diff options
Diffstat (limited to 'inc/3rdparty/site_config/standard/pcworld.com.txt')
-rw-r--r-- | inc/3rdparty/site_config/standard/pcworld.com.txt | 19 |
1 files changed, 19 insertions, 0 deletions
diff --git a/inc/3rdparty/site_config/standard/pcworld.com.txt b/inc/3rdparty/site_config/standard/pcworld.com.txt new file mode 100644 index 00000000..30ccbb5f --- /dev/null +++ b/inc/3rdparty/site_config/standard/pcworld.com.txt | |||
@@ -0,0 +1,19 @@ | |||
1 | title: //div[@class='articleHead']//h1 | ||
2 | author: //div[@class="author-name"]/a[1] | ||
3 | body: //div[@class="main"] | ||
4 | |||
5 | # remove 'From the Lab' and 'Recent posts' text | ||
6 | strip: //div[@class='blogLabel'] | ||
7 | |||
8 | # remove byline and meta info | ||
9 | strip: //h1 | ||
10 | strip: //div[@class="article-meta"] | ||
11 | strip: //div[@class="author-info"] | ||
12 | |||
13 | #strip tags and categories | ||
14 | strip: //div[@class="department"] | ||
15 | |||
16 | #strip product cap links | ||
17 | strip: //div[@class="cap-main"] | ||
18 | strip: //div[@id="compare-lede"] | ||
19 | test_url: http://www.pcworld.com/article/262034/are-printer-companies-gouging-us-on-laser-toner-pricing.html \ No newline at end of file | ||