python 爬取猫眼榜单100（二）--多个页面以及多进程

#!/usr/bin/env python
# -*- coding: utf- -*-
# @Author: Dang Kai
# @Date: -- ::
# @Last Modified time: -- ::
# @E-mail: @qq.com
# @Description:增加多进程

# http://maoyan.com/board/4
# http://maoyan.com/board/4?offset=20

import requests
import re
import json
from multiprocessing import Pool
from requests.exceptions import RequestException

def get_one_page(url, headers):
    '''获取单页的html'''
    try:
        reponse = requests.get(url, headers=headers)
        if reponse.status_code == :
            return reponse.text
        else:
            return None
    except RequestException:  # 异常处理
        return None

def parse_one_page(html):
    '''正则匹配所需数据'''
    pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a'
                         + '.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'
                         + '.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>', re.S)

    items = re.findall(pattern, html)
    # print(items)
    for item in items:
        yield{
            'index': item[],
            'image': item[],
            'title': item[],
            'actor': item[].strip()[:],
            'starttime': item[].strip()[:],
            'score': item[] + item[]
        }

def write_to_file(content):
    '''写入文件'''
    with open('result.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False) + '\n')
        f.close()

def main(offset):
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.75 Safari/537.36'}
    html = get_one_page(
        'http://maoyan.com/board/4?offset=' + str(offset), headers)
    # print(html)
    for item in parse_one_page(html):
        print(item)
        write_to_file(item)
if __name__ == '__main__':
    # for i in range():
    #     main(i*)
    pool = Pool()
    pool.map(main, {i* for i in range()})