import  requests

import re

import json

from multiprocessing import Pool

#引用异常处理机制,这个类是所有异常类的超类,所以能全捕捉

from  requests.exceptions import RequestException

def get_one_page(url):

    try:

        response=requests.get(url)

        if response.status_code==200:

            return response.text

        return  None

    except RequestException :

        return  None

def parse_one_page(html):

    pattern=re.compile('<dd>.*?board-index.*?(\d+)</i>.*?data-src="(.*?)".*?name"><a.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?integer">(.*?)</i>.*?fraction">(.*?)</i>',re.S)

    items=re.findall(pattern,html)

    for item in items:

        yield  {

            "index":item[0],

            "iamge":item[1],

            "title":item[2],

            "actor":item[3].strip()[3:],

            "time":item[4].strip()[5:],

            "score":item[5]+item[6]

        }

def write_to_file(content):

    with open("result.txt","a",encoding="utf8") as f:

        f.write(json.dumps(content,ensure_ascii=False)+"\n")

        # f.close() 可以不关

def main(offset):

    url="http://maoyan.com/board/4?offset="+str(offset)

    html=get_one_page(url)

    # print(html)

    # parse_one_page(html)

    for item in parse_one_page(html):

        print(item)

        write_to_file(item)

    # print(html)

if __name__=="__main__":

    # for i in range(10):

    #     main(i*10)

    # 使用多进程

    pool=Pool()

    pool.map(main,[i*10 for i in range(10)])