diff options
Diffstat (limited to 'menshealth.com.txt')
| -rw-r--r-- | menshealth.com.txt | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/menshealth.com.txt b/menshealth.com.txt new file mode 100644 index 0000000..a1a46f6 --- /dev/null +++ b/menshealth.com.txt @@ -0,0 +1,16 @@ +# need to find a way to eliminate <span> content for "related content" without eliminating important content + +convert_double_br_tags: [yes] +#body: //div[@id='leftside'] +title: //h1 +title: //h2 +Author: substring-after(//h4, 'By ') +Author: substring-after(//h4, 'By: ') +#Strip: //span +strip_id_or_class: morefromcat +strip_id_or_class: mostpopular +strip_id_or_class: articlepagination +strip_id_or_class: toolbar +body: //div[@id='zmodcontent'] +single_page_link: //li[@class='onepage'] //a[contains (@href, 'printer.php')] +test_url: http://www.menshealth.com/mhlists/pursuit_of_happiness/index.php
\ No newline at end of file |