今日头条网页图片爬取

import requests,os,json,re
from urllib import request
from day3.mysql_text import mysql_conn
for i in range(0,60,20):
    url = 'https://www.toutiao.com/search_content/?offset={}&format=json&keyword=%E8%A1%97%E6%8B%8D&autoload=true&count=20&cur_tab=1&from=search_tab'.format(i)
    print(url)

    headers = {
        'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.75 Safari/537.36'
    }

    response = requests.get(url,headers=headers)
    html_json_dict = response.json()


    # 获取dict中的data key对应的列表



    data_list = html_json_dict['data']

    # 获取列表中含有article_url的值
    for data_item in data_list:
        if 'article_url' in data_item:
            article_url = data_item['article_url']

            response = requests.get(article_url,headers=headers)

            html_str = response.text
            pattern = r'gallery: JSON.parse((.*)),'

            match_res = re.search(pattern, html_str)

            # 新建文件夹
            if not os.path.exists('downloads'):
                os.mkdir('downloads')

            if match_res:
                # print(match_res.group(1))
                json_origin = match_res.group(1)
                a1 = json.loads(json_origin)
                # print(a1,type(a1))
                a2 = json.loads(a1)
                # print(a2['sub_images'])
                for a2_list in a2['sub_images']:
                    image_url = a2_list['url']

                    filename = 'downloads/' + image_url.split('/')[-1] + '.jpg'
                    print(filename)
                    request.urlretrieve(image_url, filename)

            else:
                pass