读书网入库练习

settings.py

DB_HOST = 'localhost'
DB_PORT = 3306
DB_USER = 'root'
DB_PWD = '1234'
DB_NAME = 'guli'
DB_CHARSET = 'utf8'
# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'readPro.pipelines.ReadproPipeline': 300,
}

　　pipelines.py

from scrapy.utils.project import get_project_settings
import pymysql

class ReadproPipeline:
    def open_spider(self, spider):
        settings = get_project_settings()
        self.host = settings['DB_HOST']


        self.port = settings['DB_PORT']
        self.user = settings['DB_USER']
        self.pwd = settings['DB_PWD']
        self.name = settings['DB_NAME']
        self.charset = settings['DB_CHARSET']
        print(self.host)
        print(self.pwd)
        self.connect()

    def connect(self):
        self.conn = pymysql.connect(host=self.host,
                                    port=self.port,
                                    user=self.user,
                                    password=self.pwd,
                                    db=self.name,
                                    charset=self.charset)

        self.cursor = self.conn.cursor()

    def process_item(self, item, spider):
        sql = 'insert into book(name,src) values("{}","{}")'.format(item['name'],item['src'])
        self.cursor.execute(sql)
        self.conn.commit()
        return item

    def close_spider(self, spider):
        self.conn.close()
        self.cursor.close()