From bdf12f775062fda8aa8bf03f7b4faade4faac16d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=BAlio=20C=C3=A9sar=20Batista?= Date: Fri, 18 Jan 2019 11:38:59 -0200 Subject: [PATCH] Logging the request referer when DUPEFILTER_DEBUG is active --- scrapy/dupefilters.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/scrapy/dupefilters.py b/scrapy/dupefilters.py index 9d8966b9c..0bcdd3495 100644 --- a/scrapy/dupefilters.py +++ b/scrapy/dupefilters.py @@ -3,8 +3,7 @@ import os import logging from scrapy.utils.job import job_dir -from scrapy.utils.request import request_fingerprint - +from scrapy.utils.request import referer_str, request_fingerprint class BaseDupeFilter(object): @@ -61,8 +60,9 @@ class RFPDupeFilter(BaseDupeFilter): def log(self, request, spider): if self.debug: - msg = "Filtered duplicate request: %(request)s" - self.logger.debug(msg, {'request': request}, extra={'spider': spider}) + msg = "Filtered duplicate request: %(request)s (referer: %(referer)s)" + args = {'request': request, 'referer': referer_str(request) } + self.logger.debug(msg, args, extra={'spider': spider}) elif self.logdupes: msg = ("Filtered duplicate request: %(request)s" " - no more duplicates will be shown"