scrapy案例实战一：jenkins在线和离线节点获取并存入数据库

自定义爬虫文件：jenkinsIP.py

# -*- coding: utf-8 -*-
import scrapy
from scrapy import selector
from bs4 import BeautifulSoup as bs
from jenkins_IP.items import JenkinsIpItem
# import sys
# reload(sys)
# sys.setdefaultencode('utf8')
import re,datetime


class JenkinsipSpider(scrapy.Spider):
    name = 'jenkinsIP'
    #allowed_domains = ['172.**.**.**:8089']  #在使用post方法时这个域名可能会导致自定义的 callback方法不执行
    #start_urls = ['http://172.**.**.**:8089/jenkins/computer/']


    def start_requests(self):
        '''post方法获取节点'''
        url="http://172.**.**.**:8089/jenkins/ajaxExecutors"
        data={}
        iphtml=scrapy.FormRequest(url=url,callback=self.parse)

        yield iphtml  #将iplist的页面回传给parse函数作为response


    def parse(self, response):
        #print response.body
        #html=bs(response.body,'lxml')
        #print html
        iplist=response.selector.xpath('//th/a["href"]')
        #iplist = response.selector.xpath('//a/@href').extract()
        lists=[]
        for it in iplist:
            href=it.xpath('@href').extract()[0]
            #print href
            lists.append(href)
        print len(iplist)
        for i in lists:
            if i == "/jenkins/computer/(master)/":
                continue

            url="http://172.**.**.**:8089"+i
            urls=response.urljoin(url)
            print("the url is :"+urls)
            ###f封装下一个爬取的url地址##
            yield  scrapy.Request(url=urls,callback=self.parse_ipreason)

    def parse_ipreason(self, response):
        '''解析具体ip地址的信息：下线原因等'''
        print ("start get ip info:")
        #print response
        item = JenkinsIpItem()
        ip= response.selector.xpath('//h1/text()').extract()[0]
        item['ip'] =re.sub('_','.',re.findall('[1-9]*_[0-9]*_[0-9]*_[0-9]*',ip)[0]).strip()
        print item['ip']
        item['type'] = response.selector.xpath('//h1/img/@src').extract()[0].strip()
        if "computer-x.png" == item['type'].split('/')[-1]:
            item['type'] = "offline"
            item['time'] =response.selector.css('div[class ="timestamp"]::text').getall()[0]  #[u'Aug 18, 2020 4:42:31 PM']
            # print  item['reason'][0].split(' ')[0:3]
            # #print datetime.datetime.strptime(item['reason'][0].split(' ')[0:3],'%b %d, %Y').strftime('%Y-%m-%d')

            item['reason'] = response.selector.css('div[class ="message"]::text').getall()[0].split(':')[1].strip()  #[u'Aug 18, 2020 4:42:31 PM']
            item['user'] = response.selector.css('div[class ="message"]::text').getall()[0].split(':')[0].strip()
        else:
            item['type']="online"
            item['reason']=" "
            item['time']=" "
            item['user']=" "
        #print  item['type']
        yield item

定义需要获取的数据：items.py

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy

'''定义需要的数据'''
class JenkinsIpItem(scrapy.Item):
    # define the fields for your item here like:
    ip = scrapy.Field()
    type=scrapy.Field()
    reason=scrapy.Field()
    time=scrapy.Field()
    user=scrapy.Field()

数据过滤：pipelines.py

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html

#######对传回来的item数据做过滤处理########
# 这里可以创建多个pipeline的类，在setting文件中配置编译顺序
#包括存储到数据库  清除空数据等
import pymysql
from scrapy.exceptions import DropItem  #扔掉item的异常
from scrapy.pipelines.images import ImagesPipeline  #继承这个类，处理图像；一般默认是继承的object类

class IsNullPipeline(object):
    def process_item(self, item, spider):
        '''必备方法'''

        if item['ip']:
            raise DropItem()  #丢弃数据
        else:
            return item  #这个item会传给下一个pipeline的类

class JenkinsIpPipeline(object):
    '''这个pipeline实现数据库数据存储'''

