标签：fallback 编写 command 配置文件 utils with pat 优先 comm
scrapy-redis是一个基于redis的scrapy组件，通过它可以快速实现简单分布式爬虫程序，该组件本质上提供了三大功能：
#- 完全自定义
from scrapy.dupefilter import BaseDupeFilter
import redis
from scrapy.utils.request import request_fingerprint
class DupFilter(BaseDupeFilter):
def __init__(self):
self.conn = redis.Redis(host=‘140.143.227.206‘,port=8888,password=‘beta‘)
def request_seen(self, request):
"""
检测当前请求是否已经被访问过
:param request:
:return: True表示已经访问过；False表示未访问过
"""
fid = request_fingerprint(request)
result = self.conn.sadd(‘visited_urls‘, fid)
if result == 1:
return False
return True
#- 使用scrapy-redis
#时间戳一直变，不方便查找
#- 继承scrapy-redis 实现自定制
from scrapy_redis.dupefilter import RFPDupeFilter
from scrapy_redis.connection import get_redis_from_settings
from scrapy_redis import defaults
class RedisDupeFilter(RFPDupeFilter):
@classmethod
def from_settings(cls, settings):
"""Returns an instance from given settings.
This uses by default the key ``dupefilter:<timestamp>``. When using the
``scrapy_redis.scheduler.Scheduler`` class, this method is not used as
it needs to pass the spider name in the key.
Parameters
----------
settings : scrapy.settings.Settings
Returns
-------
RFPDupeFilter
A RFPDupeFilter instance.
"""
server = get_redis_from_settings(settings)
# XXX: This creates one-time key. needed to support to use this
# class as standalone dupefilter with scrapy‘s default scheduler
# if scrapy passes spider on open() method this wouldn‘t be needed
# TODO: Use SCRAPY_JOB env as default and fallback to timestamp.
key = defaults.DUPEFILTER_KEY % {‘timestamp‘: ‘xiaodongbei‘}
debug = settings.getbool(‘DUPEFILTER_DEBUG‘)
return cls(server, key=key, debug=debug)
定义去重规则（被调度器调用并应用）
a. 内部会使用以下配置进行连接Redis
# REDIS_HOST = ‘localhost‘ # 主机名
# REDIS_PORT = 6379 # 端口
# REDIS_URL = ‘redis://user:pass@hostname:9001‘ # 连接URL（优先于以上配置）
# REDIS_PARAMS = {} # Redis连接参数 默认：REDIS_PARAMS = {‘socket_timeout‘: 30,‘socket_connect_timeout‘: 30,‘retry_on_timeout‘: True,‘encoding‘: REDIS_ENCODING,}）
# REDIS_PARAMS[‘redis_cls‘] = ‘myproject.RedisClient‘ # 指定连接Redis的Python模块 默认：redis.StrictRedis
# REDIS_ENCODING = "utf-8" # redis编码类型 默认：‘utf-8‘
b. 去重规则通过redis的集合完成，集合的Key为：
key = defaults.DUPEFILTER_KEY % {‘timestamp‘: int(time.time())}
默认配置：
DUPEFILTER_KEY = ‘dupefilter:%(timestamp)s‘
c. 去重规则中将url转换成唯一标示，然后在redis中检查是否已经在集合中存在
from scrapy.utils import request
from scrapy.http import Request
req = Request(url=‘http://www.cnblogs.com/wupeiqi.html‘)
result = request.request_fingerprint(req)
print(result) # 8ea4fd67887449313ccc12e5b6b92510cc53675c
PS:
- URL参数位置不同时，计算结果一致；
- 默认请求头不在计算范围，include_headers可以设置指定请求头
示例：
from scrapy.utils import request
from scrapy.http import Request
req = Request(url=‘http://www.baidu.com?name=8&id=1‘,callback=lambda x:print(x),cookies={‘k1‘:‘vvvvv‘})
result = request.request_fingerprint(req,include_headers=[‘cookies‘,])
print(result)
req = Request(url=‘http://www.baidu.com?id=1&name=8‘,callback=lambda x:print(x),cookies={‘k1‘:666})
result = request.request_fingerprint(req,include_headers=[‘cookies‘,])
print(result)
"""
# Ensure all spiders share same duplicates filter through redis.
# DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
不写方法，直接在settings中修改配置就可以用。
"""
调度器，调度器使用PriorityQueue（有序集合）、FifoQueue（列表）、LifoQueue（列表）进行保存请求，并且使用RFPDupeFilter对URL去重
a. 调度器
SCHEDULER_QUEUE_CLASS = ‘scrapy_redis.queue.PriorityQueue‘ # 默认使用优先级队列（默认），其他：PriorityQueue（有序集合），FifoQueue（列表）、LifoQueue（列表）
SCHEDULER_QUEUE_KEY = ‘%(spider)s:requests‘ # 调度器中请求存放在redis中的key
SCHEDULER_SERIALIZER = "scrapy_redis.picklecompat" # 对保存到redis中的数据进行序列化，默认使用pickle
SCHEDULER_PERSIST = True # 是否在关闭时候保留原来的调度器和去重记录，True=保留，False=清空
SCHEDULER_FLUSH_ON_START = True # 是否在开始之前清空 调度器和去重记录，True=清空，False=不清空
SCHEDULER_IDLE_BEFORE_CLOSE = 10 # 去调度器中获取数据时，如果为空，最多等待时间（最后没数据，未获取到）。
SCHEDULER_DUPEFILTER_KEY = ‘%(spider)s:dupefilter‘ # 去重规则，在redis中保存时对应的key
SCHEDULER_DUPEFILTER_CLASS = ‘scrapy_redis.dupefilter.RFPDupeFilter‘# 去重规则对应处理的类
"""
