爬点今日头条街拍美女。。。

上代码这里写代码片

import re,json,requests,os
from urllib import request
headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.5702.400 QQBrowser/10.2.1893.400'
}
for i in range(0,60,20):
    url='https://www.toutiao.com/search_content/?offset='+str(i)+'&format=json&keyword=%E8%A1%97%E6%8B%8D&autoload=true&count=20&cur_tab=3&from=gallery'
    req = request.Request(url,headers=headers)
    response = request.urlopen(req)
    html = response.read().decode('utf-8')
    html = json.loads(html)
    try:
        for url_list in html['data']:
            url = url_list['article_url']
            response = requests.get(url,headers=headers)
            html = response.text
            req = r'gallery: JSON\.parse\((.*)\),'
            html1 = re.search(req,html)
            html1 = html1.group(1)
            html2=json.loads(html1)
            html3=json.loads(html2)
            list = html3['sub_images']
            for image in list:
                image_url = image['url']
                filename = 'image1/' + image_url.split('/')[-1] + '.jpg'
                request.urlretrieve(image_url, filename)
    except:
        continue