python爬取本站电子书信息并入库的实现代码


Posted in Python onJanuary 20, 2020

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 1";
    effect_row,cur = dbUtil.exeQuery(cur,selectLastBookSql);
    bookId = cur.fetchone()[0];
    dbUtil.connClose(conn,cur);
    return bookId;
  def __addBookDownLoadInfos(self,downLoadInfos,bookId):
    logging.info("add bookId:%s" % bookId);
    dbUtil = DBUtils();
    conn,cur = dbUtil.connDB();
    for downLoadinfo in downLoadInfos:
      insertBookDownLoadInfo = ("insert into book_down_url (bookId,downName,downUrl) values ('%s','%s','%s');"%(bookId,downLoadinfo.downName,downLoadinfo.downUrl));
      dbUtil.exeUpdate(conn,cur,insertBookDownLoadInfo);
    dbUtil.connClose(conn,cur);
  def addBookInfo(self,book):
    logging.info("add bookInfo:%s" % book.bookName);
    self.__addBook(book);
    bookId = self.__selectLastBookId();
    self.__addBookDownLoadInfos(book.downLoadInfos,bookId);
if __name__ == '__main__':
  bookope = BookOperator();
  book = Book("aaa","yang","cccc");
  book.addDownLoadUrl(DownLoadInfo("aaa.html","书籍"));
  bookope.addBookInfo(book);

书籍信息文件 bookInfo.py

import sys
sys.encoding = "utf8"
class Book(object):
  #书籍信息#
  def __init__(self,mainInfo,downLoadUrl,bookName):
    self.mainInfo = mainInfo;
    self.downLoadUrl = downLoadUrl;
    self.bookName = bookName;
    self.downLoadInfos = [];
  def addDownLoadUrl(self,downloadInfo):
    self.downLoadInfos.append(downloadInfo);
  def print_book_info(self):
    print ("bookName :%s" % (self.bookName));
class DownLoadInfo(object):
  #下载信息#
  def __init__(self,downUrl,downName):
    self.downUrl = downUrl;
    self.downName = downName;
  def print_down_info(self):
    print ("downLoad %s - %s" % (self.downUrl,self.downName));

