mirror of
https://github.com/wallabag/wallabag.git
synced 2024-12-20 22:56:30 +00:00
19 lines
582 B
Text
19 lines
582 B
Text
|
title: //div[@class='articleHead']//h1
|
||
|
author: //div[@class="author-name"]/a[1]
|
||
|
body: //div[@class="main"]
|
||
|
|
||
|
# remove 'From the Lab' and 'Recent posts' text
|
||
|
strip: //div[@class='blogLabel']
|
||
|
|
||
|
# remove byline and meta info
|
||
|
strip: //h1
|
||
|
strip: //div[@class="article-meta"]
|
||
|
strip: //div[@class="author-info"]
|
||
|
|
||
|
#strip tags and categories
|
||
|
strip: //div[@class="department"]
|
||
|
|
||
|
#strip product cap links
|
||
|
strip: //div[@class="cap-main"]
|
||
|
strip: //div[@id="compare-lede"]
|
||
|
test_url: http://www.pcworld.com/article/262034/are-printer-companies-gouging-us-on-laser-toner-pricing.html
|