X-Git-Url: https://git.mdrn.pl/wolnelektury.git/blobdiff_plain/111104c8e3e9487965eac9e916200a12d43bf2be..3f07d81cce72585a8ec7d4a4e062dc15d53fd931:/src/wolnelektury/utils.py

diff --git a/src/wolnelektury/utils.py b/src/wolnelektury/utils.py
index 72bc7d0c7..2657a5542 100644
--- a/src/wolnelektury/utils.py
+++ b/src/wolnelektury/utils.py
@@ -2,6 +2,9 @@
 # This file is part of Wolnelektury, licensed under GNU Affero GPLv3 or later.
 # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
 #
+import codecs
+import csv
+import cStringIO
 import json
 import os
 from functools import wraps
@@ -9,6 +12,7 @@ from functools import wraps
 import pytz
 from inspect import getargspec
 
+import re
 from django.core.mail import send_mail
 from django.http import HttpResponse
 from django.template import RequestContext
@@ -115,3 +119,50 @@ def send_noreply_mail(subject, message, recipient_list, **kwargs):
         u'[WolneLektury] ' + subject,
         message + u"\n\n-- \n" + ugettext(u'Message sent automatically. Please do not reply.'),
         'no-reply@wolnelektury.pl', recipient_list, **kwargs)
+
+
+# source: https://docs.python.org/2/library/csv.html#examples
+class UnicodeCSVWriter(object):
+    """
+    A CSV writer which will write rows to CSV file "f",
+    which is encoded in the given encoding.
+    """
+
+    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
+        # Redirect output to a queue
+        self.queue = cStringIO.StringIO()
+        self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
+        self.stream = f
+        self.encoder = codecs.getincrementalencoder(encoding)()
+
+    def writerow(self, row):
+        self.writer.writerow([s.encode("utf-8") for s in row])
+        # Fetch UTF-8 output from the queue ...
+        data = self.queue.getvalue()
+        data = data.decode("utf-8")
+        # ... and reencode it into the target encoding
+        data = self.encoder.encode(data)
+        # write to the target stream
+        self.stream.write(data)
+        # empty queue
+        self.queue.truncate(0)
+
+    def writerows(self, rows):
+        for row in rows:
+            self.writerow(row)
+
+
+# the original re.escape messes with unicode
+def re_escape(s):
+    return re.sub(r"[(){}\[\].*?|^$\\+-]", r"\\\g<0>", s)
+
+
+BOT_BITS = ['bot', 'slurp', 'spider', 'facebook', 'crawler', 'parser', 'http']
+
+
+def is_crawler(request):
+    user_agent = request.META.get('HTTP_USER_AGENT')
+    if not user_agent:
+        return True
+    user_agent = user_agent.lower()
+    return any(bot_bit in user_agent for bot_bit in BOT_BITS)