27 lines
821 B
Plaintext
Executable File
27 lines
821 B
Plaintext
Executable File
title: //h1
|
|
date: //div[@class='datum']
|
|
single_page_link: //a[contains(@href, '?type=99')]
|
|
|
|
# this hack preserves the intro text, because it would be striped otherwise if the title is set to //h1
|
|
dissolve: //div[@class='artikelMeldung']
|
|
|
|
|
|
strip_id_or_class: anzeige
|
|
strip_id_or_class: top_page_navigation
|
|
strip_id_or_class: cr_image_container
|
|
strip_id_or_class: cr_image_reference
|
|
strip_id_or_class: cr_image_icon
|
|
strip_id_or_class: _close_txt
|
|
strip_id_or_class: _close_ico
|
|
strip_id_or_class: clearer
|
|
|
|
strip://h1
|
|
strip://h6
|
|
strip://div[contains(@id, 'plista')]
|
|
strip://img[contains(@id,'tiny')]
|
|
strip://img[@class='cr_image']
|
|
|
|
# strip url at the top
|
|
strip: //p[@style='font-size: 10px;']
|
|
|
|
test_url: http://www.elektroniknet.de/automotive/technik-know-how/sicherheitselektronik/article/87717/0/Besser_als_die_Wirklichkeit/ |