import re
import time
import os
import requests


def get_html_str(url, head):
    resp = requests.get(url=url, headers=head).text
    return resp


if __name__ == '__main__':
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                      'Chrome/103.0.5060.114 Safari/537.36 Edg/103.0.1264.62 '
    }
    start = input("請輸入起始頁[start,end]:")
    end = input("請輸入終止頁:")
    for i in range(int(start), int(end) + 1):
        base_url = "https://www.vmgirls.net/page/{}?ref=www.xike.store".format(i)
        txt01 = get_html_str(base_url, headers)
        re01 = 'class="media-content" href="(.*?)"'
        title_url = re.findall(re01, txt01)
        for j in title_url:
            txt02 = get_html_str(j, headers)
            re02 = '<h1 class="post-title mb-3">(.*?)</h1>'
            file_title = re.findall(re02, txt02)[-1]
            file_title.replace('/', '').replace('|', '').replace(':', '')
            file_path = 'weimei/'+file_title
            if os.path.exists(file_path):
                print('文件夾已存在')
                continue
            os.mkdir(file_path)
            re03 = 'src="(.*?)"'
            img_url = re.findall(re03, txt02)
            del img_url[0:1]
            # print(img_url)
            for k in range(1, len(img_url)):
                img_name = str(k)+".png"
                img = requests.get(url=img_url[k], headers=headers).content
                with open(file_path+'/'+img_name, 'wb') as fp:
                    fp.write(img)
                fp.close()
                print(f"第{k}張下載成功")
                time.sleep(0.3)

# 沒難度