diff options
| -rw-r--r-- | rollingstone.com.txt | 13 |
1 files changed, 7 insertions, 6 deletions
diff --git a/rollingstone.com.txt b/rollingstone.com.txt index 9a10a69..af81515 100644 --- a/rollingstone.com.txt +++ b/rollingstone.com.txt @@ -1,10 +1,11 @@ -title: //h1 -author: //h3[@class="byline"]/strong - -body: //div[@id='main']/h2 | //div[@id='main']//div[@class='body'] +body: //div[@id='collection-items-container'] +body: //div[contains(@class, 'article-content')] prune: no -single_page_link: //a[@class='print-page'] +next_page_link: //link[@rel="next"]/@href +if_page_contains: //a[contains(@class, 'pagination-collection')] -test_url: http://www.rollingstone.com/politics/news/the-plastic-bag-wars-20110725
\ No newline at end of file +test_url: http://www.rollingstone.com/politics/news/the-plastic-bag-wars-20110725 +# mult-page article +test_url: http://www.rollingstone.com/culture/pictures/beyond-gypsy-blancharde-when-mothers-harm-their-kids-w437364 |