mirror of
https://github.com/wallabag/wallabag.git
synced 2024-12-27 01:50:29 +00:00
13 lines
583 B
Text
13 lines
583 B
Text
|
title: //div[@class="bodyText"]/h1/text()
|
||
|
|
body: //div[@class="bodyText"]
|
||
|
|
|
||
|
|
# author and date are separated by only a newline
|
||
|
|
# can't figure out how to tokenize that yet
|
||
|
|
author: //div[@class="bodyText"]/span[@class="info"]/text()
|
||
|
|
date: //div[@class="bodyText"]/span[@class="info"]/text()
|
||
|
|
|
||
|
|
# strip metdata from body text
|
||
|
|
strip: //div[@class="bodyText"]/h1/text()
|
||
|
|
strip: //div[@class="bodyText"]/span[@class="info"]
|
||
|
|
strip: //div[@class="bodyText"]/span[@class="info"]
|
||
|
|
test_url: http://www.wmnf.org/news_stories/light-rail-advocates-join-forces-to-combat-opposition-in-pinellas
|