# Enables scheduling storing requests queue in redis.
SCHEDULER = "scrapy_redis.scheduler.Scheduler"
# Default requests serializer is pickle, but it can be changed to any module
# with loads and dumps functions. Note that pickle is not compatible between
# python versions.
# Caveat: In python 3.x, the serializer must return strings keys and support
# bytes as values. Because of this reason the json or msgpack module will not
# work by default. In python 2.x there is no such issue and you can use
# ‘json‘ or ‘msgpack‘ as serializers.
# SCHEDULER_SERIALIZER = "scrapy_redis.picklecompat"
# Don‘t cleanup redis queues, allows to pause/resume crawls.
# SCHEDULER_PERSIST = True
# Schedule requests using a priority queue. (default)
# SCHEDULER_QUEUE_CLASS = ‘scrapy_redis.queue.PriorityQueue‘
# Alternative queues.
# SCHEDULER_QUEUE_CLASS = ‘scrapy_redis.queue.FifoQueue‘
# SCHEDULER_QUEUE_CLASS = ‘scrapy_redis.queue.LifoQueue‘
# Max idle time to prevent the spider from being closed when distributed crawling.
# This only works if queue class is SpiderQueue or SpiderStack,
# and may also block the same time when your spider start at the first time (because the queue is empty).
# SCHEDULER_IDLE_BEFORE_CLOSE = 10
示例
找到 SCHEDULER = "scrapy_redis.scheduler.Scheduler" 配置并实例化调度器对象
- 执行Scheduler.from_crawler
- 执行Scheduler.from_settings
- 读取配置文件：
SCHEDULER_PERSIST # 是否在关闭时候保留原来的调度器和去重记录，True=保留，False=清空
SCHEDULER_FLUSH_ON_START # 是否在开始之前清空 调度器和去重记录，True=清空，False=不清空
SCHEDULER_IDLE_BEFORE_CLOSE # 去调度器中获取数据时，如果为空，最多等待时间（最后没数据，未获取到）。
- 读取配置文件：
SCHEDULER_QUEUE_KEY # %(spider)s:requests
SCHEDULER_QUEUE_CLASS # scrapy_redis.queue.FifoQueue
SCHEDULER_DUPEFILTER_KEY # ‘%(spider)s:dupefilter‘
DUPEFILTER_CLASS # ‘scrapy_redis.dupefilter.RFPDupeFilter‘
SCHEDULER_SERIALIZER # "scrapy_redis.picklecompat"
- 读取配置文件：
REDIS_HOST = ‘140.143.227.206‘ # 主机名
REDIS_PORT = 8888 # 端口
REDIS_PARAMS = {‘password‘:‘beta‘} # Redis连接参数 默认：REDIS_PARAMS = {‘socket_timeout‘: 30,‘socket_connect_timeout‘: 30,‘retry_on_timeout‘: True,‘encoding‘: REDIS_ENCODING,}）
REDIS_ENCODING = "utf-8"
- 示例Scheduler对象
定义持久化，爬虫yield Item对象时执行RedisPipeline
a. 将item持久化到redis时，指定key和序列化函数
REDIS_ITEMS_KEY = ‘%(spider)s:items‘
REDIS_ITEMS_SERIALIZER = ‘json.dumps‘
b. 使用列表保存item数据
"""
起始URL相关
a. 获取起始URL时，去集合中获取还是去列表中获取？True，集合；False，列表
REDIS_START_URLS_AS_SET = False # 获取起始URL时，如果为True，则使用self.server.spop；如果为False，则使用self.server.lpop
b. 编写爬虫时，起始URL从redis的Key中获取
REDIS_START_URLS_KEY = ‘%(name)s:start_urls‘
"""
# If True, it uses redis‘ ``spop`` operation. This could be useful if you
# want to avoid duplicates in your start urls list. In this cases, urls must
# be added via ``sadd`` command or you will get a type error from redis.
# REDIS_START_URLS_AS_SET = False
# Default start urls key for RedisSpider and RedisCrawlSpider.
# REDIS_START_URLS_KEY = ‘%(name)s:start_urls‘
示例
- 调用 scheduler.enqueue_requests() def enqueue_request(self, request): # 请求是否需要过滤？ # 去重规则中是否已经有？（是否已经访问过，如果未访问添加到去重记录中。） if not request.dont_filter and self.df.request_seen(request): self.df.log(request, self.spider) # 已经访问过就不要再访问了 return False if self.stats: self.stats.inc_value(‘scheduler/enqueued/redis‘, spider=self.spider) # print(‘未访问过，添加到调度器‘, request) self.queue.push(request) return True
- 调用 scheduler.next_requests() def next_request(self): block_pop_timeout = self.idle_before_close request = self.queue.pop(block_pop_timeout) if request and self.stats: self.stats.inc_value(‘scheduler/dequeued/redis‘, spider=self.spider) return request
标签：fallback 编写 command 配置文件 utils with pat 优先 comm
原文地址：https://www.cnblogs.com/gaoya666/p/9255864.html
