summaryrefslogtreecommitdiff
path: root/bbc.co.uk.txt
diff options
context:
space:
mode:
Diffstat (limited to 'bbc.co.uk.txt')
-rw-r--r--bbc.co.uk.txt32
1 files changed, 32 insertions, 0 deletions
diff --git a/bbc.co.uk.txt b/bbc.co.uk.txt
new file mode 100644
index 0000000..a855ceb
--- /dev/null
+++ b/bbc.co.uk.txt
@@ -0,0 +1,32 @@
+body: //div[@class="story-body"]
+title: //h1[@class="story-header"]
+date: //span[@class="story-date"]/span[@class='date']
+
+# recipes, e.g. http://www.bbc.co.uk/food/recipes/mymincepies_71055
+body: //div[contains(@class, 'hrecipe')]//div[@id='subcolumn-1']
+
+#strip: //div[@class="story-feature narrow"]
+#strip: //div[@class="story-feature wide"]
+#strip: //div[@class="story-feature dslideshow-enclosure"]
+strip: //div[contains(@class, "story-feature")]
+strip: //span[@class="story-date"]
+#strip: //div[@class="caption body-narrow-width"]
+strip: //div[@class="warning"]//p
+strip: //div[@id='page-bookmark-links-head']
+strip: //object
+strip: //div[contains(@class, "bbccom_advert_placeholder")]
+strip: //div[contains(@class, "embedded-hyper")]
+strip: //div[contains(@class, 'market-data')]
+strip: //a[contains(@class, 'hidden')]
+strip: //div[contains(@class, 'hypertabs')]
+strip: //div[contains(@class, 'related')]
+strip: //form[@id='comment-form']
+strip: //div[contains(@class, 'comment-introduction')]
+
+replace_string(<noscript>): <div>
+replace_string(</noscript>): </div>
+
+prune: no
+
+dissolve: //h2
+test_url: http://www.bbc.co.uk/news/business-15060862 \ No newline at end of file