mirror of
https://github.com/moparisthebest/wallabag
synced 2024-12-11 02:02:19 -05:00
25 lines
817 B
Plaintext
25 lines
817 B
Plaintext
author: //p[@class='mastname']
|
|
|
|
body: //div[@class='indivbody']
|
|
date: //div[@class='indivbody']/h2[1]
|
|
|
|
# Remove blog title. Specify first occurrence in case h1 is used in article
|
|
strip: //div[@class='indivbody']/h1[1]
|
|
|
|
# Remove blog description (the first p element)
|
|
strip: //div[@class='indivbody']/p[1]
|
|
|
|
# Remove navigation (second p element)
|
|
strip: //div[@class='indivbody']/p[2]
|
|
|
|
# Remove duplicate of article title. Specify first occurrence in case h3 is used in article
|
|
strip: //div[@class='indivbody']/h3[1]
|
|
|
|
# Remove publishing date, it's extracted by rule above
|
|
strip: //div[@class='indivbody']/h2[1]
|
|
|
|
# Remove duplicate of date at end, and newsletter signup
|
|
strip: //p[@class='posted']
|
|
|
|
# Leave date at top
|
|
test_url: http://www.schneier.com/blog/archives/2010/12/security_in_202.html |