# -*-  coding:utf-8 -*-

import json

from urllib.parse import urlencode

from requests.exceptions import RequestException

import requests

def get_page_html(offset,keyword):

    data = {

        'offset':offset,

        'format':'json',

        'keyword':keyword,

        'autoload':'true',

        'count':'',

        'cur_tab':1

    }

#   urlencode把字典对象自动转化为url参数，

#   快速导入，请选中以后，按alt+enter

    url = 'https://www.toutiao.com/search_content/?' + urlencode(data)

    try:

        response = requests.get(url)

        if response.status_code == 200:

            return response.text

        return None

    except RequestException:

        print('请求索引页失败')

        return None

def parse_page_index(html):

#因为html打印出来是json字符串格式，json.loads作用是将已编码的 JSON 字符串解码为 Python 对象

# json.dumps作用是将 Python 对象编码成 JSON 字符串

#参考http://www.runoob.com/python/python-json.html

    data = json.loads(html)

    if data and 'data' in data.keys():

        for item in data.get('data'):

            yield item.get('article_url')

def main():

    html = get_page_html(0,'中超')

#打印抓取的文章详细内容的url

    for url in parse_page_index(html):

        print(url)

#打印获取页面内容

    print(html)

if __name__ == '__main__':

    main()