网络爬出五个小实例

实例一

爬取京东商品信息

  
  

    
    

     
     

    
    
    
    

     
     

      
      import requests
     
     
    
    

    
    

     
     

    
    
    
    

     
     

      
      url=
      
      "https://item.jd.com/6946605.html"
     
     
    
    

    
    

     
     

    
    
    
    

     
     

      
      try:
     
     
    
    

    
    

     
     

    
    
    
    

     
     

      
          r=requests.get(url)
     
     
    
    

    
    

     
     

    
    
    
    

     
     

      
          r.raise_for_status()
     
     
    
    

    
    

     
     

    
    
    
    

     
     

      
          r.encoding=r.apparent_encoding
     
     
    
    

    
    

     
     

    
    
    
    

     
     

      
          print(r.text[:
      
      1000])
     
     
    
    

    
    

     
     

    
    
    
    

     
     

      
      except:
     
     
    
    

    
    

     
     

    
    
    
    

     
     

      
          print(
      
      "爬取失败")
     
     
    
    
  
  

---

实例二

爬取亚马逊商品信息

 
 

   
   

    
    

   
   
   
   

    
    

     
     import requests
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
     url=
     
     "https://www.amazon.cn/gp/product/B07D51Y714"
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
     try:
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         kv={
     
     'user-agent':
     
     'Mozailla/5.0'}
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         r=requests.get(url,headers=kv)
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         r.raise_for_status()
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         r.encoding=r.apparent_encoding
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         print(r.text[
     
     1000:
     
     2000])
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
     except:
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         print(
     
     "爬取失败")
    
    
   
   
 
 

---

实例三

百度搜索

 
 

   
   

    
    

   
   
   
   

    
    

     
     import requests
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
     keyword=
     
     "Python"
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
     try:
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         kv={
     
     'wd':keyword}
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         r=requests.get(
     
     "http://www.baidu.com/s",params=kv)
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         print(r.request.url)
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         r.raise_for_status()
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         print(len(r,text))
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
     except:
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         print(
     
     "爬取失败")
    
    
   
   
 
 

---

实例四

爬取单张网络图片

 
 

   
   

    
    

   
   
   
   

    
    

     
     import requests
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
     import os
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
     url=
     
     "http://img0.dili360.com/ga/M00/4A/77/wKgBzFsfM-2ADQ9iAC7rBKt1uIE377.tub.jpg"
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
     root=
     
     "E:/pics//"
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
     path=root +url.split(
     
     '/')[
     
     -1]
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
     try:
    
    
   
   

   
   

    
    

   
   
   
   

    
    
    
     
     if 
     
     not os.path.exists(root):
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
             os.mkdir(root)
    
    
   
   

   
   

    
    

   
   
   
   

    
    
    
     
     if 
     
     not os.path.exists(path):
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
             r=requests.get(url)
    
    
   
   

   
   

    
    

   
   
   
   

    
    
        
     
     with open(path,
     
     'wb') 
     
     as f:
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
                 f.write(r.content)
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
                 f.close()
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
                 print(
     
     "文件保存成功")
    
    
   
   

   
   

    
    

   
   
   
   

    
    
    
     
     else:
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
             print(
     
     "文件已存在")
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
     except:
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         print(
     
     "爬取失败")
    
    
   
   
 
 

---

实例五

IP地址查询

 
 

   
   

    
    

   
   
   
   

    
    

     
     import requests
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
     url=
     
     "http://www.ip138.com/ips138.asp?ip="
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
     try:
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         r=requests.get(url+
     
     '202.204.80.112')
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         r.raise_for_status()
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         r.encoding=r.apparent_encoding
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         print(r.text[
     
     -500:])
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
     except:
    
    
   
   

   
   

    
    

   
   
   
   

    
    

     
         print(
     
     "爬取失败")