updated specific configuration for parsing

[github/wallabag/wallabag.git] / inc / 3rdparty / site_config / standard / fnal.gov.txt

diff --git a/inc/3rdparty/site_config/standard/fnal.gov.txt b/inc/3rdparty/site_config/standard/fnal.gov.txt
old mode 100644 (file)
new mode 100755 (executable)
index 7faa6bf..e404ccb
--- a/inc/3rdparty/site_config/standard/fnal.gov.txt
+++ b/inc/3rdparty/site_config/standard/fnal.gov.txt
@@ -1,15 +1,15 @@
-title: normalize(//h1)\r
-\r
-author: //td/p[position()=last()]/em\r
-\r
-# I swear, this is really the best way to do this\r
-date: normalize(//td[contains(@style, "color: #ffffff")])\r
-\r
-# my god, it's full of tables\r
-body: /table/tbody/tr[5]//table/tbody//table/tbody/tr/td\r
-strip: //h1\r
-\r
-# the following two lines strip the byline at the end of the article (the byline is a <p> that consists of an em dash and then some text in an <em>). I have no idea why I can't just strip //p[position()=last()], but trying to do so includes a bunch of other crap in the output.\r
-strip: //p[position()=last()]/em\r
+title: normalize(//h1)
+
+author: //td/p[position()=last()]/em
+
+# I swear, this is really the best way to do this
+date: normalize(//td[contains(@style, "color: #ffffff")])
+
+# my god, it's full of tables
+body: /table/tbody/tr[5]//table/tbody//table/tbody/tr/td
+strip: //h1
+
+# the following two lines strip the byline at the end of the article (the byline is a <p> that consists of an em dash and then some text in an <em>). I have no idea why I can't just strip //p[position()=last()], but trying to do so includes a bunch of other crap in the output.
+strip: //p[position()=last()]/em
 strip: //p[position()=last()]/child::text()
 test_url: http://www.fnal.gov/pub/today/archive_2011/today11-11-09_MuonDepartmentReadMore.html
\ No newline at end of file