1
0
mirror of https://github.com/moparisthebest/wallabag synced 2024-12-25 08:48:53 -05:00
wallabag/inc/3rdparty/site_config/standard/fnal.gov.txt
2013-12-06 10:13:03 +01:00

15 lines
733 B
Plaintext

title: normalize(//h1)
author: //td/p[position()=last()]/em
# I swear, this is really the best way to do this
date: normalize(//td[contains(@style, "color: #ffffff")])
# my god, it's full of tables
body: /table/tbody/tr[5]//table/tbody//table/tbody/tr/td
strip: //h1
# the following two lines strip the byline at the end of the article (the byline is a <p> that consists of an em dash and then some text in an <em>). I have no idea why I can't just strip //p[position()=last()], but trying to do so includes a bunch of other crap in the output.
strip: //p[position()=last()]/em
strip: //p[position()=last()]/child::text()
test_url: http://www.fnal.gov/pub/today/archive_2011/today11-11-09_MuonDepartmentReadMore.html