diff options
| -rw-r--r-- | smithsonianmag.com.txt | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/smithsonianmag.com.txt b/smithsonianmag.com.txt index 3e8fee9..fc479c2 100644 --- a/smithsonianmag.com.txt +++ b/smithsonianmag.com.txt @@ -7,6 +7,9 @@ body://div[@id = 'article-body'] # full content single_page_link://td/li[@class = 'article-singlepage']/a +# continue link +single_page_link: //a[@id='continue-btn'] + # caption clean up wrap_in(i)://span[@class='articleImageCaptionwide'] move_into (//span[@class='articleImageCaptionwide'])://div[@id = 'articleImage']/p @@ -17,4 +20,4 @@ strip://p[@id = 'articlePaginationWrapper'] strip://ul[contains(@class, 'cat-breadcrumb')] strip://div [@class= 'viewMorePhotos'] -test_url: http://www.smithsonianmag.com/history-archaeology/The-Goddess-Goes-Home.html
\ No newline at end of file +test_url: http://www.smithsonianmag.com/history-archaeology/The-Goddess-Goes-Home.html |