article[1]
+author: //div[@class='author-mini-bio']//a
+author: //a[contains(@href, '/author/')]
 
-body: //div[contains(@class,'article-content')]
-strip: //h2[@class='title']
-strip: //div[contains(@class, 'pullbox')]
+strip: //header//h1 | //header//h1/following-sibling::div[contains(@class, 'md:')] | //header//h1/preceding-sibling::div
+strip: //div[@class='author-mini-bio']/self::* | //div[@class='author-mini-bio']/following-sibling::*
+strip: //div[contains(@class, 'story-tools')]/self::* | //div[contains(@class, 'story-tools')]/following-sibling::*
 
-strip_id_or_class: byline
-strip_id_or_class: story-sidebar
-prune: no
-
-find_string: " data-src="
-replace_string: "><img src="
-
-find_string: " data-responsive="
-replace_string: " /><span "
-
-find_string: <figure style="
-replace_string: </span><figure style="
+strip: //svg
 
-date: //div[@class='byline']/span[@class='posted']//abbr/@original-title
-date: //div[@class='byline']/span[@class='posted']//abbr
-date: //*[@class='byline']//time[@class='date']
+strip_id_or_class: view-comments
+strip_id_or_class: pswp-caption-content
+strip_id_or_class: related-stories
+strip_id_or_class: text-settings-dropdown-story
 
-title: //div[@id='story']//h2[@class='title']
 
-strip: //div[@class='pager']
-native_ad_clue: //meta[@property="og:url" and contains(@content, '/sponsored/')]
-
-strip: //aside
-next_page_link: //nav//a[contains(text(), 'Next')]/@href
-next_page_link: //span[@class='numbers']//a/span[@class='next']/..
-next_page_link: //nav//a/span[contains(text(), 'Next')]/../@href
+prune: no
+tidy: no
 
 test_url: http://arstechnica.com/tech-policy/news/2012/02/gigabit-internet-for-80-the-unlikely-success-of-californias-sonicnet.ars
 test_url: http://arstechnica.com/apple/2005/04/macosx-10-4/
 test_url: https://arstechnica.com/features/2020/10/the-space-operating-systems-booting-up-where-no-one-has-gone-before
 test_url: https://arstechnica.com/gaming/2021/02/coders-reverse-engineer-grand-theft-autos-raw-pc-source-code/
-
-# test_url: http://arstechnica.co.uk/science/2016/06/what-is-open-access-free-sharing-of-all-human-knowledge/
-# test_url: http://arstechnica.co.uk/information-technology/2016/05/eben-moglen-gpl-online-advertising-is-becoming-a-perfect-despotism/
+test_url: http://arstechnica.co.uk/science/2016/06/what-is-open-access-free-sharing-of-all-human-knowledge/
+test_url: http://arstechnica.co.uk/information-technology/2016/05/eben-moglen-gpl-online-advertising-is-becoming-a-perfect-despotism/

blog.rchapman.org.txt

@@ -0,0 +1,12 @@
+body: //article[@class='post-container']
+title: //h1[@class='post-title']
+author: 'Ryan A. Chapman'
+date: substring-after(//article[@class='post-container']/header/text() , 'Published')
+
+strip: //header
+strip: //footer/self::* | //footer/following-sibling::*
+
+prune: no
+tidy: no
+
+test_url: https://blog.rchapman.org/posts/Linux_System_Call_Table_for_x86_64/

buildvirtual.net.txt

@@ -0,0 +1,6 @@
+body: //article[1]/div[contains(@class, 'post-entry')]
+title: substring-before(//meta[@property='og:title']/@content , ' - buildVirtual')
+
+prune: no
+
+test_url: https://buildvirtual.net/how-to-use-docker-stack-to-deploy-docker-containers/

callistaenterprise.se.txt

@@ -0,0 +1,9 @@
+# <head> contains a condition redirect via <meta http-equiv="refresh" ...>
+# to /oldie/
+# following line deactivates this for FTR and wallabagger browser extension
+# but unfortunately NOT for wallabag UI
+
+replace_string(http-equiv="refresh"): foo="bar"
+
+
+test_url: https://callistaenterprise.se/blogg/teknik/2016/05/27/building-a-microservice-with-golang/

canardpc.com.txt

@@ -1,11 +1,17 @@
 title: //div[contains(@class, 'main-article-titre')]
 body: //div[contains(@class, 'post-content')]
-author: //div[@class="post-informations"]//a[contains(@href, 'https://www.canardpc.com/auteur/')]
+author: //div[contains(@class, "post-informations")]//a[contains(@href, 'https://www.canardpc.com/auteur/')]
 date: //meta[@property="article:published_time"]/@content
 
 strip: //div[contains(@class, 'slick-cloned')]
 strip_id_or_class: locomotive-navigation
 strip: //div[contains(@class, "encarts")]//div[contains(@class, "layout-framed")]
+#strip: //div[contains(@class, "post-row desktop")]
+strip: //div[contains(@class, "post-row mobile")]
+strip_id_or_class: main-cartouche
+strip: //div[contains(@class, 'post-informations')]/span
+
+prune: no
 