51job界面解析文件 FiveOneJobFetch.py

import requests
from bs4 import BeautifulSoup
import sys
from bookInfo import Book
from bookInfo import DownLoadInfo
import logging
sys.encoding = "utf8"
class PageFetch(object):
  host = "//3water.com/";  #域名+分类
  category = "books/"; #具体请求页
  def __init__(self,pageUrl):
    self.pageUrl = pageUrl; #完整URL
    self.url = PageFetch.host+PageFetch.category + pageUrl;
  def __getPageContent(self):
    req = requests.get(self.url);
    if req.status_code == 200:
      req.encoding = "gb2312";
      strText = req.text;
      return strText;
    else:
      return "";
  def getPageContent(url):
    req = requests.get(url);
    if req.status_code == 200:
      req.encoding = "gb2312";
      strText = req.text;
      return strText;
    else:
      return "";
  def __getMaxPageNumAndUrl(self):
    fetchUrl = self.pageUrl;
    #获取分页地址 分页url 形如 list45_2.html 2为页号#
    maxPageNum = 0;
    maxLink = "";
    while maxLink == "":
      url = PageFetch.host+PageFetch.category +fetchUrl;
      reqContent = PageFetch.getPageContent(url)
      soup = BeautifulSoup (reqContent,"html.parser");
      for ul in soup.select(".plist"):
        print ("数据");
        print (ul);
        maxPageNum = ul.select("strong")[0].text;
        alink = ul.select("a");
        if alink[-1]['href'] == "#":
          maxLink = alink[1]['href'];
        else:
          fetchUrl = alink[-1]['href'];
    return maxPageNum,maxLink;
  def __formatPage(self,pageNum):
    #格式化url 形如 list45_2.html#
    lineBeginSite = self.pageUrl.index("_")+1;
    docBeginSite = self.pageUrl.index(".");
    return self.pageUrl[:lineBeginSite]+str(pageNum+1)+self.pageUrl[docBeginSite:];
  def getBookPageList(self):
    #获取书籍每页的URL#
    shortPageList = [];
    maxPageNum,urlPattern = self.__getMaxPageNumAndUrl();
    for i in range(int(maxPageNum)):
      shortPageList.append(self.host +self.category+ self.__formatPage(i));
    return shortPageList;
  def getDownloadPage(url):
    downPage= [];
    reqContent = PageFetch.getPageContent(url);
    soup = BeautifulSoup (reqContent,"html.parser");
    for a in soup.select(".cur-cat-list .btn-dl"):
      downPage.append(PageFetch.host+a['href']);
    return downPage;
  def getBookInfo(url):
    logging.info("获取书籍信息url:%s" % url);
    reqContent = PageFetch.getPageContent(url);
    soup = BeautifulSoup (reqContent,"html.parser");
    mainInfo = (soup.select("#soft-intro"))[0].text.replace("截图:","").replace("'","");
    title = (soup.select("dl dt h1"))[0].text.replace("'","");
    book = Book(mainInfo,url,title);
    for ul in soup.select(".ul_Address"):
      for li in ul.select("li"):
        downLoadInfo = DownLoadInfo(li.select("a")[0]['href'],li.select("a")[0].text);
        book.addDownLoadUrl(downLoadInfo);
    return book;
if __name__ == '__main__':
  p = PageFetch("list152_1.html");
  shortPageList = p.getBookPageList();
  downPage= [];
  for page in shortPageList:
    downLoadPage = PageFetch.getDownloadPage(page);
    downPage = downPage+downLoadPage;
  print ("================汇总如下===============================");
  for bookDownLoadPage in downPage:
    book = PageFetch.getBookInfo(bookDownLoadPage);
    print (book.bookName+":%s" % book.downLoadUrl);
    for d in book.downLoadInfos:
      print ("%s - %s" % (d.downUrl,d.downName));
  # p = PageFetch("list977_1.html");
  # p = p.getMaxPageNumAndUrl();
  # print (p);

执行文件,以上文件copy在相同的文件夹下 执行此文件即可 51Job.py

from FiveOneJobFetch import PageFetch
from bookInfo import Book
from bookInfo import DownLoadInfo
from bookOpe import BookOperator

def main(url):
  p = PageFetch(url);
  shortPageList = p.getBookPageList();
  bookOperator = BookOperator();
  downPage= [];
  for page in shortPageList:
    downLoadPage = PageFetch.getDownloadPage(page);
    downPage = downPage+downLoadPage;
  for bookDownLoadPage in downPage:
    book = PageFetch.getBookInfo(bookDownLoadPage);
    bookOperator.addBookInfo(book);
  print ("数据抓取成功:"+url);

if __name__ == '__main__':
  urls = ["list152_35.html","list300_2.html","list476_6.html","list977_2.html","list572_5.html","list509_2.html","list481_1.html","list576_1.html","list482_1.html","list483_1.html","list484_1.html"];
  for url in urls:
    main(url);

数据库表:书籍信息表和下载地址表

CREATE TABLE `book` (
`id` INT(11) NOT NULL AUTO_INCREMENT,
`bookName` VARCHAR(200) NULL DEFAULT NULL,
`bookUrl` VARCHAR(500) NULL DEFAULT NULL,
`bookInfo` TEXT NULL,
PRIMARY KEY (`id`)
)
COLLATE='utf8mb4_general_ci'
ENGINE=InnoDB
AUTO_INCREMENT=2936;
CREATE TABLE `book_down_url` (
`id` INT(11) NOT NULL AUTO_INCREMENT,
`bookId` INT(11) NOT NULL DEFAULT '0',
`downName` VARCHAR(200) NOT NULL DEFAULT '0',
`downUrl` VARCHAR(2000) NOT NULL DEFAULT '0',
PRIMARY KEY (`id`)
)
COLLATE='utf8mb4_general_ci'
ENGINE=InnoDB
AUTO_INCREMENT=44441;

