scrapy-redis分布式爬虫

#使用scrapy-redis里的去重组件，不使用scrapy默认的去重方式
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"

#使用scrapy-redis里的调度器组件，不使用默认的
SCHEDULER = "scrapy_redis.scheduler.Scheduler"

#允许暂停，redis请求记录不丢失
SCHEDULER_PERSIST = True

#默认的scrapy-redis请求队列形式（按优先级）
SCHEDULER_QUEUE_CLASS = "scrapy_redis.queue.SpiderPriorityQueue"

#队列形式，先进先出
SCHEDULER_QUEUE_CLASS = "scrapy_redis.queue.SpiderQueue"

#栈形式，请求先进后出
SCHEDULER_QUEUE_CLASS = "scrapy_redis.queue.SpiderStack"

#只是将数据放到redis数据库，不需要写pipeline，存储到mysql还是需要写的
ITEM_PIPELINES = {
    ‘scrapy_redis.pipelines.RedisPipeline‘:400
}




#链接redis数据库

REDIS_URL = ‘redis://:@127.0.0.1:6379‘

scrapy runspider myspider.py
#后面的py文件是你需要运行的分布式爬虫的文件名

myspider:request

myspider:dupefilter

#如果打开item管道存储在redis的数据的话，就还有这这么一个字段
myspider:item

#在redis中删除所有的键命令为：flushdb
#查看所有键：keys *

import scrapy
from scrapy.selector import Selector
from Scrapy_Redist.items import ScrapyRedistItem
from scrapy_redis.spiders import RedisCrawlSpider
from scrapy.linkextractor import LinkExtractor
from scrapy.spiders import CrawlSpider,Rule

class MybaidukeSpider(RedisCrawlSpider):                  ##基于RedisCrawlSpider
    name = ‘mybaike‘
    alloweb_domains = [‘baike.baidu.com‘]
    # start_urls = [‘https://baike.baidu.com/item/Python/407313‘]
    redis_key = ‘mybaike:start_url‘
    rules = [Rule(LinkExtractor(allow=("item/(.*)")),callback="get_parse",follow=True)]
    def get_parse(self,response):
        items = ScrapyRedistItem()

        Seit = Selector(response)
        title = Seit.xpath(‘//dd[@class="lemmaWgt-lemmaTitle-title"]/h1/text()‘).extract()
        contentList = Seit.xpath(‘//div[@class="lemma-summary"]//text()‘)
        content = ‘‘
        for c in contentList:
            content += c.extract().strip()

        items[‘title‘] = title
        items[‘content‘] = content
        yield items

import scrapy
from scrapy.selector import Selector
from Scrapy_Redist.items import ScrapyRedistItem

from scrapy_redis.spiders import RedisSpider

class MybaidukeSpider(RedisSpider):
    name = ‘mybaike‘
    alloweb_domains = [‘baike.baidu.com‘]
    # start_urls = [‘https://baike.baidu.com/item/Python/407313‘]

    redis_key = ‘mybaike:start_url‘
　　#这句话很重要哦，也就是写在redis中键


    #rules = [Rule(LinkExtractor(allow=("item/(.*)")),callback="get_parse",follow=True)]# 如果自己写一个翻页的花就继承于 RedisSpider


    def get_parse(self,response):
        items = ScrapyRedistItem()

        Seit = Selector(response)
        title = Seit.xpath(‘//dd[@class="lemmaWgt-lemmaTitle-title"]/h1/text()‘).extract()
        contentList = Seit.xpath(‘//div[@class="lemma-summary"]//text()‘)
        content = ‘‘
        for c in contentList:
            content += c.extract().strip()

        items[‘title‘] = title
        items[‘content‘] = content
        yield items