diff options
Diffstat (limited to 'inc/3rdparty/site_config/standard/welt.de.txt')
-rw-r--r-- | inc/3rdparty/site_config/standard/welt.de.txt | 22 |
1 files changed, 22 insertions, 0 deletions
diff --git a/inc/3rdparty/site_config/standard/welt.de.txt b/inc/3rdparty/site_config/standard/welt.de.txt new file mode 100644 index 00000000..6e4f828f --- /dev/null +++ b/inc/3rdparty/site_config/standard/welt.de.txt | |||
@@ -0,0 +1,22 @@ | |||
1 | # set body | ||
2 | tidy: no | ||
3 | body: //div[contains(@class, 'articleContent')] | ||
4 | |||
5 | # remove clutter | ||
6 | strip: //div[@class='advertising'] | ||
7 | strip: //div[@class='themenalarm'] | ||
8 | strip: //div[contains(@class, 'inTextTeaser')] | ||
9 | |||
10 | # remove captions | ||
11 | strip: //span[@class='copyRight'] | ||
12 | |||
13 | # remove photo galleries and extras | ||
14 | strip: //div[contains(@class, 'textGallery')] | ||
15 | strip: //div[contains(@class, 'videoGallery')] | ||
16 | strip: //div[contains(@class, 'imageGallery')] | ||
17 | strip: //div[contains(@class, 'openContent')] | ||
18 | |||
19 | # remove comments | ||
20 | strip: //div[@id = 'writeComment'] | ||
21 | |||
22 | test_url: http://www.welt.de/vermischtes/weltgeschehen/article11050589/27-Bergleute-in-neuseelaendischer-Mine-vermisst.html \ No newline at end of file | ||