Python爬虫——scrapy_读书网数据入库和链接跟进

错过人间飞鸿2023-08-23 23:02

数据入库

先创建一个数据库

mysql 复制代码

create table book(
	id int primary key auto_increment,
	name varchar(128),
	src varchar(128));

settings.py

python 复制代码

DB_HOST = '169.254.38.183'
# 端口号是一个整数
DB_PORT = 3306
DB_USER = 'root'
DB_PASSWORD = '123456'
# 数据库名称
DB_NAME = 'spider01'
DB_CHARSET = 'utf8'

# 管道
ITEM_PIPELINES = {
   "scarpy_readbook_41.pipelines.ScarpyReadbook41Pipeline": 300,
   'scarpy_readbook_41.pipelines.MysqlPipeline': 301
}

pipelines.py

python 复制代码

# 加载settings文件
from scrapy.utils.project import get_project_settings
import pymysql

class MysqlPipeline:
    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.password = settings['DB_PASSWORD']
        self.name = settings['DB_NAME']
        self.charset = settings['DB_CHARSET']

        self.coonect()

    def coonect(self):
        self.conn = pymysql.connect(host=self.host, port=self.port, user=self.user, password=self.password, 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'])
        # 执行sql语句
        self.cursor.execute(sql)
        # 提交
        self.conn.commit()

        return item

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

链接跟进：

在read.py里follow改成=True

python 复制代码

rules = (Rule(LinkExtractor(allow=r"/book/1206_\d+\.html"), callback="parse_item", follow=True),)