neue Verzeichnissstruktur

content/management/commands/importarticles.py

@@ -0,0 +1,73 @@
+# -*- coding: utf-8 -*-
+
+from content.models import Article, Category
+from django.contrib.auth.models import User
+from django.core.management.base import BaseCommand
+from django.template.defaultfilters import slugify
+from django.utils.datetime_safe import datetime
+import re
+import xlrd #@UnresolvedImport
+
+class Command(BaseCommand):
+    help = "Importiert die alten Daten aus einer CSV Datei" #@ReservedAssignment
+    date_header_regex = r"""<h1><span class=\"small\">(?P<date>[\d\.]*)[\ -]*</span>[\ -]*(?P<title>.*)</h1>(?P<content>.*)"""
+    header_regex = r"""<h1>[\ -]*(?P<title>.*)</h1>(?P<content>.*)"""
+
+    def __init__(self):
+        self.author = User.objects.get(username="xeniac")
+        self.category = Category.objects.get(slug='allgemeines')
+        
+    def create_article(self):
+        self.slug = slugify(self.headline[:50])
+        article, created = Article.objects.get_or_create(slug=self.slug, date_created=self.date_created, 
+            defaults={
+            'author': self.author,
+            'headline_de': self.headline,
+            'content_de':  self.content,
+            'category': self.category       
+        })
+        if created:
+            print "Created: %s - %s" % (self.date_created, self.headline)            
+            article.clean()
+            article.save()
+        
+    def parse_with_date(self, original):
+        match_obj = re.search(self.date_header_regex, original, re.IGNORECASE | re.DOTALL)
+        if match_obj:
+            self.date_created = datetime.strptime(match_obj.group('date'), '%d.%m.%Y')
+            self.headline = match_obj.group('title').strip()
+            self.content = match_obj.group('content').strip()
+            return True
+        else:
+            return False
+
+    def parse_without_date(self, original):
+        match_obj = re.search(self.header_regex, original, re.IGNORECASE | re.DOTALL)
+        if match_obj:
+            self.date_created = datetime.strptime('01.01.1982', '%d.%m.%Y')
+            self.headline = match_obj.group('title').strip()
+            self.content = match_obj.group('content').strip()
+            return True
+        else:
+            return False
+
+    def handle(self, *args, **options):
+        try:
+            xls_file = xlrd.open_workbook(args[0])
+        except IndexError:
+            print "Bitte den Pfad zur CSV Datei angeben!"
+            return False
+        except IOError:
+            print "Datei '%s' wurde nicht gefunden! " % args[0]
+            return False
+        
+        table = xls_file.sheet_by_index(0)
+        for row in xrange(1, table.nrows):
+            if not table.cell_value(row, 2) in ('Archiv', 'News'):
+                continue
+            original = table.cell_value(row, 3)
+            if self.parse_with_date(original) or self.parse_without_date(original):
+                self.create_article()
+            else:
+                print "Fehler bei String!"
+                print table.cell_value(row, 3)