diff options
| -rw-r--r-- | echo-online.de.txt | 2 | ||||
| -rw-r--r-- | maxim.com.txt | 4 | ||||
| -rw-r--r-- | philly.com.txt | 5 | ||||
| -rw-r--r-- | popsci.com.txt | 11 |
4 files changed, 20 insertions, 2 deletions
diff --git a/echo-online.de.txt b/echo-online.de.txt index e53de23..d62b02a 100644 --- a/echo-online.de.txt +++ b/echo-online.de.txt @@ -1,4 +1,4 @@ -# Author: Marvin Dickhaus <github@marvindickhaus.de> +# Author: Marvin Dickhaus # 2014-10-08 #Tidy just messes up the DOM diff --git a/maxim.com.txt b/maxim.com.txt new file mode 100644 index 0000000..344866c --- /dev/null +++ b/maxim.com.txt @@ -0,0 +1,4 @@ +body: //div[contains(@class, 'field-name-body') or contains(@class, 'featured-image')] + +test_url: http://www.maxim.com/rss-feeds.xml +test_url: http://www.maxim.com/entertainment/article/second-city-chicago-goes-flames
\ No newline at end of file diff --git a/philly.com.txt b/philly.com.txt index accbd60..4e04d56 100644 --- a/philly.com.txt +++ b/philly.com.txt @@ -1,10 +1,13 @@ title: //h1[@class='entry-title'] author: //p[@class='byline']/span -body: //@id='body-content' +body: //div[contains(@class, 'body-content')] date: //div[@class='article_timestamp']/span +strip_id_or_class: related-links + strip: //@class=b-group strip: //*[contains(@style, 'none')] strip: //a[contains(@href, 'comments')] strip: //*[contains(@class, 'comment')] +test_url: http://www.philly.com/philly/blogs/sports/eagles/Davis-Happy-For-Kendricks.html test_url: http://www.philly.com/philly/sports/eagles/20120127_Ohio_State_s_Posey_didn_t_waste_time_lost_to_suspension.html
\ No newline at end of file diff --git a/popsci.com.txt b/popsci.com.txt new file mode 100644 index 0000000..2a928e2 --- /dev/null +++ b/popsci.com.txt @@ -0,0 +1,11 @@ +body: //div[contains(@class, 'field-body')] +strip_image_src: placeholder +find_string: <noscript> +replace_string: <div> +find_string: </noscript> +replace_string: </div> + +prune: no + +test_url: http://www.popsci.com/nasa-crashed-another-plane-today +test_url: http://www.popsci.com/rss.xml
\ No newline at end of file |
