数据库
首页 > 数据库> > scrapy-Redis分布式爬虫案例----阳光问政平台爬虫

scrapy-Redis分布式爬虫案例----阳光问政平台爬虫

作者:互联网

我们将之前的阳光热线问政平台爬虫案例,改写成Scrapy-redis分布式爬虫

1.items.py

import scrapy

class MyprojectItem(scrapy.Item):
    number = scrapy.Field() #帖子编号
    title = scrapy.Field() #帖子标题
    content = scrapy.Field() #帖子内容
    status = scrapy.Field() #处理状态

2.settings.py

BOT_NAME = 'myProject'

SPIDER_MODULES = ['myProject.spiders']
NEWSPIDER_MODULE = 'myProject.spiders'

ROBOTSTXT_OBEY = False
COOKIES_ENABLED = False

# 指定使用scrapy-redis的调度器
SCHEDULER = "scrapy_redis.scheduler.Scheduler"

# 指定使用scrapy-redis的去重过滤器
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"

#默认情况下,RFPDupeFilter只记录第一个重复请求。将DUPEFILTER_DEBUG设置为True会记录所有重复的请求。
DUPEFILTER_DEBUG =True

# 指定排序爬取地址时使用的队列,
# 按优先级排序(Scrapy默认),由sorted set实现的一种非FIFO、LIFO方式。
#SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.SpiderPriorityQueue'
# 可选的 按先进先出排序(FIFO)
# SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.SpiderQueue'
# 可选的 按后进先出排序(LIFO)
# SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.SpiderStack'

# 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

DOWNLOAD_DELAY = 1.0
# 支持随机下载延迟
RANDOMIZE_DOWNLOAD_DELAY = True

DOWNLOADER_MIDDLEWARES = {
   'myProject.middlewares.MyprojectDownloaderMiddleware': 543,
}

ITEM_PIPELINES = {
   # 'myProject.pipelines.MyprojectPipeline': 300,
    'scrapy_redis.pipelines.RedisPipeline': 500
}

#指定数据库连接参数,默认是本地
REDIS_HOST = 'xxx'
REDIS_PORT = 6379

USER_AGENTS = [
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
        "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",
        "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
        "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/531.21.8 (KHTML, like Gecko) Version/4.0.4 Safari/531.21.10",
        "Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/533.17.8 (KHTML, like Gecko) Version/5.0.1 Safari/533.17.8",
        "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533.19.4 (KHTML, like Gecko) Version/5.0.2 Safari/533.18.5",
        "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-GB; rv:1.9.1.17) Gecko/20110123 (like Firefox/3.x) SeaMonkey/2.0.12",
        "Mozilla/5.0 (Windows NT 5.2; rv:10.0.1) Gecko/20100101 Firefox/10.0.1 SeaMonkey/2.7.1",
        "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.8 (KHTML, like Gecko) Chrome/4.0.302.2 Safari/532.8",
        "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.464.0 Safari/534.3",
        "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_5; en-US) AppleWebKit/534.13 (KHTML, like Gecko) Chrome/9.0.597.15 Safari/534.13",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.186 Safari/535.1",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.54 Safari/535.2",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7",
        "Mozilla/5.0 (Macintosh; U; Mac OS X Mach-O; en-US; rv:2.0a) Gecko/20040614 Firefox/3.0.0 ",
        "Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.5; en-US; rv:1.9.0.3) Gecko/2008092414 Firefox/3.0.3",
        "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.5; en-US; rv:1.9.1) Gecko/20090624 Firefox/3.5",
        "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.6; en-US; rv:1.9.2.14) Gecko/20110218 AlexaToolbar/alxf-2.0 Firefox/3.6.14",
        "Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.5; en-US; rv:1.9.2.15) Gecko/20110303 Firefox/3.6.15",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1"
    ]

3.middlewares.py

import random
import json
import redis

from myProject.settings import USER_AGENTS

class MyprojectDownloaderMiddleware:
    def spider_opened(self, spider):
        self.r = redis.StrictRedis()  # 创建redis数据库连接客户端,用于取里面存储的代理Ip和port
        spider.logger.info('Spider opened: %s' % spider.name)
    
    def process_request(self, request, spider):
        #取出redis数据库中定时更新的代理ip
        proxy_list = json.loads(self.r.get('proxy_list'))
        proxy = random.choice(proxy_list)
        request.headers['User-Agent'] = random.choice(USER_AGENTS) #设置user-agent
        request.meta['proxy'] ='http://'+proxy['ip']+':'+str(proxy['port']) #设置ip代理

    return None

4.spiders/sun.py

from myProject.items import MyprojectItem
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import Rule
from scrapy_redis.spiders import RedisCrawlSpider #导入Redis爬虫基类

class SunSpider(RedisCrawlSpider):#继承Redis的爬虫基类
    name = 'sun'
    allowed_domains = ['wz.sun0769.com']
    redis_key = 'sunspider:start_urls' #增加redis_key

    rules = (
        Rule(LinkExtractor(allow=r'id=\d+&page=\d+')),#匹配每个页面
        Rule(LinkExtractor(allow=r'politics/index\?id=\d+'), callback='parse_item'),#匹配每个帖子链接
    )

    def parse_item(self, response):
        item = MyprojectItem()
        title = response.xpath('//div[@class="mr-three"]/p[@class="focus-details"]/text()').extract()[0] #投诉标题
        status = response.xpath('//div[@class="focus-date clear focus-date-list"]/span[3]/text()').extract()[0].split()[1] #处理状态
        number = response.xpath('//div[@class="focus-date clear focus-date-list"]/span[4]/text()').extract()[0].split(':')[-1] #投诉编号
        content = response.xpath('//div[@class="details-box"]/pre/text()').extract()[0] #投诉内容
        item['title'] = title
        item['status'] = status
        item['number'] = number
        item['content'] = content
        yield item
        

5.运行

标签:5.0,like,KHTML,Mozilla,Redis,爬虫,----,AppleWebKit,Gecko
来源: https://www.cnblogs.com/eliwang/p/14758164.html