ajax爬取今日头条

代码
import requests
from urllib.parse import urlencode
import os,time
from urllib.request import urlretrieve

#请求：
def get_page(offset):
    params = {
        "offset":offset,
        'format':'json',
        'keyword':'街拍',
        'autoload':'true',
        'count':'20',
        'cur_tab':'1',

    }
    url = 'https://www.toutiao.com/search_content/?'+urlencode(params)
    try:
        res = requests.get(url)
        if res.status_code == 200:
            return res.json()
        else:
            return None
    except requests.ConnectionError:
        return None
#解析
def get_images(json):
    if json.get('data'):
        for item in json.get("data"):
                print(item)
                title = item.get('title')
                image_list = item.get('image_list',[])特别是注意这里，如果没有数据，就需要要后门加上[]
                print(image_list)
                for image in image_list:
                    yield{
                        "image":image.get('url'),
                        'title':title,

                    }
#保存图片
def saveTmage(item):
    path = os.path.join("./mypic",item.get('title'))
    if not os.path.exists(path):
        os.mkdir(path)

    local_image_url = item.get("image")
    image_url = 'http:'+ local_image_url.replace('list','large')
    save_pic = path +"/"+local_image_url.split("/").pop()+'.jpg'

    urlretrieve(image_url,save_pic)
#主函数
def main(offset):
    json = get_page(offset)
    for item in get_images(json):
        print(item)
        saveTmage(item)
#调用主函数
if __name__ == '__main__':
    for i in range(5):
        main(offset=i*20)
        time.sleep(1)