differentiate between abbreviations and redirects

2 files changed, 11 insertions, 0 deletions

diff --git a/scrapers/at.py b/scrapers/at.py
index bc4d874..1af9894 100755
--- a/scrapers/at.py
+++ b/scrapers/at.py
@@ -50,6 +50,16 @@ for page in pages:
         )
         if 'Abkuerzung' in info:
             data['abbr'] = info['Abkuerzung'].strip()
+            data['redir'] = data['abbr'].lower()\
+                .replace(')', '')\
+                .replace('(', '')\
+                .replace(' – ', '-')\
+                .replace(' ', '-')\
+                .replace('\xa0', '-')\
+                .replace('ä', 'ae')\
+                .replace('ü', 'ue')\
+                .replace('ö', 'oe')\
+                .replace('ß', 'ss')
         normen[info['Gesetzesnummer']] = data
 
 with open('laws/at.json', 'w') as f:
diff --git a/scrapers/de.py b/scrapers/de.py
index 7e0cd1f..9450143 100755
--- a/scrapers/de.py
+++ b/scrapers/de.py
@@ -21,6 +21,7 @@ for idx, l in enumerate(LETTERS, 1):
             title = el[1].tail.strip(),
             url = urllib.parse.urljoin(url, target),
             abbr = abbr,
+            redir = abbr,
         ))
 with open('laws/de.json', 'w') as f:
     json.dump(sorted(laws, key=lambda l: l['title']), f, indent=2, ensure_ascii=False)