diff options
| -rw-r--r-- | theverge.com.txt | 19 |
1 files changed, 11 insertions, 8 deletions
diff --git a/theverge.com.txt b/theverge.com.txt index 3960fb9..6a0d560 100644 --- a/theverge.com.txt +++ b/theverge.com.txt @@ -1,13 +1,12 @@ -title: //h1[contains(@class, "headline")] - author: //p[contains(@class, "byline")]/a[contains(@class, "author")] -date: substring-after(normalize-space(//p[contains(@class, "byline")]/span[contains(@class, "publish-date")]), "on ") +date: //span[contains(@class, "publish-date")]/time[@pubdate]/@datetime -body: //article[contains(@class, 'feature-entry')] +body: //div[contains(@class, 'entry-content')] +# for vergecasts, e.g. http://www.theverge.com/2013/8/22/4648566/the-vergecast-090-august-22th-2013-video body: //article prune: no -tidy: no +#tidy: no strip: //article/header strip: //*[@id='sticky-menu'] @@ -22,9 +21,12 @@ strip_id_or_class: related-product-meta strip_id_or_class: comments strip_id_or_class: ui-jump-list strip_id_or_class: pullquote +strip_id_or_class: m-ad +strip_id_or_class: social-sharing +strip_id_or_class: m-video-entry__excerpt -find_string: <script -replace_string: <div style="display:none" +find_string: <script +replace_string: <div style="display:none" find_string: </script> replace_string: </div> @@ -34,4 +36,5 @@ strip: //a[contains(@class, 'entry-section-title')] test_url: http://www.theverge.com/2012/2/29/2821763/lytro-review test_url: http://www.theverge.com/2011/11/3/2534861/nokia-lumia-800-review -test_url: http://www.theverge.com/2013/2/24/4026114/barnes-noble-shifting-focus-away-from-nook-hardware
\ No newline at end of file +test_url: http://www.theverge.com/2013/2/24/4026114/barnes-noble-shifting-focus-away-from-nook-hardware +test_url: http://www.theverge.com/rss/frontpage
\ No newline at end of file |