diff options
Diffstat (limited to 'inc/3rdparty/site_config/standard/scientificamerican.com.txt')
-rwxr-xr-x | inc/3rdparty/site_config/standard/scientificamerican.com.txt | 25 |
1 files changed, 0 insertions, 25 deletions
diff --git a/inc/3rdparty/site_config/standard/scientificamerican.com.txt b/inc/3rdparty/site_config/standard/scientificamerican.com.txt deleted file mode 100755 index 1b3f31cf..00000000 --- a/inc/3rdparty/site_config/standard/scientificamerican.com.txt +++ /dev/null | |||
@@ -1,25 +0,0 @@ | |||
1 | # | ||
2 | # After site revisions at SciAm, this configuration does | ||
3 | # not work, especially for multi-page articles. For | ||
4 | # every article there is now a "Print" link which | ||
5 | # is far more reliable. So this configuration should be | ||
6 | # removed or disabled. | ||
7 | # 2/3/13 | ||
8 | # | ||
9 | |||
10 | # meta data | ||
11 | title://h1[@class = 'articleTitle'] | ||
12 | author:substring-after(//span[@class = 'byline'],'By ') | ||
13 | date:substring-before(//span[@class = 'datestamp'],'|') | ||
14 | |||
15 | #body content | ||
16 | body://div[@id = 'articleContent'] | ||
17 | #next_page_link://li[@id = 'flairPagination']/a[last()] | ||
18 | |||
19 | single_page_link: //a[contains(@href, 'print=true')] | ||
20 | |||
21 | #cleanup | ||
22 | strip://div[@class = 'fsgBooks'] | ||
23 | |||
24 | test_url: http://www.scientificamerican.com/article.cfm?id=do-brain-scans-comatose-patients-reveal-conscious-state | ||
25 | test_url: http://www.scientificamerican.com/article.cfm?id=solar-wind-transforms-venus-into-shape-of-comet \ No newline at end of file | ||