From cf276423f79f4969c69f64dc71360ad812660692 Mon Sep 17 00:00:00 2001
From: Daniil Sukhonos <olspark0310@gmail.com>
Date: Wed, 10 Oct 2018 09:05:11 +0200
Subject: [PATCH] Fix the issue with webpage parsing

Due to incorrect matching of the pattern to the list of files with PDF sets, they could not be downloaded.
With this change the downloading procedure should work
---
 bin/lhapdf-getdata | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/bin/lhapdf-getdata b/bin/lhapdf-getdata
index edd7f86..c610d1c 100755
--- a/bin/lhapdf-getdata
+++ b/bin/lhapdf-getdata
@@ -34,7 +34,7 @@ def getPDFSetList(url):
         logging.debug(pdflistpage)
         hreq.close()
         import re
-        re_anchor = re.compile(r'^\s*<tr>.*<td><a\s+href="([^"]+)">\1.*$')
+        re_anchor = re.compile(r'^.*<td\s+class="name"><a\s+href=".*/.*/([^"]+)"\s+title=.*$')
         rtn = []
         for line in pdflistpage.splitlines():
             m = re_anchor.match(line)