✨ 新增基础去重；

✨ 新增状态记录
✏️ 修改错别字
⬆️ 升级依赖包
🔥 删除多余文件

README.md

@@ -5,23 +5,23 @@
 ![GitHub last commit](https://img.shields.io/github/last-commit/crawlmap/scrapy-redis-sentinel)
 ![PyPI - Downloads](https://img.shields.io/pypi/dw/scrapy-redis-sentinel)
 
-本项目基于原项目 [scrpy-redis](https://github.com/rmax/scrapy-redis)
+本项目基于原项目 [scrapy-redis](https://github.com/rmax/scrapy-redis)
 
 进行修改，修改内容如下：
 
 1. 添加了 `Redis` 哨兵连接支持
 2. 添加了 `Redis` 集群连接支持
 3. 添加了 `Bloomfilter` 去重
 
-## 安装 
+## 安装
 
 ```bash
 pip install scrapy-redis-sentinel --user
 ```
 
 ## 配置示例
 
-> 原版本 scrpy-redis 的所有配置都支持, 优先级：哨兵模式 > 集群模式 > 单机模式
+> 原版本 scrapy-redis 的所有配置都支持, 优先级：哨兵模式 > 集群模式 > 单机模式
 
 ```python
 # ----------------------------------------Bloomfilter 配置-------------------------------------
@@ -55,8 +55,8 @@ REDIS_SENTINELS = [
 ]
 
 # REDIS_SENTINEL_PARAMS 哨兵模式配置参数。
-REDIS_SENTINEL_PARAMS= {
-    "service_name":"mymaster",
+REDIS_SENTINEL_PARAMS = {
+    "service_name": "mymaster",
     "password": "password",
     "db": 0
 }
@@ -71,18 +71,23 @@ REDIS_STARTUP_NODES = [
 ]
 
 # REDIS_CLUSTER_PARAMS 集群模式配置参数
-REDIS_CLUSTER_PARAMS= {
+REDIS_CLUSTER_PARAMS = {
     "password": "password"
 }
 
 # ----------------------------------------Scrapy 其他参数-------------------------------------
 
 # 在 redis 中保持 scrapy-redis 用到的各个队列，从而允许暂停和暂停后恢复，也就是不清理 redis queues
-SCHEDULER_PERSIST = True  
+SCHEDULER_PERSIST = True
 # 调度队列  
-SCHEDULER = "scrapy_redis_sentinel.scheduler.Scheduler"  
-# 去重 
-DUPEFILTER_CLASS = "scrapy_redis_sentinel.dupefilter.RFPDupeFilter"  
+SCHEDULER = "scrapy_redis_sentinel.scheduler.Scheduler"
+# 基础去重
+DUPEFILTER_CLASS = "scrapy_redis_sentinel.dupefilter.RedisDupeFilter"
+# BloomFilter
+# DUPEFILTER_CLASS = "scrapy_redis_sentinel.dupefilter.RedisBloomFilter"
+
+# 启用基于 Redis 统计信息
+STATS_CLASS = "scrapy_redis_sentinel.stats.RedisStatsCollector"
 
 # 指定排序爬取地址时使用的队列
 # 默认的 按优先级排序( Scrapy 默认)，由 sorted set 实现的一种非 FIFO、LIFO 方式。
@@ -99,11 +104,12 @@ DUPEFILTER_CLASS = "scrapy_redis_sentinel.dupefilter.RFPDupeFilter"
 
 **修改 RedisSpider 引入方式**
 
-原版本 `scrpy-redis` 使用方式
+原版本 `scrapy-redis` 使用方式
 
 ```python
 from scrapy_redis.spiders import RedisSpider
 
+
 class Spider(RedisSpider):
     ...
 
@@ -114,6 +120,7 @@ class Spider(RedisSpider):
 ```python
 from scrapy_redis_sentinel.spiders import RedisSpider
 
+
 class Spider(RedisSpider):
     ...
 

makefile

@@ -1,7 +1,10 @@
-.PHONY: sdist upload
+.PHONY: clean sdist upload
 
 sdist:
-	 python setup.py sdist
+	python setup.py sdist bdist_wheel --universa
 
 upload:
-	twine upload dist/*
+	python setup.py upload
+
+clean:
+	rm -rf build scrapy_redis_sentinel.egg-info dist

requirements.txt

@@ -1,4 +1,3 @@
-scrapy
-redis==3.0.1
-six>=1.5.2
-redis-py-cluster==2.0.0
+redis==3.5.3
+redis-py-cluster==2.1.3
+Scrapy

scrapy_redis_sentinel/__init__.py

@@ -3,4 +3,4 @@
 __original_author__ = "Rolando Espinoza"
 __author__ = "Shi Tao"
 __email__ = "shitao0418@gmail.com"
-__version__ = "0.6.8"
+__version__ = "0.7.1"

scrapy_redis_sentinel/bloomfilter.py

@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
 class HashMap(object):
     def __init__(self, m, seed):
         self.m = m

scrapy_redis_sentinel/connection.py

@@ -1,3 +1,6 @@
+# -*- coding: utf-8 -*-
+import sys
+
 import six
 from scrapy.utils.misc import load_object
 
@@ -8,9 +11,13 @@
     "REDIS_URL": "url",
     "REDIS_HOST": "host",
     "REDIS_PORT": "port",
+    "REDIS_DB": "db",
     "REDIS_ENCODING": "encoding"
 }
 
+if sys.version_info > (3,):
+    SETTINGS_PARAMS_MAP["REDIS_DECODE_RESPONSES"] = "decode_responses"
+
 
 def get_redis_from_settings(settings):
     """Returns a redis client instance from given Scrapy settings object.

scrapy_redis_sentinel/defaults.py

@@ -1,14 +1,19 @@
+# -*- coding: utf-8 -*-
 import redis
 
-# For standalone use.
 import rediscluster
 from redis.sentinel import Sentinel
 
 DUPEFILTER_KEY = "dupefilter:%(timestamp)s"
 
 PIPELINE_KEY = "%(spider)s:items"
 
+STATS_KEY = '%(spider)s:stats'
+
 REDIS_CLS = redis.StrictRedis
+REDIS_CLUSTER_CLS = rediscluster.RedisCluster
+REDIS_SENTINEL_CLS = Sentinel
+
 REDIS_ENCODING = "utf-8"
 # Sane connection defaults.
 REDIS_PARAMS = {
@@ -21,10 +26,10 @@
 SCHEDULER_QUEUE_KEY = "%(spider)s:requests"
 SCHEDULER_QUEUE_CLASS = "scrapy_redis_sentinel.queue.PriorityQueue"
 SCHEDULER_DUPEFILTER_KEY = "%(spider)s:dupefilter"
-SCHEDULER_DUPEFILTER_CLASS = "scrapy_redis_sentinel.dupefilter.RFPDupeFilter"
+SCHEDULER_DUPEFILTER_CLASS = "scrapy_redis_sentinel.dupefilter.RedisDupeFilter"
+
+SCHEDULER_PERSIST = False
 
 START_URLS_KEY = "%(name)s:start_urls"
 START_URLS_AS_SET = False
-
-REDIS_CLUSTER_CLS = rediscluster.RedisCluster
-REDIS_SENTINEL_CLS = Sentinel
+START_URLS_AS_ZSET = False