git地址:https://git.oschina.net/yangsj/BookFetch/tree/master

Python 相关文章推荐
Python信息抽取之乱码解决办法
Jun 29 Python
解决Django模板无法使用perms变量问题的方法
Sep 10 Python
Python数据可视化正态分布简单分析及实现代码
Dec 04 Python
python+opencv轮廓检测代码解析
Jan 05 Python
Centos 升级到python3后pip 无法使用的解决方法
Jun 12 Python
Python设计模式之解释器模式原理与用法实例分析
Jan 10 Python
Python socket非阻塞模块应用示例
Sep 12 Python
Django静态资源部署404问题解决方案
May 11 Python
python des,aes,rsa加解密的实现
Jan 16 Python
PyTorch 实现L2正则化以及Dropout的操作
May 27 Python
Python基础学习之奇异的GUI对话框
May 27 Python
Python中的 Set 与 dict
Mar 13 Python
浅谈Tensorflow 动态双向RNN的输出问题
Jan 20 #Python
关于tf.nn.dynamic_rnn返回值详解
Jan 20 #Python
双向RNN:bidirectional_dynamic_rnn()函数的使用详解
Jan 20 #Python
关于tf.reverse_sequence()简述
Jan 20 #Python
tensorflow使用range_input_producer多线程读取数据实例
Jan 20 #Python
浅谈tensorflow中Dataset图片的批量读取及维度的操作详解
Jan 20 #Python
使用tensorflow DataSet实现高效加载变长文本输入
Jan 20 #Python
You might like
php自动加载autoload机制示例分享
2014/02/20 PHP
PHP5全版本绕过open_basedir读文件脚本漏洞详细介绍
2015/01/20 PHP
PHP7扩展开发之hello word实现方法详解
2018/01/15 PHP
php nginx 实时输出的简单实现方法
2018/01/21 PHP
js获取单选按钮的数据
2006/11/27 Javascript
深入理解JavaScript系列(6) 强大的原型和原型链
2012/01/15 Javascript
中国地区三级联动下拉菜单效果分析
2012/11/15 Javascript
javascript无刷新评论实现方法
2015/05/13 Javascript
基于jquery实现鼠标左右拖动滑块滑动附源码下载
2015/12/23 Javascript
js+css实现select的美化效果
2016/03/24 Javascript
解决Window10系统下Node安装报错的问题分析
2016/12/13 Javascript
Jquery树插件zTree实现菜单树
2017/01/24 Javascript
JavaScript登录验证基础教程
2017/11/01 Javascript
详解vue通过NGINX部署在子目录或者二级目录实践
2018/09/03 Javascript
Vue项目pdf(base64)转图片遇到的问题及解决方法
2018/10/19 Javascript
详解vue路由篇(动态路由、路由嵌套)
2019/01/27 Javascript
微信小程序学习笔记之跳转页面、传递参数获得数据操作图文详解
2019/03/28 Javascript
Element InputNumber 计数器的实现示例
2020/08/03 Javascript
selenium 反爬虫之跳过淘宝滑块验证功能的实现代码
2020/08/27 Javascript
[55:45]LGD vs OG 2019国际邀请赛淘汰赛 胜者组 BO3 第三场 8.24
2019/09/10 DOTA
django admin 后台实现三级联动的示例代码
2018/06/22 Python
Python队列、进程间通信、线程案例
2019/10/25 Python
Series和DataFrame使用简单入门
2019/11/13 Python
Python unittest工作原理和使用过程解析
2020/02/24 Python
基于python实现地址和经纬度转换
2020/05/19 Python
The North Face北面荷兰官网:美国著名户外品牌
2019/10/16 全球购物
中学教师师德承诺书
2014/05/23 职场文书
班级读书活动总结
2014/06/30 职场文书
2014年感恩节活动策划方案
2014/10/06 职场文书
新郎婚礼答谢词
2015/01/04 职场文书
追悼会答谢词范文
2015/09/29 职场文书
医务人员医德医风心得体会
2016/01/25 职场文书
《生物入侵者》教学反思
2016/02/16 职场文书
详解Java实现数据结构之并查集
2021/06/23 Java/Android
关于python中模块和重载的问题
2021/11/02 Python
使用HBuilder制作一个简单的HTML5网页
2022/07/07 HTML / CSS