python爬取本站电子书信息并入库的实现代码

这篇文章主要介绍了python爬取本站电子书信息并入库的实现代码,需要的朋友可以参考下
入门级爬虫：只抓取书籍名称，信息及下载地址并存储到数据库

数据库工具类：DBUtil.py

import pymysql
 
class DBUtils(object):
  def connDB(self):               #连接数据库
    conn=pymysql.connect(host='192.168.251.114',port=3306, user='root',passwd='b6f3g2',db='yangsj',charset='utf8');
    cur=conn.cursor();
    return (conn,cur);
 
  def exeUpdate(self,conn,cur,sql):        #更新或插入操作
    sta=cur.execute(sql);
    conn.commit();
    return (sta);
 
  def exeDelete(self,conn,cur,IDs):        #删除操作 demo 没用到
    sta=0;
    for eachID in IDs.split(' '):
      sta+=cur.execute("delete from students where Id=%d"%(int(eachID)));
    conn.commit();
    return (sta);
 
  def exeQuery(self,cur,sql):           #查找操作
    effect_row = cur.execute(sql);
    return (effect_row,cur);
 
  def connClose(self,conn,cur):          #关闭连接，释放资源
    cur.close();
    conn.close();
 
if __name__ == '__main__':
  dbUtil = DBUtils();
  conn,cur = dbUtil.connDB();

书籍操作文件 bookOpe.py

from DBUtil import DBUtils
from bookInfo import Book
from bookInfo import DownLoadInfo
import logging
logging.basicConfig(
  level=logging.INFO
)
class BookOperator(object):
  def __addBook(self,book):
    logging.info("add book:%s" % book.bookName);
    dbUtil = DBUtils();
    conn,cur = dbUtil.connDB();
    insertBookSql = ("insert into book (bookName,bookUrl,bookInfo) values ('%s','%s','%s');"%(book.bookName,book.downLoadUrl,book.mainInfo));
    dbUtil.exeUpdate(conn,cur,insertBookSql);
    dbUtil.connClose(conn,cur);
  def __selectLastBookId(self):
    logging.info("selectLastBookId ");
    dbUtil = DBUtils();
    conn,cur = dbUtil.connDB();
    selectLastBookSql = "select id from book order by id desc limit