summaryrefslogtreecommitdiff
path: root/webwereld.nl.txt
diff options
context:
space:
mode:
authorFiveFilters.org <fivefilters@fivefilters.org>2013-05-13 00:52:49 +0200
committerFiveFilters.org <fivefilters@fivefilters.org>2013-05-13 00:52:49 +0200
commit41e3199b3fa8e49b362de214a51fb5ec11936410 (patch)
treee2b898e88a624a749f5139ede2871223eaa4a1db /webwereld.nl.txt
parent40f2b0baa973089866d6cb83a427ec1b2139d582 (diff)
downloadftr-site-config-41e3199b3fa8e49b362de214a51fb5ec11936410.tar.gz
ftr-site-config-41e3199b3fa8e49b362de214a51fb5ec11936410.zip
Mostly Instapaper changes
Diffstat (limited to 'webwereld.nl.txt')
-rw-r--r--webwereld.nl.txt8
1 files changed, 8 insertions, 0 deletions
diff --git a/webwereld.nl.txt b/webwereld.nl.txt
new file mode 100644
index 0000000..40a5aa3
--- /dev/null
+++ b/webwereld.nl.txt
@@ -0,0 +1,8 @@
+strip: //*[@class="paginator"]
+body: //*[@id="articleText"]
+next_page_link: //a[@class="next"]
+
+# No author detection
+# No publishing date detection
+# No author and intro deduplication over multiple pages
+test_url: http://webwereld.nl/analyse/111452/de-code-van-dorifel-nader-bekeken.html \ No newline at end of file