果壳问答——函数

import re
import json
import requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36'
}
a = []

def get_html(link):
    print("\n===========正在获取数据的目标地址： ",link)
    try:
        resp = requests.get(link,headers)
        if resp.status_code == 200:
            return resp.text
    except requests.RequestException as b:
        print(b)


def parser_html(resp):
    patt = re.compile(' <h2><a target="_blank" href="(.*)">(.*\n?)</a></h2>')  # 加了 ？ 为非贪婪
    mess_list = patt.findall(resp)
    global a   #  调用 全局变量（空列表）
    for mess in mess_list:
        mess_dict = {}
        mess_dict['title'] = mess[1]
        mess_dict['link'] = mess[0]
        a.append(mess_dict)   #   列表里的字典

    conten = json.dumps(a,ensure_ascii=False)  # 数据转换 此时类型是 str  也是需要保存 json的内容


    print("\n==========正在保存数据============")
    with open(r'C:\Users\DELL\Desktop\python_wd\文本信息\\'+ '果壳问答'+ '.json','w',encoding='utf-8')as f:
        f.write(conten)
    print("\n\t\t数据保存完毕。。。。。。")









def main():
    for page in range(1,101):
        link = 'https://www.guokr.com/ask/highlight/?page={}'.format(page)
        resp = get_html(link)
        parser_html(resp)



if __name__ == '__main__':
    main()