diff options
| author | FiveFilters.org <fivefilters@fivefilters.org> | 2013-09-10 17:09:30 +0200 |
|---|---|---|
| committer | FiveFilters.org <fivefilters@fivefilters.org> | 2013-09-10 17:09:30 +0200 |
| commit | da27b5ec115d898961b3f2b1ebdb7586ac07ae8e (patch) | |
| tree | 8fde883687bfa32ccc8b6e0be7b94e9c8c93685e | |
| parent | 028133cec62243ca45ec2b0f4c336598e6240c2f (diff) | |
| download | ftr-site-config-da27b5ec115d898961b3f2b1ebdb7586ac07ae8e.tar.gz ftr-site-config-da27b5ec115d898961b3f2b1ebdb7586ac07ae8e.zip | |
washingtonpost.com
| -rw-r--r-- | articles.washingtonpost.com.txt | 11 | ||||
| -rw-r--r-- | washingtonpost.com.txt | 10 |
2 files changed, 20 insertions, 1 deletions
diff --git a/articles.washingtonpost.com.txt b/articles.washingtonpost.com.txt new file mode 100644 index 0000000..a76c2d0 --- /dev/null +++ b/articles.washingtonpost.com.txt @@ -0,0 +1,11 @@ +body: //div[contains(@class, "article_body")] +# print view +body: //div[@id='print_facet']//div[@id='body'] + +tidy: no +prune: no + +single_page_link: concat(substring-before(//div[@id="echo_container_a"]/@guid, '_story.html'), '_print.html') + +test_url: http://articles.washingtonpost.com/2011-10-22/world/35279694_1_germany-acts-german-leaders-chancellor-angela-merkel +test_url: http://articles.washingtonpost.com/2013-05-31/opinions/39658000_1_chemical-weapons-mass-destruction-cartels
\ No newline at end of file diff --git a/washingtonpost.com.txt b/washingtonpost.com.txt index 47358d8..0318aba 100644 --- a/washingtonpost.com.txt +++ b/washingtonpost.com.txt @@ -1,4 +1,9 @@ -body: //div[@class="article_body"] +# Seems to be redirecting to articles.washingtonpost.com for many users + +body: //div[contains(@class, "article_body")] +# print view +body: //div[@id='print_facet']//div[@id='body'] + author://meta[@name='DC.creator']/@content title://meta[@name='title']/@content date://div[contains(@class,'byline')]//span[contains(@class,'published')]/@title @@ -16,6 +21,9 @@ strip_id_or_class: carousel strip_id_or_class: toolbar strip_id_or_class: module +# Change gJQAwdJG4U_story.html to gJQAwdJG4U_story_print.html +single_page_link: concat(substring-before(//link[@rel="canonical"]/@href, "_story.html"), "_story_print.html") + test_url: http://www.washingtonpost.com/world/europe/in-europe-new-fears-of-german-might/2011/10/19/gIQA3baZ7L_story.html?hpid=z1 test_url: http://www.washingtonpost.com/national/health-science/radical-theory-of-first-americans-places-stone-age-europeans-in-delmarva-20000-years-ago/2012/02/28/gIQA4mriiR_story.html test_url: http://www.washingtonpost.com/lifestyle/magazine/the-sorry-fate-of-a-tech-pioneer-halsey-minor-and-historic-virginia-estate-carters-grove/2012/05/30/gJQAwdJG4U_story.html
\ No newline at end of file |