# may not work with wallabag UI or FTR because of anti-bot technologies
# should work with wallabagger browser plugin

http_header(user-agent): Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:145.0) Gecko/20100101 Firefox/145.0
#http_header(user-agent): Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/140.0.0.0 Safari/537.36

http_header(referer): https://www.reuters.com/

body: //main[@id='main-content']//div[contains(@class, 'masthead')] | //main[@id='main-content']//article
body: //main[@id='main-content']/article[1]/div[1]
body: //div[@id='articleImage' or @id='frame_fd1fade'] | //span[@id='article-text'] | //div[@class='pageNavigation']
body: //article[@itemtype="http://schema.org/NewsArticle"]
body: //article[contains(concat(' ',normalize-space(@class),' '),' content-view ')]

author: substring-after(//p[@itemprop="author"] , 'By ')
author: substring-after(//ul[contains(@class, 'article-meta')]//p[@class='byline'] , 'By ')
date: //time/@datetime

strip_id_or_class: article-meta
strip_id_or_class: related-items
strip_id_or_class: related-container
strip_id_or_class: share-in-article-container
strip_id_or_class: meta-container
strip_id_or_class: hidden-md-up
strip_id_or_class: carousel-indicators
strip_id_or_class: foocrsl-indicators
strip_id_or_class: hidden-sm-up
strip_id_or_class: other-stories-container

strip: //svg
strip: //nav
strip: //aside
strip: //header

strip: //li[@class='next']
strip: //span[@class='articleLocation']
strip: //div[contains(@class, 'registration-prompt')]
strip: //*[@data-testid="toolbar-container" or @data-testid="ArticleToolbar" or @data-testid="LicenceContentButton" or @data-testid="promo-box" or @data-testid="ResponsiveAdSlot"]
strip: //a//span[contains(., 'opens new tab')]
strip: //a[contains(@class, 'caption__license')]
strip: //div[contains(@class, 'author-bio__')]
strip: //p[contains(@class, '_promo-box_')]
strip: //div[@data-testid="SocialIcon"]
strip: //div[@data-testid="AuthorBio"]
strip: //a[contains(@href, '/about-us/trust-principles')]/parent::*
strip: //div[contains(@class, 'article-module__read-next')]
strip: //*[@aria-hidden="true"]

# activate images in galeries/carousels
replace_string(class="carousel): class="foocrsl
replace_string(carousel-item): crslitm
replace_string(<noscript>): <!-- noscript -->
replace_string(</noscript>): <!-- /noscript -->

## [wallabag] prevent indentation:
strip_attr: //div[contains(concat(' ',normalize-space(@class),' '),' container ')]/@class


prune: no
tidy: no

test_url: https://www.reuters.com/world/us/us-attorney-general-garland-confirms-fbi-investigating-trump-2022-08-11/

test_url: https://www.reuters.com/investigates/special-report/usa-taser-experts/
test_contains: Among the settlements examined by Reuters

test_url: https://www.reuters.com/investigates/adoption
test_contains: There is one potential safeguard
