【python爬虫】美拍网图片下载

import os
import re
import threading
import requests
from bs4 import BeautifulSoup
import time

headers = {
    'Cookie': '_ga=GA1.2.87052855.1662906879; _gid=GA1.2.106606571.1662906879; twk_idm_key=Szy-fmwxLJBDQNQQ_hKZE; TawkConnectionTime=0; twk_uuid_5e23d8f08e78b86ed8aa0035=%7B%22uuid%22%3A%221.101H94883vBguY180oYHfz0VN3Yrx0pdi2oaeD50URIjcHT13XZdZReDZEMwzt5gW4NEYVHRIUmMAPKTQXzgo0tbdNL6fRa2f2JnkKEdjUC5Me7ZTzLZlaEgUmdlaJJk9PBSm4ORF3UQSw%22%2C%22version%22%3A3%2C%22domain%22%3A%224zipai.net%22%2C%22ts%22%3A1662906990942%7D; __cf_bm=v0FGBMppZPUweg7R0uBuFPrQlE71b0ptig4q4MkaeBU-1662906991-0-AcVALr7cJKi1sMQpzf8Zs1DEJ1PojPDd9mLT8fncCrdyiEBznfws9/awsYksUmTA0dbcUfgPxplYWbTz7LfBSmLvl1dQAD4RU0ni6jxBgdSIvn8SxmBZSJkJCI00EuzjOw==',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'
}

class myThread(threading.Thread):
    def __init__(self, url, fileName, file_path):
        threading.Thread.__init__(self)
        self.url = url
        self.file_path = file_path
        self.fileName = fileName

    def open_url(self, url):
        response = requests.get(url, headers)
        return response.text

    def run(self):
        img = requests.get(self.url, headers=headers)
        file = self.file_path + "\\" + self.fileName + ".jpg"
        if not os.path.exists(file):
            print("Downloading %s" % self.fileName)
            with open('%s/%s.jpg' % (self.file_path, self.fileName), 'wb') as f:
                f.write(img.content)
        else:
            print(self.file_path + "\\" + self.fileName + " exist")

# 'https://4zipai.net/selfies/202207/139004.html'
save_path = input("输入要保存的路径文件夹")
url = input("输入网址")
rsp = requests.get(url=url, headers=headers)
rsp.encoding="UTF-8"
soup = BeautifulSoup(rsp.text, 'lxml')
# 获得标题名
title=soup.find('div',class_="item_title")
save_path=save_path+'\\'+ str(title.find("h1").text).strip(" ")
# 创建标题对应目录
if not os.path.exists(save_path):
    os.makedirs(save_path)
li = soup.find(class_='content_left')
for i in li.find_all('img'):
    # 查找图片链接
    each_url=str(i.get('src'))
    judge = each_url[1]
    if judge == "d":
        each_url = "https://4zipai.net/" + each_url
    name = str(each_url).split('/')[-1].split('.')[0]
    if len(name) >= 9:
        thread1 = myThread(each_url, name, save_path)
        thread1.start()
        time.sleep(0.1)