diff options
Diffstat (limited to 'smithsonianmag.com.txt')
| -rw-r--r-- | smithsonianmag.com.txt | 20 |
1 files changed, 20 insertions, 0 deletions
diff --git a/smithsonianmag.com.txt b/smithsonianmag.com.txt new file mode 100644 index 0000000..3e8fee9 --- /dev/null +++ b/smithsonianmag.com.txt @@ -0,0 +1,20 @@ +# meta data +title://h1[@id = 'articleTitle'] +author:substring-after(//ul[@id = 'byLine']/li[1],'By ') +date:substring-before(substring-after(//ul[@id = 'byLine']/li[last()],','),',') +body://div[@id = 'article-body'] + +# full content +single_page_link://td/li[@class = 'article-singlepage']/a + +# caption clean up +wrap_in(i)://span[@class='articleImageCaptionwide'] +move_into (//span[@class='articleImageCaptionwide'])://div[@id = 'articleImage']/p + + +# clean up +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 |