【爬虫系列，OMG，学它

import requests

import re

import os

#如果目录不存在，那么创建目录，反之不创建

if not os.path.exists(’./qiutuLibs’):

os.mkdir('./qiutuLibs')

url = ‘https://www.qiushibaike.com/imgrank/’

headers = {

'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36'

}

#解析页面以二进制的形式

page_text = requests.get(url=url,headers=headers).text

#利用正则定位出图片url地址，以便于下载

ex = ‘

. ?<img src="(.?)" alt.*?

’

img_src_list = re.findall(ex,page_text,re.S)

for src in img_src_list:

#拼接出一个完整的链接

src = 'https:'+src

#请求到图片的二进制数据

img_data = requests.get(url=src,headers=headers).content

#给你的图片命名

img_name = src.split('/')[-1]

#图片路径设置

imgPath = './qiutuLibs/'+img_name

#下载图片

with open(imgPath,'wb') as fp:

    fp.write(img_data)

    print(img_name,'SUCCESSFUL!!!!!!!!!!!!!!')

[]( )3、爬取多页面数据

------------------------------------------------------------------------

import requests

import re

import os

if not os.path.exists(’./qiutuLibs’):

os.mkdir('./qiutuLibs')

#设置一个通用的url模板即可实现多页爬取

url = ‘https://www.qiushibaike.com/imgrank/page/%d’

headers = {

'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36'

}

#利用for循环，循环出页码，针对每页进行解析下载

#类似于打印乘法口诀那样

for pageNum in range(1,3):

new_url = format(url%pageNum)

page_text = requests.get(url=new_url,headers=headers).text



ex = '<div class="thumb">.*?<img src="(.*?)" alt.*?</div>'

img_src_list = re.findall(ex,page_text,re.S)

# print(img_src_list)



for src in img_src_list:

    #拼接出一个完整的链接

    src = 'https:'+src

    #请求到图片的二进制数据

    img_data = requests.get(url=src,headers=headers).content

    img_name = src.split('/')[-1]

    imgPath = './qiutuLibs/'+img_name

    with open(imgPath,'wb') as fp:

        fp.write(img_data)

        print(img_name,'SUCCESSFUL!!!!!!!!!!!!!!')

[]( )4、贪婪模式和非贪婪模式

---------------------------------------------------------------------------




### 最后

> **笔者已经把面试题和答案整理成了面试专题文档**
>
> **[CodeChina开源项目：【一线大厂Java面试题解析+核心总结学习笔记+最新讲解视频】](https://codechina.csdn.net/m0_60958482/java-p7)**

![image](https://img-blog.csdnimg.cn/img_convert/24665a3f512164a3f895b0e4f4726b90.png)

 ![image](https://img-blog.csdnimg.cn/img_convert/d17764a544b93f81a76f27a12d7b603d.png)

![image](https://img-blog.csdnimg.cn/img_convert/047f1898e0b3432ffaabe55912dda465.png)

 ![image](https://img-blog.csdnimg.cn/img_convert/90e4b9e81ed9f702356d96a16d1e575b.png)

![image](https://img-blog.csdnimg.cn/img_convert/9774a4f7ca0f235e3ac51c5afdfa2452.png)

)]

 [外链图片转存中...(img-YwQXll1E-1630929738692)]

[外链图片转存中...(img-sASLdr5a-1630929738693)]

 [外链图片转存中...(img-cTQYk5OQ-1630929738695)]

[外链图片转存中...(img-xLfvGMt6-1630929738696)]

 ![image](https://img-blog.csdnimg.cn/img_convert/8a02592cd22916e3e750d045a5ee6d00.png)