 # wallabag-specific login directives (not supported in FTR)
 requires_login: yes

community.element14.com.txt

@@ -0,0 +1,18 @@
+http_header(user-agent): PHP/7.4
+
+body: (//div[@class='content'])[1]
+date: //time/@datetime
+author: //span[@class='user-name']//a
+# and for wallabag
+author: //div[@class='avatar']/following-sibling::a
+
+strip_id_or_class: toc
+
+# remove large gaps between <p>
+find_string: ">&nbsp;</p
+replace_string: "></p
+
+prune: no
+tidy: no
+
+test_url: https://community.element14.com/technologies/test-and-measurement/b/blog/posts/building-solderable-in-circuit-oscilloscope-probes

community.openstreetmap.org.txt

@@ -1,4 +1,12 @@
+# [Fulltext-RSS] needs this to catch page 2+
+http_header(user-agent): curl/7.83.1
+
+body: //div[contains(@id, 'post_')]
+
 next_page_link: //link[@rel='next']/@href
+
+prune: no
+tidy: no
+
 test_url: https://community.openstreetmap.org/t/lidar-mapping-of-roads/97100
 test_contains: Roadroid had an app since 2011, so we are probably the longest lasting app for the issue
-

countrylife.co.uk.txt

@@ -0,0 +1,28 @@
+http_header(user-agent): Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:133.0) Gecko/20100101 Firefox/133.0
+
+body: //div[@class='articleBody'] | //div[contains(@class, 'featured-media')]
+title: normalize-space(//h1[@class='title-primary'])
+
+strip_id_or_class: collection
+strip_id_or_class: post-tags
+strip_id_or_class: keystone-voep-widget-3
+strip_id_or_class: hidden-md
+strip_id_or_class: hidden-lg
+
+
+# rewrite image parameters to show images in wallabag and FTR
+
+strip_attr: //img/@data-srcset
+
+find_string: data-processed src="https://
+replace_string: foo="" bar="https://
+
+find_string: data-src="https://
+replace_string: dummy="" src="https://
+
+
+prune: no
+tidy: no
+
+test_url: https://www.countrylife.co.uk/food-drink/curious-questions-how-did-the-tea-bag-take-over-from-loose-leaf-tea-219407
+test_url: https://www.countrylife.co.uk/architecture/ptolemy-dean-the-magic-that-happens-when-you-stop-to-draw-a-place-instead-of-just-taking-a-photograph-274700

derekseaman.com.txt

@@ -0,0 +1,6 @@
+body: //div[@class='entry-content']
+
+prune: no
+tidy: no
+
+test_url: https://www.derekseaman.com/2019/09/how-to-pi-hole-plus-dnscrypt-setup-on-raspberry-pi-4.html

diepresse.com.txt

@@ -4,25 +4,26 @@
 # or add a category, e.g.:
 # https://www.diepresse.com/rss/kultur/kunst
 
-
+title: //article/h1[1]
 title: //div[@class='article']/h1
 date: substring-before(//p[@class='articletime'],'|')
+author: //meta[@name='cXenseParse:author']/@content
 author: //div[@class='author']/descendant::a
 body: //article | //div[@id='articletext'] | //div[@id='article-body']
 
 strip: //div[@class='meta__date']
 strip: //div[@class='meta__authors']
-strip: //h1[@class='article__title']
+strip: //article/h1[1]
 strip: //div[contains(@class, 'fm-relation')]
-strip: //svg
 strip: //div[@class='vued']
+strip: //svg
+strip: //button
 
 strip_id_or_class: skyline
 strip_id_or_class: article__actions
 strip_id_or_class: article__byline
 strip_id_or_class: article__breadcrumbs
 
-
 # strip gerneric text images when there is no article photo/image
 
 find_string: https://www.diepresse.com/assets_v2/images/

discuss.logseq.com.txt

@@ -0,0 +1,11 @@
+# [Fulltext-RSS] needs this to catch page 2+
+http_header(user-agent): curl/7.83.1
+
+body: //div[contains(@id, 'post_')]
+
+next_page_link: //link[@rel='next']/@href
+
+prune: no
+tidy: no
+
+test_url: https://discuss.logseq.com/t/concerns-on-db-version-and-future-state-from-a-3-year-user/29225

haaretz.com.txt

@@ -1,3 +1,30 @@
+http_header(user-agent): Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:132.0) Gecko/20100101 Firefox/132.0
+
+body: //article[1]/div[1]/header[1] | //article[1]/div[1]/div[1]/section[1] | //div[@data-test="articleBody"]
+
+strip_id_or_class: trinity-iframe
+strip_id_or_class: undefined
+
+strip: //nav
+strip: //button
+strip: //svg
+
+strip: //header//h1
+strip: //div[@data-test='shareBar']
+strip: //div[@data-display-dates='true']/parent::div
+strip: //div[@data-test='tags']
+strip: //a[contains(@href, 'mailto:')]
+
+prune: no
+tidy: no
+
+
+strip_attr: //img[@height='9']/@width
+strip_attr: //img[@height='9']/@height
+
+
+### old version: 2020-2024
+
 body: //div[@data-test="articleBody"]
 title: //meta[@property="og:title"]/@content
 date: //meta[@property="article:published"]/@content
@@ -11,4 +38,5 @@ strip: //ul[@data-test="relatedArticles"]
 strip: //div[contains(@id, 'newsletter')]
 strip: //button
 
