scrapy之持久化存储

# -*- coding: utf-8 -*-
import scrapy
from qiubai.items import QiubaiItem


class QiubaiSpiderSpider(scrapy.Spider):
    name = ‘qiubai_spider‘
    # allowed_domains = [‘www.qiushibaike.com/text‘]  # 防止爬取的内容不属于当前域名
    start_urls = [‘https://www.qiushibaike.com/text/‘]

    def parse(self, response):
        # 建议使用xpath进行指定内容的解析（框架集成了xpath解析的接口）
        # 段子的内容和作者
        div_list = response.xpath(‘//div[@id="content-left"]/div‘)
        # 存储解析到的页面数据
        for div in div_list:
            # xpath解析到的指定内容被存储到了Selector对象
            # extract()该方法可以将Selector对象中存储的数据值拿到
            # author = div.xpath(‘./div/a[2]/h2/text()‘)
            # extract_first()  ==   extract()[0]
            author = div.xpath(‘./div/a[2]/h2/text()‘).extract_first()
            content = div.xpath(‘.//div[@class="content"]/span/text()‘).extract_first()

            # 1. 创建item对象
            item = QiubaiItem()
            item[‘author‘] = author
            item[‘content‘] = content

            # 2. 提交给管道
            yield item

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

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

import scrapy


class QiubaiItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()

    # 声明属性
    author = scrapy.Field()
    content = scrapy.Field()

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

# Define your item pipelines here
#
# Don‘t forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html

import redis
import pymysql


class QiubaiPipeline(object):
    conn = None

    def open_spider(self, spider):
        print(‘redis连接开始‘)
        self.conn = redis.Redis(host=‘127.0.0.1‘, port=6379)

    # 编写向数据库中存储数据的相关代码
    def process_item(self, item, spider):
        """
        :param item: 接收到的item对象
        :param spider:
        :return:
        """
        dic = {
            ‘author‘: item[‘author‘],
            ‘content‘: item[‘content‘],
        }
        self.conn.lpush(‘data‘, dic)
        return item

    def close_spider(self, spider):
        print(‘redis链接结束‘)


class QiubaiByMysql(object):
    """
        实现将数据值存储到mysql数据库中
    """

    conn = None
    cursor = None

    # 编写向数据库中存储数据的相关代码
    def open_spider(self, spider):
        print(‘mysql链接开始‘)
        # 链接数据库
        self.conn = pymysql.Connect(host=‘127.0.0.1‘, port=3306, user=‘root‘, password=‘112233‘, db=‘qiubai‘)

    def process_item(self, item, spider):
        """
        :param item: 接收到的item对象
        :param spider:
        :return:
        """
        print(‘数据已写入mysql‘)
        # 1. 链接数据库
        # 2. 执行sql语句
        sql = f‘insert into qiubai values("{item["author"]}","{item["content"]}")‘
        self.cursor = self.conn.cursor()
        try:
            self.cursor.execute(sql)
            self.conn.commit()
        except Exception as e:
            print(e)
            self.conn.rollback()
        # 3. 提交事物
        return item

    def close_spider(self, spider):
        print(‘mysql链接结束‘)
        self.cursor.close()
        self.conn.close()


class QiubaiByFiles(object):
    """
    将数据值存储到本地磁盘中
    """
    fp = None

    def open_spider(self, spider):
        print(‘打开文件‘)
        self.fp = open(‘../qiubai.txt‘, ‘w‘, encoding=‘utf-8‘)

    def process_item(self, item, spider):
        print(‘数据已经写入到文件‘)
        author = item[‘author‘]
        content = item[‘content‘]

        self.fp.write(author + ‘:‘ + content + ‘\n\n\n‘)
        return item

    def close_spider(self, spider):
        print(‘关闭文件‘)
        self.fp.close()

BOT_NAME = ‘qiubai‘

SPIDER_MODULES = [‘qiubai.spiders‘]
NEWSPIDER_MODULE = ‘qiubai.spiders‘

USER_AGENT = ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36‘

ROBOTSTXT_OBEY = False

# 配置管道
ITEM_PIPELINES = {
    ‘qiubai.pipelines.QiubaiPipeline‘: 300,
    ‘qiubai.pipelines.QiubaiByFiles‘: 400,
    ‘qiubai.pipelines.QiubaiByMysql‘: 500,
}