Python+Scrapy+Crawlspider 爬取数据且存入MySQL数据库

1、Scrapy使用流程

1-1、使用Terminal终端创建工程，输入指令：scrapy startproject ProName

1-2、进入工程目录：cd ProName

1-3、创建爬虫文件（此篇介绍使用spider下的Crawlspider 派生类新建爬虫文件 ），scrapy genspider -t craw spiderFile www.xxx.com

1-4、执行工程，scrapy crawl spiderFile （待编程结束执行此命名）

需到新建工程下执行

 2、创建爬虫并编写代码

2-1、编写items.py

import scrapy

# title及状态类、时间
class MsproItem(scrapy.Item):
    # define the fields for your item here like:
    title = scrapy.Field() # 来信标题
    AcceptTime = scrapy.Field() # 受理时间
    status = scrapy.Field() # 受理状态

# 详情受理单位及内容
class DetailItem(scrapy.Item):
    detailTitle = scrapy.Field() # 详情页标题
    reviseUnit = scrapy.Field() # 受理单位
    FromTime = scrapy.Field() # 来信时间
     content = scrapy.Field() # 来信内容

2-2、编写Spider/msSpider.py

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from MSPro.items import MsproItem,DetailItem

class MsspiderSpider(CrawlSpider):
    name = 'msSpider'
    # allowed_domains = ['www.xx.com']
    start_urls = ['http://wlwz.huizhou.gov.cn/wlwzlist.shtml?method=letters4bsznList3&reload=true&pager.offset=0']

    # 链接提取器：根据指定规则(allow='正则')提取指定链接提取
    link = LinkExtractor(allow=r'&pager.offset=\d+')
    # 提取详情页的链接
    linkDetail = LinkExtractor(allow=r'&lid=\d+')

    # 规则提取器：将链接提取器提取的规则来进行callback解析操作
    rules = (
        Rule(link, callback='parse_item', follow=True),
        # follow作用：可以继续将链接提取器作用到连接提取到所对应的页面中
        Rule(linkDetail, callback='parse_detail')
    )

    # 如下两个请求方法中是不可以使用请求传参scrapy.Request
    # 如何将两个方法解析的数据存储到item中,需实现两个存储items
    # 在此方法中可以解析标题，受理状态
    def parse_item(self, response):
        # 注意：xpath中不可以存在tbody标签
        trlist = response.xpath('/html/body/table//tr/td/table//tr[2]/td/table[2]//tr')
        for tr in trlist:
            # 标题
            title = tr.xpath('./td[2]/a//text()').extract_first()
            title = "".join(title).strip()
            # 受理时间
            AcceptTime = tr.xpath('./td[4]//text()').extract_first()
            AcceptTime = "".join(AcceptTime).strip()
            # 受理状态
            status = tr.xpath('./td[5]//text()').extract_first().strip()
            # print("来信标题:", title)
            # print("受理状态：", status)
            item = MsproItem()
            item['title'] = title,
            item['AcceptTime'] = AcceptTime,
            item['status'] = status

            # 提交item到管道
            yield item

    # 此方法解析详情页的内容及受理单位
    def parse_detail(self, response):
        tbodylist = response.xpath('/html/body/table//tr[2]/td/table//tr[2]/td/table[1]')
        for tbody in tbodylist:
            # 详情页来信主题
            detailTitle = tbody.xpath('.//tr[2]/td[2]//text()').extract()
            # 字符串拼接及去掉前后空格
            detailTitle = "".join(detailTitle).strip()
            # 受理单位
            reviseUnit = tbody.xpath('.//tr[3]/td[2]//text()').extract()
            # 字符串拼接及去掉前后空格
            reviseUnit = "".join(reviseUnit).strip()
            # 来信时间
            FromTime = tbody.xpath('.//tr[3]/td[4]//text()').extract_first()
            # 字符串拼接及去掉前后空格
            FromTime = "".join(FromTime).strip()
            # 来信内容
            content = tbody.xpath('.//tr[5]/td[2]//text()').extract()
            # 字符串拼接及去掉前后空格
            content = "".join(content).strip()

            # print("受文单位:",reviseUnit)
            # print("来信内容：",content)
            item = DetailItem()
            item['detailTitle'] = detailTitle,
            item['reviseUnit'] = reviseUnit,
            item['FromTime'] = FromTime,
            item['content'] = content

            # 提交item到管道
            yield item

2-3、编写pipelines.py

import pymysql

class MsproPipeline:
    def process_item(self, item, spider):
        # 如何判断item的类型
        if item.__class__.__name__ == 'MsproItem':
            print(item['title'][0],item['AcceptTime'][0],item['status'])
        else:
            print(item['detailTitle'][0],item['FromTime'][0],item['reviseUnit'][0],item['content'])
        return item

# 数据写入到数据库中
class MysqlSpiderPipeline:

    def __init__(self):
        self.conn = None
        self.cursor = None

    def process_item(self, item, spider):
        self.conn = pymysql.Connect(host='127.0.0.1', port=3306, user='root', password="123456", db='qsbk',
                                    charset='utf8')
        self.cursor = self.conn.cursor()
        try:
            if item.__class__.__name__ == 'SunproItem':
                sql = "insert into info(Title,Status,AcceptTime) values (%s,%s,%s)"
                params = [(item['title'][0], item['status'], item['AcceptTime'][0])]
                # 执行Sql
                self.cursor.executemany(sql, params)
                # 提交事物
                self.conn.commit()
            else:
                sql = "UPDATE info Set ReviseUnit = %s,Content = %s, FromTime = %s where title = %s"
                params = [(item['reviseUnit'][0],item['content'],item['FromTime'][0],item['detailTitle'][0])]
                # 执行Sql
                self.cursor.executemany(sql,params)
                # 提交事物
                self.conn.commit()
        except Exception as msg:
            print("插入数据失败：case%s" % msg)
            self.conn.rollback()

        finally:
            return item

    def close_sipder(self, spider):
        # 关闭游标
        self.cursor.close()
        # 关闭数据库
        self.conn.close()

2-4、编写settings文件

BOT_NAME = 'MSPro'

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

# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36'

LOG_LEVEL = 'ERROR'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

#开启管道~ 写入本地或写入数据库中

ITEM_PIPELINES = {
   'MSPro.pipelines.MsproPipeline': 300,
   'MSPro.pipelines.MysqlSpiderPipeline': 301,
}

3、使用Pycharm连接MySQL数据库
3-1、连接数据库

3-2、连接数据库界面操作

4、创建爬虫项目对应表及执行爬虫工程

4-1、创建数据库表

drop table  MSBasic;

CREATE TABLE `MSBasic`
(
  `id`         int(100) NOT NULL AUTO_INCREMENT,
  `Title`      varchar(200) DEFAULT NULL,
  `Status`       varchar(100) DEFAULT NULL,
  `ReviseUnit`      varchar(200) DEFAULT NULL,
  `Content`     text(0) DEFAULT NULL,
  `FromTime`    varchar(100) DEFAULT NULL,
  `AcceptTime` varchar(100) DEFAULT NULL,
  PRIMARY KEY (`id`)
) engine = InnoDB
  default charset = utf8mb4;

4-2、执行爬虫文件

4-3、验证爬虫结果