2014-07-13 04:15:40 -04:00
|
|
|
# set body
|
|
|
|
|
tidy: no
|
|
|
|
|
body: //div[contains(@class, 'articleContent')]
|
|
|
|
|
|
|
|
|
|
# remove clutter
|
|
|
|
|
strip: //div[@class='advertising']
|
|
|
|
|
strip: //div[@class='themenalarm']
|
|
|
|
|
strip: //div[contains(@class, 'inTextTeaser')]
|
|
|
|
|
|
|
|
|
|
# remove captions
|
|
|
|
|
strip: //span[@class='copyRight']
|
|
|
|
|
|
|
|
|
|
# remove photo galleries and extras
|
|
|
|
|
strip: //div[contains(@class, 'textGallery')]
|
|
|
|
|
strip: //div[contains(@class, 'videoGallery')]
|
|
|
|
|
strip: //div[contains(@class, 'imageGallery')]
|
|
|
|
|
strip: //div[contains(@class, 'openContent')]
|
|
|
|
|
|
|
|
|
|
# remove comments
|
|
|
|
|
strip: //div[@id = 'writeComment']
|
|
|
|
|
|
2013-12-06 04:13:03 -05:00
|
|
|
test_url: http://www.welt.de/vermischtes/weltgeschehen/article11050589/27-Bergleute-in-neuseelaendischer-Mine-vermisst.html
|
