update config from @fivefilters

This commit is contained in:
Nicolas Lœuillet
2015-08-01 21:20:43 +02:00
parent 7efe6a03d5
commit 3bb6a8ed2a
112 changed files with 734 additions and 121 deletions

View File

@ -7,6 +7,9 @@ body://div[@id = 'article-body']
# full content
single_page_link://td/li[@class = 'article-singlepage']/a
# continue link
single_page_link: //a[@id='continue-btn']
# caption clean up
wrap_in(i)://span[@class='articleImageCaptionwide']
move_into (//span[@class='articleImageCaptionwide'])://div[@id = 'articleImage']/p
@ -17,4 +20,4 @@ strip://p[@id = 'articlePaginationWrapper']
strip://ul[contains(@class, 'cat-breadcrumb')]
strip://div [@class= 'viewMorePhotos']
test_url: http://www.smithsonianmag.com/history-archaeology/The-Goddess-Goes-Home.html
test_url: http://www.smithsonianmag.com/history-archaeology/The-Goddess-Goes-Home.html