Merge remote-tracking branch 'upstream/master'

apple.news.txt

@@ -0,0 +1,2 @@
+single_page_link: //p//a[contains(., 'Click here')]
+test_url: https://apple.news/AHQREjzH0Ts6iikKhNe6o8w

heise.de.txt

@@ -42,6 +42,12 @@ strip_id_or_class: ad_
 # Some optimizations
 replace_string(<h5>): <h2>
 replace_string(</h5>): </h2>
+replace_string(<title>Druckversion - ): <title>
+replace_string( | heise online</title>): </title>
+replace_string( | c't Magazin</title>): </title>
+replace_string( | Telepolis</title>): </title>
+replace_string( | heise Security</title>): </title>
+replace_string( | heise Autos</title>): </title>
 # this line breaks the parser
 #replace_string(<span class="bild_rechts" style="width:): <p "
 replace_string(<div class="heisebox">): <blockquote>

iphon.fr.txt

@@ -0,0 +1,5 @@
+date: //meta[@name="date"]/@content
+author: //meta[@name="author"]/@content
+strip_id_or_class: follow
+
+test_url: http://www.iphon.fr/post/iphone-8-x-recharge-sans-fil-cable-simultanee-891682

lemonde.fr.txt

@@ -17,6 +17,11 @@ body: //div[@id='articleBody']
 find_string: <a target='_blank' onclick='return false;' class='lien_interne conjug'
 replace_string: <input type='hidden' style='display:none;' 
 
+# Remove the insane cross-linking categories "Toute l’actualité"
+find_string: <a class="lien_interne rub"
+replace_string: <input type="hidden" style="display:none;"
+
 prune: no
 
 test_url: http://www.lemonde.fr/economie/article/2011/07/05/moody-s-abaisse-la-note-du-portugal-de-quatre-crans_1545237_3234.html
+test_url: http://www.lemonde.fr/big-browser/article/2017/10/27/assassinat-de-kennedy-ce-qu-on-a-appris-dans-les-documents-declassifies_5207029_4832693.html

lenta.ru.txt

@@ -1,7 +1,9 @@
 body: //div[@itemprop='articleBody'] | //img[@itemprop='image']
 strip_id_or_class: b-inline-topics-box
+strip: //iframe[@name='banner']
 
 # do not prune embedded videos
 prune: no
 
 test_url: https://lenta.ru/news/2016/07/08/weakpound/
+test_url: https://lenta.ru/news/2017/11/01/bigdata/

nature.com.txt

@@ -1,2 +1,2 @@
-body: //div[@id='content']
+body: //div[@id='article']
 test_url: https://www.nature.com/npp/journal/v42/n11/full/npp201786a.html

slate.fr.txt

@@ -4,10 +4,10 @@
 
 body: //article[contains(concat(' ',normalize-space(@class),' '),' full_article ')]
 
-strip_id_or_class: media_legend
 strip_id_or_class: article_author
 strip_id_or_class: tag_articles
 strip_id_or_class: article_insert
+strip_id_or_class: col-right
 
 strip_id_or_class: tag
 strip_id_or_class: category

sowetanlive.co.za.txt

@@ -0,0 +1,7 @@
+body: //div[contains(concat(' ',normalize-space(@class),' '),' article-widgets ')]
+strip_id_or_class: related_articles
+find_string:=s180"
+replace_string:=s750"
+
+test_url: https://www.sowetanlive.co.za/rss/?publication=sowetan-live
+test_url: https://www.sowetanlive.co.za/sundayworld/news/2017-11-08-manana-should-pay-medical-bills-for-assault-victims-court-told/

wsj.com.txt

@@ -3,10 +3,10 @@ body: //div[@id='wsj-article-wrap']
 # is this still used?
 body: //div[@id='article_story_body']
 
-author: //h3[@class='byline']/a
+author: //meta[@name="author"]/@content
 # for slide show content
 body: //ul[@id='imageSlide']//li[@class='firstSlide']//img | (//div[@class='txt_body']//p)[1]
-date: //li[@class='dateStamp']/small
+date: //meta[@itemprop="dateCreated"]/@content
 
 strip_id_or_class: insetFullBracket
 strip_id_or_class: insettipBox