爬虫day7 头条街拍下载，简单规律，涉及正则，图片写入

import requests
import re
import json
from urllib import request
import os
def download(n):
    # 控制变量 控制页数
    url = 'https://www.toutiao.com/search_content/?offset='+str(20*(n-1))+'&format=json&keyword=%E8%A1%97%E6%8B%8D&autoload=true&count=20&cur_tab=1&from=search_tab'
    for i in range(0,n):
        url = 'https://www.toutiao.com/search_content/?offset=' + str(20 * n) + '&format=json&keyword=%E8%A1%97%E6%8B%8D&autoload=true&count=20&cur_tab=1&from=search_tab'
        response = requests.get(url)


        res_dict = response.json()
        # print(res_dict,type(res_dict))
        data_list = res_dict['data']
        src_list =[]
        # print(data_list)
        # print(data_list[1]['article_url'])
        for data in data_list:
            if 'article_url' in data.keys():
                src_list.append(data['article_url'])
        for src in src_list:
            url = src
            if not os.path.exists('download'):
                os.mkdir('download')
            headers = {
                'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
            }
            response = requests.get(url, headers=headers)
            # 正则
            res = re.search('gallery: JSON\.parse\((.*)\),', response.text)
            if res:
                res_dict = json.loads(json.loads(res.group(1)))
                print(res_dict)
                res_list = res_dict['sub_images']
                src_list = []
                for res in res_list:
                    src_list.append(res['url'])
                # print(src_list)
                print(len(src_list))
                for src in src_list:
                    print(src)
                    # 写入图片
                    filename = 'download/' + src.split('/')[-1] + '.jpg'
                    request.urlretrieve(src, filename)

download(6)