diff options
Diffstat (limited to 'bostonglobe.com.txt')
| -rw-r--r-- | bostonglobe.com.txt | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/bostonglobe.com.txt b/bostonglobe.com.txt new file mode 100644 index 0000000..4c74a34 --- /dev/null +++ b/bostonglobe.com.txt @@ -0,0 +1,16 @@ +# NOTE: If testing this configuration yields bad results, including junk text like "Try BostonGlobe.com today" and "THIS STORY APPEARED IN", please replace the Test URL with a current-day headline link from bostonglobe.com. + +title: //div[@class="header"]/h1 +author: substring-after(//div[@class="byline"]/h2[@class="author"],"By ") +date: //div[@class="byline"]/p[last()] +body: //div[@class="article-body"] + +strip_id_or_class: aside +strip_id_or_class: promo +strip_id_or_class: skip-nav +strip_id_or_class: article-more +strip_id_or_class: article-bar + +# This removes image captions. If the parser starts saving images from bostonglobe.com (currently, it does not), then this directive should be removed. +strip_id_or_class: figure +test_url: http://bostonglobe.com/news/nation/2012/03/17/illinois-primary-could-pivotal/PsDzFZqvhEYyXbOcF9FOkO/story.html
\ No newline at end of file |