aboutsummaryrefslogtreecommitdiffhomepage
path: root/inc/3rdparty/site_config/standard/macworld.com.txt
diff options
context:
space:
mode:
Diffstat (limited to 'inc/3rdparty/site_config/standard/macworld.com.txt')
-rw-r--r--inc/3rdparty/site_config/standard/macworld.com.txt24
1 files changed, 24 insertions, 0 deletions
diff --git a/inc/3rdparty/site_config/standard/macworld.com.txt b/inc/3rdparty/site_config/standard/macworld.com.txt
new file mode 100644
index 00000000..96175872
--- /dev/null
+++ b/inc/3rdparty/site_config/standard/macworld.com.txt
@@ -0,0 +1,24 @@
1title: //article//h1
2date: //meta[@name="date"]/@content
3author: //div[@class="author-name" or @class="article-byline"]/a[1]
4
5body: //section[@class="page"]
6
7# remove 'From the Lab' and 'Recent posts' text
8strip: //div[@class='blogLabel']
9
10# remove byline and meta info
11strip: //div[@class="article-meta"]
12strip: //div[@class="author-info"]
13
14#strip tags and categories
15strip: //div[@class="department"]
16
17#strip product cap links
18strip: //div[@class="cap-main"]
19strip: //div[@id="compare-lede"]
20
21prune: no
22
23# copes less well with Review pages, seems fine for News
24test_url: http://www.macworld.com/article/163184/2011/10/the_ipod_as_an_iconic_cultural_force.html \ No newline at end of file