diff options
Diffstat (limited to 'inc/3rdparty/site_config/standard/post-gazette.com.txt')
-rwxr-xr-x[-rw-r--r--] | inc/3rdparty/site_config/standard/post-gazette.com.txt | 50 |
1 files changed, 25 insertions, 25 deletions
diff --git a/inc/3rdparty/site_config/standard/post-gazette.com.txt b/inc/3rdparty/site_config/standard/post-gazette.com.txt index 1ea945a0..baa9d69d 100644..100755 --- a/inc/3rdparty/site_config/standard/post-gazette.com.txt +++ b/inc/3rdparty/site_config/standard/post-gazette.com.txt | |||
@@ -1,26 +1,26 @@ | |||
1 | title: //div[@class='story_headline'] | 1 | title: //div[@class='story_headline'] |
2 | author: substring-before(substring-after(//div[@class='story_byline'],'By'),'/') | 2 | author: substring-before(substring-after(//div[@class='story_byline'],'By'),'/') |
3 | date: //div[@class='story_lastupdate'] | 3 | date: //div[@class='story_lastupdate'] |
4 | body: //div[@id='story'] | 4 | body: //div[@id='story'] |
5 | strip: //div[@class='story_byline'] | 5 | strip: //div[@class='story_byline'] |
6 | strip: //div[@class='story_lastupdate'] | 6 | strip: //div[@class='story_lastupdate'] |
7 | strip: //div[@class='story_headline'] | 7 | strip: //div[@class='story_headline'] |
8 | strip: //div[@id='abuse'] | 8 | strip: //div[@id='abuse'] |
9 | strip: //h2 | 9 | strip: //h2 |
10 | strip: //div[@class='pagenumbers_wrap'] | 10 | strip: //div[@class='pagenumbers_wrap'] |
11 | strip: //ul[@class='pagenumbers'] | 11 | strip: //ul[@class='pagenumbers'] |
12 | strip: //div[starts-with(., 'To report inappropriate comments')] | 12 | strip: //div[starts-with(., 'To report inappropriate comments')] |
13 | 13 | ||
14 | strip_id_or_class: story_share | 14 | strip_id_or_class: story_share |
15 | strip_id_or_class: OUTBRAIN | 15 | strip_id_or_class: OUTBRAIN |
16 | strip_id_or_class: story_box_right | 16 | strip_id_or_class: story_box_right |
17 | strip: //div[a[@href='http://www.post-gazette.com/pg/12062/1213990-42.stm']] | 17 | strip: //div[a[@href='http://www.post-gazette.com/pg/12062/1213990-42.stm']] |
18 | strip: //ul[@id='pikame']/li[position()>1] | 18 | strip: //ul[@id='pikame']/li[position()>1] |
19 | 19 | ||
20 | prune: no | 20 | prune: no |
21 | tidy: no | 21 | tidy: no |
22 | 22 | ||
23 | single_page_link: //a[contains(@href, '?p=0')] | 23 | single_page_link: //a[contains(@href, '?p=0')] |
24 | 24 | ||
25 | test_url: http://www.post-gazette.com/stories/sports/penguins/pens-crosby-expects-to-return-thursday-226648/ | 25 | test_url: http://www.post-gazette.com/stories/sports/penguins/pens-crosby-expects-to-return-thursday-226648/ |
26 | test_url: http://www.post-gazette.com/stories/sports/pirates/pirates-fork-over-changes-for-fans-at-pnc-park-629789 \ No newline at end of file | 26 | test_url: http://www.post-gazette.com/stories/sports/pirates/pirates-fork-over-changes-for-fans-at-pnc-park-629789 \ No newline at end of file |