Python批量爬取写真网站

介绍

　　一个批量爬取写真网站的爬虫，无聊随便写的。代码也非常的简单，随便分享一下吧
站点：http://www.tdz4.com/

效果

代码

import re
import os
import requests
num =1
if not os.path.exists('D:/image/'):
    os.mkdir(('D:/image/'))

pages =int(input('输入你要爬取的页数'))
for page in range(0,pages):
    print(f'\n===========\t正在爬取第{page}页\t===========')
    url = f"http://www.tdz4.com/whzm/page/{page}"

    resp = requests.get(url=url)
    # print(resp.text)
    data =re.findall('<h2><a  href="(.*?)">(.*?)</a></h2>',resp.text)

    for i in data:
        name =i[1]
        img_url=i[0]
        print(img_url,name)
        data =requests.get(url=img_url)
        img_url= re.findall('data-src="(.*?)"> <img',data.text)

        for a in img_url:
         print(a)
         data =requests.get(url=a).content
         with open(f'D:/image/{name}{num}.jpg',"wb")as f:
             f.write(data)
             num +=1

print('\n\n===========\t爬取完毕！！！===========\t')
print(f'\n共爬取{num-1}张')

爬取url链接

差不多，上面代码是爬取图片下载，下面是爬取图片url然后保存到文本！

import re
import os
import requests
num =1
if not os.path.exists('D:/image/'):
    os.mkdir(('D:/image/'))

pages =int(input('输入你要爬取的页数'))
for page in range(0,pages):
    print(f'\n===========\t正在爬取第{page}页\t===========')
    url = f"http://www.tdz4.com/whzm/page/{page}"

    resp = requests.get(url=url)
    # print(resp.text)
    data =re.findall('<h2><a  href="(.*?)">(.*?)</a></h2>',resp.text)

    for i in data:
        name =i[1]
        img_url=i[0]
        print(img_url,name)
        data =requests.get(url=img_url)
        img_url= re.findall('data-src="(.*?)"> <img',data.text)

        for a in img_url:
         print(a)
         data =requests.get(url=a).content
         with open(f'写真.txt', mode='a', encoding='utf-8', ) as f:  # 保存路径，追加写入
             f.write(a)
             f.write('\n')
             num +=1

print('\n\n===========\t爬取完毕！！！===========\t')
print(f'\n共爬取{num-1}张')