圆月山庄资源网

python爬取本站电子书信息并入库的实现代码
脚本专栏 2024/11/3 佚名
3 2
圆月山庄资源网 Design By www.vgjia.com

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 = "//www.jb51.net/";  #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

标签：
python爬虫
圆月山庄资源网 Design By www.vgjia.com
广告合作：本站广告合作请联系QQ：858582 申请时备注：广告合作（否则不回）
免责声明：本站文章均来自网站采集或用户投稿，网站不提供任何软件下载或自行开发的软件！ 如有用户或公司发现本站内容信息存在侵权行为，请邮件告知！ 858582#qq.com
圆月山庄资源网 Design By www.vgjia.com
www.vgjia.com 圆月山庄资源网
139,976互联网资源
144,792高清电影
21,817无损音乐
631,128技术资源

《魔兽世界》大逃杀！60人新游玩模式《强袭风暴》3月21日上线

暴雪近日发布了《魔兽世界》10.2.6 更新内容，新游玩模式《强袭风暴》即将于3月21 日在亚服上线，届时玩家将前往阿拉希高地展开一场 60 人大逃杀对战。

艾泽拉斯的冒险者已经征服了艾泽拉斯的大地及遥远的彼岸。他们在对抗世界上最致命的敌人时展现出过人的手腕，并且成功阻止终结宇宙等级的威胁。当他们在为即将于《魔兽世界》资料片《地心之战》中来袭的萨拉塔斯势力做战斗准备时，他们还需要在熟悉的阿拉希高地面对一个全新的敌人──那就是彼此。在《巨龙崛起》10.2.6 更新的《强袭风暴》中，玩家将会进入一个全新的海盗主题大逃杀式限时活动，其中包含极高的风险和史诗级的奖励。

《强袭风暴》不是普通的战场，作为一个独立于主游戏之外的活动，玩家可以用大逃杀的风格来体验《魔兽世界》，不分职业、不分装备（除了你在赛局中捡到的），光是技巧和战略的强弱之分就能决定出谁才是能坚持到最后的赢家。本次活动将会开放单人和双人模式，玩家在加入海盗主题的预赛大厅区域前，可以从强袭风暴角色画面新增好友。游玩游戏将可以累计名望轨迹，《巨龙崛起》和《魔兽世界：巫妖王之怒 经典版》的玩家都可以获得奖励。

更新日志

友情链接

杰晶网络 DDR爱好者之家 桃源资源网 杰网资源 富贵资源网 南强小屋 铁雪资源网 幽灵资源网 万梅资源网 狼山资源网 白云岛资源网 昆仑资源网 相思资源网 明霞山资源网 内蒙古资源网 黑松山资源网 茶园资源网 饿虎岗资源网 大旗谷资源网 常春岛资源网 岱庙资源网 兴国资源网 快活林资源网 蝙蝠岛资源网 帝王谷资源网 白云城资源网 伏龙阁资源网 清风细雨楼 天枫庄资源网 圆月山庄资源网 无争山庄资源网 神水资源网 移花宫资源网 神剑山庄资源网 无为清净楼资源网 金钱帮资源网 丐帮资源网 华山资源网 极乐门资源网 小李飞刀资源网 凤求凰客栈 风云阁资源网 金狮镖局 鸳鸯亭资源网 千金楼资源网 更多链接