]>
Commit | Line | Data |
---|---|---|
ac4d1142 NL |
1 | title: //h1\r |
2 | date: //div[@class='datum']\r | |
3 | single_page_link: //a[contains(@href, '?type=99')]\r | |
4 | \r | |
5 | # this hack preserves the intro text, because it would be striped otherwise if the title is set to //h1\r | |
6 | dissolve: //div[@class='artikelMeldung']\r | |
7 | \r | |
8 | \r | |
9 | strip_id_or_class: anzeige\r | |
10 | strip_id_or_class: top_page_navigation\r | |
11 | strip_id_or_class: cr_image_container\r | |
12 | strip_id_or_class: cr_image_reference\r | |
13 | strip_id_or_class: cr_image_icon\r | |
14 | strip_id_or_class: _close_txt\r | |
15 | strip_id_or_class: _close_ico\r | |
16 | strip_id_or_class: clearer\r | |
17 | \r | |
18 | strip://h1\r | |
19 | strip://h6\r | |
20 | strip://div[contains(@id, 'plista')]\r | |
21 | strip://img[contains(@id,'tiny')]\r | |
22 | strip://img[@class='cr_image']\r | |
23 | \r | |
24 | # strip url at the top\r | |
25 | strip: //p[@style='font-size: 10px;']\r | |
26 | ||
27 | test_url: http://www.elektroniknet.de/automotive/technik-know-how/sicherheitselektronik/article/87717/0/Besser_als_die_Wirklichkeit/ |