    def __init__(self,myhost,mydb,password,myuser,myport):
        self.db=mydb
        self.host=myhost
        self.passwd=password
        self.user=myuser
        self.port=myport
        print("#"*40)
        print self.db,self.host,self.passwd,self.port,self.user
    ####开始注入setting中配置的数据库的数据：依赖注入##
    @classmethod
    def from_crawler(cls, crawler):
        '''这里的cls是表示的当前类，cra表示获取当前的整个工程'''
        #print crawler.settings.get("HOST")
        return cls(
            myhost=crawler.settings.get("HOST"),  #将setting文件里面配置的参数回传给init方法，setting的配置必须为大写命名
            mydb=crawler.settings.get("MYDB"),
            password=crawler.settings.get("PSWD"),
            myuser=crawler.settings.get("USER"),
            myport=crawler.settings.get("PORT"),
        )


    def process_item(self, item, spider):
        '''必备方法'''
        print ("*"*10)
        sql="select * from mytable"
        self.cursor.execute(sql)

        sqls="insert into mytable(***) values(%s,%s,%s,%s,%s)" %(item['ip'],item['time'],item['type'],item['reason'],item['user'])
        self.cursor.execute(sqls)
        self.db.commit()

        return item
    def open_spider(self,spider):
        '''相当于init初始化函数 最开始调用'''
        self.db=pymysql.connect(self.host,self.db,self.user,self.passwd,charset="utf8",port=self.port)
        self.cursor=self.db.cursor()

    def close_spider(self,spider):
        '''相当于析构函数自动调用 最后执行'''
        self.db.close()
        self.cursor.close()


class imagePipeline(ImagesPipeline):
    '''这个pipeline实现图片下载'''
    def __init__(self):
        pass
    #具体方法百度

中间件处理：middlewares.py

# -*- coding: utf-8 -*-

# Define here the models for your spider middleware
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html

from scrapy import signals


class JenkinsIpSpiderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, dict or Item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Request, dict
        # or Item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)


class JenkinsIpDownloaderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the downloader middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.

        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called
        return None

    def process_response(self, request, response, spider):
        # Called with the response returned from the downloader.

        # Must either;
        # - return a Response object
        # - return a Request object
        # - or raise IgnoreRequest
        return response

    def process_exception(self, request, exception, spider):
        # Called when a download handler or a process_request()
        # (from other downloader middleware) raises an exception.

        # Must either:
        # - return None: continue processing this exception
        # - return a Response object: stops process_exception() chain
        # - return a Request object: stops process_exception() chain
        pass

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)

基础信息配置：settings.py

# -*- coding: utf-8 -*-

# Scrapy settings for jenkins_IP project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'jenkins_IP'

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

#####这里配置数据库信息，命名必须为大写####
HOST="localhost"
MYDB="mydb"
PORT="8080"
USER="root"
PSWD=""
#



# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'jenkins_IP (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False  #关闭robots协议

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
DEFAULT_REQUEST_HEADERS = {
    'Content-Type': 'text/html;charset=UTF-8',
    'Transfer-Encoding': 'chunked',
    'X-Content-Encoding-Over-Network': 'gzip',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36'
}

###定义文件存储路径##
IMAGES_STORE='./images'

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'jenkins_IP.middlewares.JenkinsIpSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
# #    'jenkins_IP.middlewares.JenkinsIpDownloaderMiddleware': 543,
# # }

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
####这里决定pipeline的执行顺序，数字大就后面执行###
ITEM_PIPELINES = {
    #'jenkins_IP.pipelines.IsNullPipeline': 300,
    'jenkins_IP.pipelines.JenkinsIpPipeline': 301,
   # 'jenkins_IP.pipelines.imagePipeline': 302,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
####同时生成文件####3
FEED_URI='./ip.cvs'
FEED_FORMAT='cvs'
FEED_EXPORT_ENCODING='ansi'

爬虫文件调用：main.py

# -*- coding: utf-8 -*-
from scrapy import  cmdline  #导入shell执行框模块
cmdline.execute(['scrapy','crawl','jenkinsIP']) #执行jenkinsip 爬虫文件

ps：这里有比较灵活的配置注入数据的方式