diff options
author | Nicolas LÅ“uillet <nicolas@loeuillet.org> | 2014-07-13 10:15:40 +0200 |
---|---|---|
committer | Nicolas LÅ“uillet <nicolas@loeuillet.org> | 2014-07-13 10:15:40 +0200 |
commit | 4e067ceabd705201a16b4c92cf4b23f3b990326c (patch) | |
tree | 939f3a8e5ff3ab9ee414a57a895d3e78e1d46ce3 /inc/3rdparty/site_config/standard/uni-watch.com.txt | |
parent | 58dbe103889148def78b0fc8744d3f94c56a1561 (diff) | |
download | wallabag-4e067ceabd705201a16b4c92cf4b23f3b990326c.tar.gz wallabag-4e067ceabd705201a16b4c92cf4b23f3b990326c.tar.zst wallabag-4e067ceabd705201a16b4c92cf4b23f3b990326c.zip |
updated specific configuration for parsing
Diffstat (limited to 'inc/3rdparty/site_config/standard/uni-watch.com.txt')
-rwxr-xr-x[-rw-r--r--] | inc/3rdparty/site_config/standard/uni-watch.com.txt | 30 |
1 files changed, 15 insertions, 15 deletions
diff --git a/inc/3rdparty/site_config/standard/uni-watch.com.txt b/inc/3rdparty/site_config/standard/uni-watch.com.txt index cbe87d19..4a5ae344 100644..100755 --- a/inc/3rdparty/site_config/standard/uni-watch.com.txt +++ b/inc/3rdparty/site_config/standard/uni-watch.com.txt | |||
@@ -1,17 +1,17 @@ | |||
1 | author: substring-before(substring-after(//div[@class='post-byline'], 'By '), ', on') | 1 | author: substring-before(substring-after(//div[@class='post-byline'], 'By '), ', on') |
2 | date: substring-after(//div[@class='post-byline'], ', on') | 2 | date: substring-after(//div[@class='post-byline'], ', on') |
3 | 3 | ||
4 | # for some reason, the following is producing a "no text [48]" error | 4 | # for some reason, the following is producing a "no text [48]" error |
5 | #title: //div[@class='post-headline'] | 5 | #title: //div[@class='post-headline'] |
6 | 6 | ||
7 | # for some reason, the following doesn't appear to isolate just the body copy | 7 | # for some reason, the following doesn't appear to isolate just the body copy |
8 | body: //div[@class='post-bodycopy'] | 8 | body: //div[@class='post-bodycopy'] |
9 | 9 | ||
10 | # we solve the above issue by stripping out everything else we don't want | 10 | # we solve the above issue by stripping out everything else we don't want |
11 | # these can probably all be removed if the body: command above worked | 11 | # these can probably all be removed if the body: command above worked |
12 | strip_id_or_class: reply | 12 | strip_id_or_class: reply |
13 | strip_id_or_class: left | 13 | strip_id_or_class: left |
14 | strip_id_or_class: post-headline | 14 | strip_id_or_class: post-headline |
15 | strip_id_or_class: post-byline | 15 | strip_id_or_class: post-byline |
16 | strip_id_or_class: footer | 16 | strip_id_or_class: footer |
17 | test_url: http://www.uni-watch.com/2011/10/18/the-curious-case-of-steve-debergs-microphone-and-speaker/ \ No newline at end of file | 17 | test_url: http://www.uni-watch.com/2011/10/18/the-curious-case-of-steve-debergs-microphone-and-speaker/ \ No newline at end of file |