diff options
author | Nicolas LÅ“uillet <nicolas.loeuillet@gmail.com> | 2013-12-06 10:13:03 +0100 |
---|---|---|
committer | Nicolas LÅ“uillet <nicolas.loeuillet@gmail.com> | 2013-12-06 10:13:03 +0100 |
commit | ac4d114214d820b20e18518a2dbc809337e39043 (patch) | |
tree | 27886128ef949b7f8dd174b0646b5a4d99883b44 /inc/3rdparty/site_config/standard/jetzt.sueddeutsche.de.txt | |
parent | d5501950e2470d52f6bf5954d2179010cdee0475 (diff) | |
download | wallabag-ac4d114214d820b20e18518a2dbc809337e39043.tar.gz wallabag-ac4d114214d820b20e18518a2dbc809337e39043.tar.zst wallabag-ac4d114214d820b20e18518a2dbc809337e39043.zip |
[add] new specific configuration files
Diffstat (limited to 'inc/3rdparty/site_config/standard/jetzt.sueddeutsche.de.txt')
-rw-r--r-- | inc/3rdparty/site_config/standard/jetzt.sueddeutsche.de.txt | 22 |
1 files changed, 22 insertions, 0 deletions
diff --git a/inc/3rdparty/site_config/standard/jetzt.sueddeutsche.de.txt b/inc/3rdparty/site_config/standard/jetzt.sueddeutsche.de.txt new file mode 100644 index 00000000..6e8af934 --- /dev/null +++ b/inc/3rdparty/site_config/standard/jetzt.sueddeutsche.de.txt | |||
@@ -0,0 +1,22 @@ | |||
1 | title: //h1 | ||
2 | author: //p[contains(@class, 'author')]/a | ||
3 | date: //p[contains(@class, 'time')] | ||
4 | body: //div[@class='content']/div[contains(@class, 'text')] | ||
5 | |||
6 | # prevent "no text" errors on multi-page articles | ||
7 | tidy: no | ||
8 | |||
9 | # we use a custom next-link detector instead of the print view because | ||
10 | # it's pretty hard to strip out the unwanted parts in the print view | ||
11 | autodetect_next_page: no | ||
12 | next_page_link: //div[contains(@class, 'text')]/div/div[contains(@class, 'paging')]/a[@class='more '] | ||
13 | |||
14 | strip: //h1 | ||
15 | |||
16 | strip_id_or_class: meta | ||
17 | strip_id_or_class: author | ||
18 | strip_id_or_class: paging | ||
19 | |||
20 | # prevent "Report an Error" from being recognized as footnote | ||
21 | footnotes: no | ||
22 | test_url: http://jetzt.sueddeutsche.de/texte/anzeigen/544308/Alles-flicken \ No newline at end of file | ||