[github/wallabag/wallabag.git] / inc / 3rdparty / site_config / standard / schneier.com.txt

author: //p[@class='mastname']\r
\r
body: //div[@class='indivbody']\r
date: //div[@class='indivbody']/h2[1]\r
\r
# Remove blog title. Specify first occurrence in case h1 is used in article\r
strip: //div[@class='indivbody']/h1[1]\r
\r
# Remove blog description (the first p element)\r
strip: //div[@class='indivbody']/p[1]\r
\r
# Remove navigation (second p element)\r
strip: //div[@class='indivbody']/p[2]\r
\r
# Remove duplicate of article title. Specify first occurrence in case h3 is used in article\r
strip: //div[@class='indivbody']/h3[1]\r
\r
# Remove publishing date, it's extracted by rule above\r
strip: //div[@class='indivbody']/h2[1]\r
\r
# Remove duplicate of date at end, and newsletter signup\r
strip: //p[@class='posted']\r
\r
# Leave date at top\r
test_url: http://www.schneier.com/blog/archives/2010/12/security_in_202.html
Commit	Line	Data
ac4d1142 NL	1	author: //p[@class='mastname']\r
	2	\r
	3	body: //div[@class='indivbody']\r
	4	date: //div[@class='indivbody']/h2[1]\r
	5	\r
	6	# Remove blog title. Specify first occurrence in case h1 is used in article\r
	7	strip: //div[@class='indivbody']/h1[1]\r
	8	\r
	9	# Remove blog description (the first p element)\r
	10	strip: //div[@class='indivbody']/p[1]\r
	11	\r
	12	# Remove navigation (second p element)\r
	13	strip: //div[@class='indivbody']/p[2]\r
	14	\r
	15	# Remove duplicate of article title. Specify first occurrence in case h3 is used in article\r
	16	strip: //div[@class='indivbody']/h3[1]\r
	17	\r
	18	# Remove publishing date, it's extracted by rule above\r
	19	strip: //div[@class='indivbody']/h2[1]\r
	20	\r
	21	# Remove duplicate of date at end, and newsletter signup\r
	22	strip: //p[@class='posted']\r
	23	\r
	24	# Leave date at top\r
	25	test_url: http://www.schneier.com/blog/archives/2010/12/security_in_202.html