爬蟲之 scrapy-redis組件

時間 2019-11-17

原文原文鏈接

scrapy-redis組件

scrapy-redis是一個基於redis的scrapy組件，經過它能夠快速實現簡單分佈式爬蟲程序，該組件本質上提供了三大功能：html

scheduler - 調度器
dupefilter - URL去重規則（被調度器使用）
pipeline - 數據持久化

基於scrapy-redis的去重規則

方案

#- 徹底自定義 
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):
		"""
		檢測當前請求是否已經被訪問過
		:param request: 
		:return: True表示已經訪問過；False表示未訪問過
		"""
		fid = request_fingerprint(request)
		result = self.conn.sadd('visited_urls', fid)
		if result == 1:
			return False
		return True

#- 使用scrapy-redis 
#時間戳一直變，不方便查找

#- 繼承scrapy-redis 實現自定製 

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)

配置

定義去重規則（被調度器調用並應用）
 
    a. 內部會使用如下配置進行鏈接Redis
 
        # REDIS_HOST = 'localhost'                            # 主機名
        # REDIS_PORT = 6379                                   # 端口
        # REDIS_URL = 'redis://user:pass@hostname:9001'       # 鏈接URL（優先於以上配置）
        # REDIS_PARAMS  = {}                                  # Redis鏈接參數             默認：REDIS_PARAMS = {'socket_timeout': 30,'socket_connect_timeout': 30,'retry_on_timeout': True,'encoding': REDIS_ENCODING,}）
        # REDIS_PARAMS['redis_cls'] = 'myproject.RedisClient' # 指定鏈接Redis的Python模塊  默認：redis.StrictRedis
        # REDIS_ENCODING = "utf-8"                            # redis編碼類型             默認：'utf-8'
     
    b. 去重規則經過redis的集合完成，集合的Key爲：
     
        key = defaults.DUPEFILTER_KEY % {'timestamp': int(time.time())}
        默認配置：
            DUPEFILTER_KEY = 'dupefilter:%(timestamp)s'
              
    c. 去重規則中將url轉換成惟一標示，而後在redis中檢查是否已經在集合中存在
     
        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參數位置不一樣時，計算結果一致；
            - 默認請求頭不在計算範圍，include_headers能夠設置指定請求頭
            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"

不寫方法，直接在settings中修改配置就能夠用。　python

調度器

"""
調度器，調度器使用PriorityQueue（有序集合）、FifoQueue（列表）、LifoQueue（列表）進行保存請求，而且使用RFPDupeFilter對URL去重
     
    a. 調度器
        SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.PriorityQueue'          # 默認使用優先級隊列（默認），其餘：PriorityQueue（有序集合），FifoQueue（列表）、LifoQueue（列表）
        SCHEDULER_QUEUE_KEY = '%(spider)s:requests'                         # 調度器中請求存放在redis中的key
        SCHEDULER_SERIALIZER = "scrapy_redis.picklecompat"                  # 對保存到redis中的數據進行序列化，默認使用pickle
        SCHEDULER_PERSIST = True                                            # 是否在關閉時候保留原來的調度器和去重記錄，True=保留，False=清空
        SCHEDULER_FLUSH_ON_START = True                                     # 是否在開始以前清空 調度器和去重記錄，True=清空，False=不清空
        SCHEDULER_IDLE_BEFORE_CLOSE = 10                                    # 去調度器中獲取數據時，若是爲空，最多等待時間（最後沒數據，未獲取到）。
        SCHEDULER_DUPEFILTER_KEY = '%(spider)s:dupefilter'                  # 去重規則，在redis中保存時對應的key
        SCHEDULER_DUPEFILTER_CLASS = 'scrapy_redis.dupefilter.RFPDupeFilter'# 去重規則對應處理的類
 
 
"""
# 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redis

找到 SCHEDULER = "scrapy_redis.scheduler.Scheduler" 配置並實例化調度器對象
- 執行Scheduler.from_crawler
- 執行Scheduler.from_settings
	- 讀取配置文件：
		SCHEDULER_PERSIST			 # 是否在關閉時候保留原來的調度器和去重記錄，True=保留，False=清空
		SCHEDULER_FLUSH_ON_START     # 是否在開始以前清空 調度器和去重記錄，True=清空，False=不清空
		SCHEDULER_IDLE_BEFORE_CLOSE  # 去調度器中獲取數據時，若是爲空，最多等待時間（最後沒數據，未獲取到）。
	- 讀取配置文件：	
		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"

	- 讀取配置文件：
		REDIS_HOST = '140.143.227.206'                            # 主機名
		REDIS_PORT = 8888                                   # 端口
		REDIS_PARAMS  = {'password':'beta'}                                  # Redis鏈接參數             默認：REDIS_PARAMS = {'socket_timeout': 30,'socket_connect_timeout': 30,'retry_on_timeout': True,'encoding': REDIS_ENCODING,}）
		REDIS_ENCODING = "utf-8"      
- 示例Scheduler對象

數據持久化

定義持久化，爬蟲yield Item對象時執行RedisPipeline
     
a. 將item持久化到redis時，指定key和序列化函數
     
        REDIS_ITEMS_KEY = '%(spider)s:items'
        REDIS_ITEMS_SERIALIZER = 'json.dumps'
     
b. 使用列表保存item數據

起始URL相關

"""
起始URL相關
 
    a. 獲取起始URL時，去集合中獲取仍是去列表中獲取？True，集合；False，列表
        REDIS_START_URLS_AS_SET = False    # 獲取起始URL時，若是爲True，則使用self.server.spop；若是爲False，則使用self.server.lpop
    b. 編寫爬蟲時，起始URL從redis的Key中獲取
        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　json

- 調用 scheduler.enqueue_requests()
	def enqueue_request(self, request):
		# 請求是否須要過濾？
		# 去重規則中是否已經有？（是否已經訪問過，若是未訪問添加到去重記錄中。）
		if not request.dont_filter and self.df.request_seen(request):
			self.df.log(request, self.spider)
			# 已經訪問過就不要再訪問了
			return False
		
		if self.stats:
			self.stats.inc_value('scheduler/enqueued/redis', spider=self.spider)
		# print('未訪問過，添加到調度器', request)
		self.queue.push(request)
		return True

下載器

- 調用 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