Add script to update laws from RSS feed and TOC

update_laws.py

@@ -0,0 +1,94 @@
+import feedparser
+import requests
+import xml.etree.ElementTree as ET
+from urllib.parse import urlparse
+import zipfile
+import io
+import os
+from datetime import datetime, timedelta
+import difflib
+import hashlib
+
+RSS_URL = 'https://www.gesetze-im-internet.de/aktuDienst-rss-feed.xml'
+TOC_URL = 'https://www.gesetze-im-internet.de/gii-toc.xml'
+OUTPUT_DIR = 'laws'
+LAST_UPDATE_FILE = 'last_update.txt'
+
+# Letztes globales Update laden
+if os.path.exists(LAST_UPDATE_FILE):
+    with open(LAST_UPDATE_FILE, 'r') as f:
+        last_update = datetime.fromisoformat(f.read().strip())
+else:
+    last_update = datetime.now() - timedelta(days=1)
+
+feed = feedparser.parse(RSS_URL)
+new_changes = []
+
+for entry in feed.entries:
+    pub_date = datetime(*entry.published_parsed[:6])
+    if pub_date > last_update:
+        title = entry.title.strip()
+        new_changes.append((title, pub_date.strftime('%Y-%m-%d')))
+
+if not new_changes:
+    print("No new changes.")
+    exit(0)
+
+# TOC laden
+toc_response = requests.get(TOC_URL)
+toc_root = ET.fromstring(toc_response.content)
+toc_laws = {item.find('title').text.strip(): item.find('link').text.strip() for item in toc_root.findall('item')}
+
+updated = False
+for change_title, change_date in new_changes:
+    match = max(toc_laws.keys(), key=lambda t: difflib.SequenceMatcher(None, t.lower(), change_title.lower()).ratio(), default=None)
+    if match and difflib.SequenceMatcher(None, match.lower(), change_title.lower()).ratio() > 0.8:
+        link = toc_laws[match]
+        abbrev = os.path.basename(urlparse(link).path).replace('/xml.zip', '')
+        zip_url = link
+
+        zip_response = requests.get(zip_url)
+        if zip_response.status_code == 200:
+            with zipfile.ZipFile(io.BytesIO(zip_response.content)) as z:
+                xml_files = [f for f in z.namelist() if f.endswith('.xml')]
+                if xml_files:
+                    xml_content = z.read(xml_files[0])
+                    xml_root = ET.fromstring(xml_content)
+
+                    # Stand extrahieren
+                    meta = xml_root.find('.//metadaten')
+                    stand_comment = ''
+                    stand_elem = meta.find('standangabe')
+                    if stand_elem is not None:
+                        comment_elem = stand_elem.find('standkommentar')
+                        if comment_elem is not None:
+                            stand_comment = ET.tostring(comment_elem, encoding='unicode', method='text').strip()
+                    new_stand_hash = hashlib.md5(stand_comment.encode()).hexdigest()
+
+                    # Lokalen Stand checken (in last_stand.txt im law_dir)
+                    law_dir = os.path.join(OUTPUT_DIR, abbrev)
+                    os.makedirs(law_dir, exist_ok=True)
+                    stand_file = os.path.join(law_dir, 'last_stand.txt')
+                    old_stand_hash = ''
+                    if os.path.exists(stand_file):
+                        with open(stand_file, 'r') as f:
+                            old_stand_hash = f.read().strip()
+
+                    if new_stand_hash != old_stand_hash:
+                        # Datum extrahieren
+                        date_str = meta.find('ausfertigung-datum').text if meta.find('ausfertigung-datum') is not None else change_date
+
+                        file_path = os.path.join(law_dir, f"{abbrev}_{change_date}_{new_stand_hash[:8]}.xml")
+                        with open(file_path, 'wb') as f:
+                            f.write(xml_content)
+                        with open(stand_file, 'w') as f:
+                            f.write(new_stand_hash)
+                        print(f"Updated: {match} as {file_path}")
+                        updated = True
+
+# Globales Update speichern
+with open(LAST_UPDATE_FILE, 'w') as f:
+    f.write(datetime.now().isoformat())
+
+if updated:
+    print("Changes committed.")