From d9defc8b514e5f2d9c545de23054e416bd7bd2ab Mon Sep 17 00:00:00 2001
From: Arthur de Jong <arthur@arthurdejong.org>
Date: Sat, 14 Apr 2018 14:01:51 +0200
Subject: Get files ready for 1.9 release
---
update/isil.py | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
(limited to 'update/isil.py')
diff --git a/update/isil.py b/update/isil.py
index d86bdef..3ef51b6 100755
--- a/update/isil.py
+++ b/update/isil.py
@@ -32,7 +32,7 @@ import BeautifulSoup
spaces_re = re.compile(r'\s+', re.UNICODE)
# the web page that holds information on the ISIL authorities
-download_url = 'http://biblstandard.dk/isil/'
+download_url = 'https://english.slks.dk/libraries/library-standards/isil/'
def clean(s):
@@ -44,7 +44,9 @@ def parse(f):
"""Parse the specified file."""
print('# generated from ISIL Registration Authority, downloaded from')
print('# %s' % download_url)
- soup = BeautifulSoup.BeautifulSoup(f, convertEntities='html')
+ # We hack the HTML to insert missing <TR> elements
+ content = f.read().replace('</TR>', '</TR><TR>')
+ soup = BeautifulSoup.BeautifulSoup(content, convertEntities='html')
# find all table rows
for tr in soup.findAll('tr'):
# find the rows with four columns of text
--
cgit v1.2.3