Python爬取当当、京东、亚马逊图书信息代码实例

yipeiwu_com7年前Python爬虫

注:1.本程序采用MSSQLserver数据库存储,请运行程序前手动修改程序开头处的数据库链接信息

2.需要bs4、requests、pymssql库支持

3.支持多线程

from bs4 import BeautifulSoup 
import re,requests,pymysql,threading,os,traceback 
 
try: 
  conn = pymysql.connect(host='127.0.0.1', port=3306, user='root', passwd='root', db='book',charset="utf8") 
  cursor = conn.cursor() 
except: 
  print('\n错误:数据库连接失败') 
 
#返回指定页面的html信息 
def getHTMLText(url): 
  try: 
    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'} 
    r = requests.get(url,headers = headers) 
    r.raise_for_status() 
    r.encoding = r.apparent_encoding 
    return r.text 
  except: 
    return '' 
#返回指定url的Soup对象 
def getSoupObject(url): 
  try: 
    html = getHTMLText(url) 
    soup = BeautifulSoup(html,'html.parser') 
    return soup 
  except: 
    return '' 
#获取该关键字在图书网站上的总页数 
def getPageLength(webSiteName,url): 
  try: 
    soup = getSoupObject(url) 
    if webSiteName == 'DangDang': 
      a = soup('a',{'name':'bottom-page-turn'}) 
      return a[-1].string 
    elif webSiteName == 'Amazon': 
      a = soup('span',{'class':'pagnDisabled'}) 
      return a[-1].string 
  except: 
    print('\n错误:获取{}总页数时出错...'.format(webSiteName)) 
    return -1 
 
class DangDangThread(threading.Thread): 
  def __init__(self,keyword): 
    threading.Thread.__init__(self) 
    self.keyword = keyword 
  def run(self): 
    print('\n提示:开始爬取当当网数据...') 
    count = 1 
   
    length = getPageLength('DangDang','http://search.dangdang.com/?key={}'.format(self.keyword))#总页数 
    tableName = 'db_{}_dangdang'.format(self.keyword) 
 
    try: 
      print('\n提示:正在创建DangDang表...') 
      cursor.execute('create table {} (id int ,title text,prNow text,prPre text,link text)'.format(tableName)) 
      print('\n提示:开始爬取当当网页面...') 
      for i in range(1,int(length)): 
        url = 'http://search.dangdang.com/?key={}&page_index={}'.format(self.keyword,i) 
        soup = getSoupObject(url) 
        lis = soup('li',{'class':re.compile(r'line'),'id':re.compile(r'p')}) 
        for li in lis: 
          a = li.find_all('a',{'name':'itemlist-title','dd_name':'单品标题'}) 
          pn = li.find_all('span',{'class': 'search_now_price'}) 
          pp = li.find_all('span',{'class': 'search_pre_price'}) 
 
          if not len(a) == 0: 
            link = a[0].attrs['href'] 
            title = a[0].attrs['title'].strip() 
          else: 
            link = 'NULL' 
            title = 'NULL' 
 
          if not len(pn) == 0: 
            prNow = pn[0].string 
          else: 
            prNow = 'NULL' 
 
          if not len(pp) == 0: 
            prPre = pp[0].string 
          else: 
            prPre = 'NULL' 
          sql = "insert into {} (id,title,prNow,prPre,link) values ({},'{}','{}','{}','{}')".format(tableName,count,title,prNow,prPre,link) 
          cursor.execute(sql) 
          print('\r提示:正在存入当当数据,当前处理id:{}'.format(count),end='') 
          count += 1 
          conn.commit() 
    except: 
      pass 

class AmazonThread(threading.Thread): 
  def __init__(self,keyword): 
    threading.Thread.__init__(self) 
    self.keyword = keyword 
 
  def run(self): 
    print('\n提示:开始爬取亚马逊数据...') 
    count = 1 
    length = getPageLength('Amazon','https://www.amazon.cn/s/keywords={}'.format(self.keyword))#总页数 
    tableName = 'db_{}_amazon'.format(self.keyword) 
     
    try: 
      print('\n提示:正在创建Amazon表...') 
      cursor.execute('create table {} (id int ,title text,prNow text,link text)'.format(tableName)) 
   
      print('\n提示:开始爬取亚马逊页面...') 
      for i in range(1,int(length)): 
        url = 'https://www.amazon.cn/s/keywords={}&page={}'.format(self.keyword,i) 
        soup = getSoupObject(url) 
        lis = soup('li',{'id':re.compile(r'result_')}) 
        for li in lis: 
          a = li.find_all('a',{'class':'a-link-normal s-access-detail-page a-text-normal'}) 
          pn = li.find_all('span',{'class': 'a-size-base a-color-price s-price a-text-bold'}) 
          if not len(a) == 0: 
            link = a[0].attrs['href'] 
            title = a[0].attrs['title'].strip() 
          else: 
            link = 'NULL' 
            title = 'NULL' 
 
