+
+
+# 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 = BytesIO()
+ 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)