1
0
mirror of https://github.com/moparisthebest/wallabag synced 2024-11-24 01:52:15 -05:00
wallabag/inc/3rdparty/site_config/standard/pcworld.com.txt
2014-07-13 10:15:40 +02:00

19 lines
564 B
Plaintext
Executable File

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