          if not len(pn) == 0: 
            prNow = pn[0].string 
          else: 
            prNow = 'NULL' 
 
          sql = "insert into {} (id,title,prNow,link) values ({},'{}','{}','{}')".format(tableName,count,title,prNow,link) 
          cursor.execute(sql) 
          print('\r提示:正在存入亚马逊数据,当前处理id:{}'.format(count),end='') 
          count += 1 
          conn.commit() 
    except: 
      pass 

class JDThread(threading.Thread): 
  def __init__(self,keyword): 
    threading.Thread.__init__(self) 
    self.keyword = keyword 
  def run(self): 
    print('\n提示:开始爬取京东数据...') 
    count = 1 
 
    tableName = 'db_{}_jd'.format(self.keyword) 
     
    try: 
      print('\n提示:正在创建JD表...') 
      cursor.execute('create table {} (id int,title text,prNow text,link text)'.format(tableName)) 
      print('\n提示:开始爬取京东页面...') 
      for i in range(1,100): 
        url = 'https://search.jd.com/Search?keyword={}&page={}'.format(self.keyword,i) 
        soup = getSoupObject(url) 
        lis = soup('li',{'class':'gl-item'}) 
        for li in lis: 
          a = li.find_all('div',{'class':'p-name'}) 
          pn = li.find_all('div',{'class': 'p-price'})[0].find_all('i') 
 
          if not len(a) == 0: 
            link = 'http:' + a[0].find_all('a')[0].attrs['href'] 
            title = a[0].find_all('em')[0].get_text() 
          else: 
            link = 'NULL' 
            title = 'NULL' 
           
          if(len(link) > 128): 
            link = 'TooLong' 
 
          if not len(pn) == 0: 
            prNow = '¥'+ pn[0].string 
          else: 
            prNow = 'NULL' 
          sql = "insert into {} (id,title,prNow,link) values ({},'{}','{}','{}')".format(tableName,count,title,prNow,link) 
          cursor.execute(sql) 
          print('\r提示:正在存入京东网数据,当前处理id:{}'.format(count),end='') 
          count += 1 
          conn.commit() 
    except : 
      pass 
def closeDB(): 
  global conn,cursor 
  conn.close() 
  cursor.close() 
 
def main(): 
  print('提示:使用本程序,请手动创建空数据库:Book,并修改本程序开头的数据库连接语句') 
  keyword = input("\n提示:请输入要爬取的关键字:") 
 
  dangdangThread = DangDangThread(keyword) 
  amazonThread = AmazonThread(keyword) 
  jdThread = JDThread(keyword) 
   dangdangThread.start() 
  amazonThread.start() 
  jdThread.start() 
  dangdangThread.join() 
  amazonThread.join() 
  jdThread.join() 
   closeDB() 
   print('\n爬取已经结束,即将关闭....') 
  os.system('pause') 
   
main() 

示例截图:

关键词:Android下的部分运行结果(以导出至Excel)

总结

以上就是本文关于Python爬取当当、京东、亚马逊图书信息代码实例的全部内容,希望对大家有所帮助。感兴趣的朋友可以继续参阅本站:

python爬取亚马逊书籍信息代码分享

Python爬虫实例爬取网站搞笑段子

Python探索之爬取电商售卖信息代码示例

如有不足之处,欢迎留言指出。感谢朋友们对本站的支持!

相关文章

python编写网页爬虫脚本并实现APScheduler调度

前段时间自学了python,作为新手就想着自己写个东西能练习一下,了解到python编写爬虫脚本非常方便,且最近又学习了MongoDB相关的知识,万事具备只欠东风。 程序的需求是这样的,...

python爬取指定微信公众号文章

本文实例为大家分享了python爬取微信公众号文章的具体代码,供大家参考,具体内容如下 该方法是依赖于urllib2库来完成的,首先你需要安装好你的python环境,然后安装urllib...

python打造爬虫代理池过程解析

最近在使用爬虫爬取数据时,经常会返回403代码,大致意思是该IP访问过于频繁,被限制访问。限制IP访问网站最常用的反爬手段了,其实破解也很容易,就是在爬取网站是使用代理即可,这个IP被限...

Python爬虫:通过关键字爬取百度图片

Python爬虫:通过关键字爬取百度图片

使用工具:Python2.7 点我下载 scrapy框架 sublime text3 一。搭建python(Windows版本)  1.安装python2.7 ---然后在cm...

python爬虫神器Pyppeteer入门及使用

python爬虫神器Pyppeteer入门及使用

前言 提起selenium想必大家都不陌生,作为一款知名的Web自动化测试框架,selenium支持多款主流浏览器,提供了功能丰富的API接口,经常被我们用作爬虫工具来使用。但是sele...