# mirror of theregister.co.uk.txt
single_page_link: //link[contains(@href, 'm.theregister')]
if_page_contains: //div[@id='nextpage']
strip: //div[@class='wptl btm']
body: //div[contains(@class,'article_head')]//h2 | //div[@id='body']
author: //div[@class='byline']/a[0]

strip_id_or_class: promo_article

# The Register embeds some quotes in a div with the class 'blockextract'.
# Unfortunately Readability considers 'extract' as an indication that a node
# should not be kept ("unlikely content")
# find/replace here will prevent Readability from removing these quotes
# wrap_in ensures that the div is wrapped in a blockquote tag
find_string: class="blockextract"
replace_string: class="blockquote"
wrap_in(blockquote): //div[contains(@class, 'blockquote')]

#multipage
test_url: http://www.theregister.co.uk/2015/07/06/geeks_guide_spaceguard_center/
#singlepage
test_url: http://www.theregister.co.uk/2015/07/06/us_japan_massive_robots_in_the_ring/
#with author
test_url: https://www.theregister.co.uk/2019/02/11/620_million_hacked_accounts_dark_web/