+
 test_url: https://www.haaretz.com/israel-news/.premium-with-israel-s-encouragement-nso-sold-spyware-to-uae-and-other-gulf-states-1.9093465

habr.com.txt

@@ -1,6 +1,8 @@
+body: //div[@id='post-content-body']
 body: //div[contains(@class, 'post__body')]
 
 strip: //section[@class='article__infopanel']
+strip: //script
 
 prune: no
 tidy: no

hpd.de.txt

@@ -0,0 +1,13 @@
+body: //article[1]/div/div[@class='content'] | //figure[contains(@class, 'file-image')]
+date: //article[1]//time/@datetime
+author: //p[@class='authors']/i
+
+strip_id_or_class: element-invisible
+
+strip: //a[contains(@href, 'https://steadyhq.com/')]/parent::*
+
+prune: no
+tidy: no
+
+test_url: https://hpd.de/artikel/mythos-thule-22499
+test_url: https://hpd.de/artikel/schaffen-affengehirne-auch-links-17728

kuemmerle.name.txt

@@ -0,0 +1,19 @@
+body: //article[contains(concat(' ',normalize-space(@class),' '),' post ')] | //div[contains(@class, 'page-banner-inner')]
+title: //meta[@name='twitter:title']/@content
+author: //div[contains(@class, 'entry-meta')]//a[contains(@href, '/author/')]
+date: //time/@datetime
+
+strip: //header
+strip: //footer
+strip: //svg
+
+strip: //div[contains(@class, 'rmp-widgets-container')]/self::div | //div[contains(@class, 'rmp-widgets-container')]/preceding-sibling::hr[1] | //div[contains(@class, 'rmp-widgets-container')]/following-sibling::*
+
+strip_id_or_class: rmp-results-widget
+strip_id_or_class: rmp-rating-widget
+strip_id_or_class: rmp-feedback-widget
+strip_id_or_class: sydney-post-sharing
+
+prune: no
+
+test_url: https://kuemmerle.name/zeit-fuer-ein-gedicht-26

lexpress.fr.txt

@@ -0,0 +1,10 @@
+body: //article[1] | //*[contains(@class, 'article__lead')] | //div[@class='article__image']
+
+replace_string(<h2): <h4
+replace_string(</h2>): </h4>
+
+prune: no
+tidy: no
+
+test_url: https://www.lexpress.fr/idees-et-debats/abel-quentin-le-climat-est-une-question-de-vie-ou-de-mort-pas-les-toilettes-non-genrees-2ZQAOWQ46JEE5I654A5IXI43WQ/
+test_url: https://www.lexpress.fr/economie/high-tech/les-reverse-etl-la-solution-pour-activer-vos-donnees-clients-IL63BDTD3ZBVLIEDWVBDNM2FAM/

macg.co.txt

@@ -1,14 +1,5 @@
-date: //time[@itemprop="datePublished"]/@datetime
-
-strip: //div[contains(concat(' ',normalize-space(@class),' '),' plusLoin ')]
-strip: //select
+body: //div[contains(concat(' ',normalize-space(@class),' '),' print:shadow-none ')]//article
+strip: //footer
 strip_id_or_class: comments
-strip_id_or_class: smart-paging-pager
-strip_id_or_class: megaUne
-strip_id_or_class: pas
-strip_id_or_class: field-name-field-pour-aller-plus-loin
-
-next_page_link: //div[contains(concat(' ',normalize-space(@class),' '),' smart-paging-pager ')]//a[@title='Aller à la page suivante']
 
-body: //section[contains(concat(' ',normalize-space(@class),' '),' corps ')]
-test_url: http://www.macg.co/aapl/2015/09/tim-cook-rassure-sur-lavenir-du-mac-90957
+test_url: https://www.macg.co/ailleurs/2024/10/microsoft-donne-des-yeux-et-une-voix-lia-de-copilot-146279

mailchi.mp.txt

@@ -9,12 +9,18 @@ replace_string(<td): <div
 replace_string(</td): </div
 
 body: //div[@id="bodyTable"]
+body: //body[1]
 
+strip_id_or_class: awesomewrap
 strip_id_or_class: templatePreheader
 strip_id_or_class: mcnShareBlock
 strip_id_or_class: templateFooter
 strip_id_or_class: mcnFollowBlock
 
+# strip hint for browser edition
+strip: (//div[contains(@class, 'mj-outlook-group-fix')])[1]
+
 prune: no
 
+
 # Test URL needs to be something that doesn't reveal a subscriber's email address