diff options
| author | FiveFilters.org <fivefilters@fivefilters.org> | 2013-02-27 23:43:10 +0100 |
|---|---|---|
| committer | FiveFilters.org <fivefilters@fivefilters.org> | 2013-02-27 23:43:10 +0100 |
| commit | 9a69161c8646f63b4d9fa17c6ac3ab922d625859 (patch) | |
| tree | 62a446347e1279f00383fdd7f9637cfd58a50879 /thedaily.com.txt | |
| download | ftr-site-config-9a69161c8646f63b4d9fa17c6ac3ab922d625859.tar.gz ftr-site-config-9a69161c8646f63b4d9fa17c6ac3ab922d625859.zip | |
Initial commit
Diffstat (limited to 'thedaily.com.txt')
| -rw-r--r-- | thedaily.com.txt | 24 |
1 files changed, 24 insertions, 0 deletions
diff --git a/thedaily.com.txt b/thedaily.com.txt new file mode 100644 index 0000000..e255e6a --- /dev/null +++ b/thedaily.com.txt @@ -0,0 +1,24 @@ +#keep all body text +prune: no + +#title, body, metadata +title: //div[@class='story_header']/h1 +body: //div[@id='content'] +author: substring-after(//span[@class='byline'], "by ") +author: substring-after(//span[@class='byline'], "By ") +author: //span[@class='byline'] +date: //span[@class='date'] + +#formatting +convert_double_br_tags: yes +dissolve: //div[@class='slides_full']/ul/li + +# cleanup +strip: //a[@id='story_note'] +strip: //br +strip: //div[@class='intro'] +strip: //div[@class='share-block'] +strip: //div[@class='sidebar-social'] +strip: //div[@class='top-stories'] +strip: //div[@class='prevnext'] +test_url: http://www.thedaily.com/page/2012/01/09/010912-news-college-costs-1-5/
\ No newline at end of file |