爬取校花网大学校花代码

标签：spl   文件   code   html   type   取出   dirname   write   网址   

import re
import os
import requests
count = 0
for i in range(10):
url = f"http://www.xiaohuar.com/list-1-{count}.html"
response = requests.get(url)
data = response.text

result_list = re.findall('src="(.*?)" /></a>',data)
# print(type(result_list))

for result in result_list:
    # print(result,type(result))
    if not result.startswith('http'): # 取出
        res = f"http://www.xiaohuar.com/{result}"  # 拼接图片网址
        print(res)  # 打印拼接好的图片路径
        img_response = requests.get(res)  # 获取图片
        img_name = res.split('/')[-1]  # 文件名字
        img_data = img_response.content  #将图片转化为二进制

        BASE_PATH = os.path.dirname(__file__)
        img_path = os.path.join(BASE_PATH,'datas',f'{img_name}')

        with open(img_path,'ab') as fw:
            fw.write(img_data)
            fw.flush()

count += 1
print(f'爬取了{count}页')

"""

http://www.xiaohuar.com/hua/
http://www.xiaohuar.com/list-1-1.html
http://www.xiaohuar.com/list-1-0.html
http://www.xiaohuar.com/list-1-1.html
http://www.xiaohuar.com/list-1-2.html

src="/d/file/20190726/small6880259bcb61b80ce246e497a448185c1564117785.jpg"

"""

爬取校花网大学校花代码

标签：spl   文件   code   html   type   取出   dirname   write   网址   

原文地址：https://www.cnblogs.com/zuihoudebieli/p/11331768.html