diff options
Diffstat (limited to 'inc/3rdparty/site_config/standard/faz.net.txt')
-rw-r--r-- | inc/3rdparty/site_config/standard/faz.net.txt | 30 |
1 files changed, 30 insertions, 0 deletions
diff --git a/inc/3rdparty/site_config/standard/faz.net.txt b/inc/3rdparty/site_config/standard/faz.net.txt new file mode 100644 index 00000000..4fe5968b --- /dev/null +++ b/inc/3rdparty/site_config/standard/faz.net.txt | |||
@@ -0,0 +1,30 @@ | |||
1 | # Title | ||
2 | title: //p[@class='Content HeadlineShort'] | ||
3 | |||
4 | # Authors | ||
5 | # some are known and have a link, others don't | ||
6 | author: substring-after(//span[@class='Autor'], 'Von') | ||
7 | |||
8 | # Date | ||
9 | date: //span[@class='Datum'] | ||
10 | |||
11 | # Body | ||
12 | body: //div[@class='Artikel'] | ||
13 | |||
14 | # Removements before body text | ||
15 | strip: //div[@class='Breadcrumbs'] | ||
16 | strip: //div[@class='QuickSearchBox'] | ||
17 | strip: //div[@class='FAZArtikelEinleitung'] | ||
18 | strip: //div[@class='FAZArtikelReiter'] | ||
19 | strip: //div[@class='clear'] | ||
20 | |||
21 | # General removements | ||
22 | strip: //span[@class='Bildnachweis'] | ||
23 | |||
24 | # Removements after body text | ||
25 | strip: //div[@class='ArtikelAbbinder'] | ||
26 | strip: //div[@class='ArtikelKommentieren Artikelfuss GETS;tk;boxen.top-lesermeinungen;tp;content'] | ||
27 | strip: //div[@class='FAZArtikelKommentare FAZArtikelContent'] | ||
28 | strip: //div[@class='FAZArtikelFunktionen'] | ||
29 | strip: //div[@id='FAZContentRight'] | ||
30 | test_url: http://www.faz.net/aktuell/gesellschaft/ehe-haltbarkeitsformel-verliebe-dich-oft-verlobe-dich-selten-heirate-vielleicht-11685306.html \ No newline at end of file | ||