关于php:python-采集唯美girl

48次阅读

共计 841 个字符，预计需要花费 3 分钟才能阅读完成。

import requests;
import re;
import os;
# 1. 申请网页
header = {"user-agent":'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'
}
response = requests.get('https://www.vmgirls.com/2957.html',headers=header)
# print(response.text)
html =  response.text

# 2. 解析网页

urls = re.findall('<img alt="(.*?)".*?data-pagespeed-lsc-url="(.*?)".*?>',html)
dir_name = re.findall('<h1 class="post-title h3">(.*?)</h1>',html);
dir_name = dir_name[0]
if not os.path.exists(dir_name):
    os.mkdir(dir_name)
# print(urls)
# print(dir_name)

# 3. 保留图片
for url in urls:
    file_name = url[1].split('/')[-1]
    # print(file_name)
    # print(url[1])
    response = requests.get(url[1],headers=header)
    with open(dir_name+'/'+file_name,'wb') as f:
        f.write(response.content)