diff options
Diffstat (limited to 'neh.gov.txt')
| -rw-r--r-- | neh.gov.txt | 17 |
1 files changed, 17 insertions, 0 deletions
diff --git a/neh.gov.txt b/neh.gov.txt new file mode 100644 index 0000000..e7cc431 --- /dev/null +++ b/neh.gov.txt @@ -0,0 +1,17 @@ +#host configuration should be http://www.neh.gov/news/humanities/ + + +#meta data +title:substring-after(substring-after(//title,':'),':') +author:substring-after(//h2[@class = 'subHead'],'By') +date:substring-before(substring-after(//title,':'),':') + +#img and caption handling +wrap_in(small)://div[@id = 'mainContent']/table/descendant::p/descendant::text() +wrap_in(fieldset)://div[@id = 'mainContent']/table + +# clean up +strip: //table[@class = 'marginpaddingTop'] +strip: //h2[@class = 'subHead'] + +test_url: http://www.neh.gov/news/humanities/2011-11/IslamicScholar.html
\ No newline at end of file |