python多线程秒爬猫眼电影Top100

• 通过python3的多线程，获取猫眼电影top100电影清单，并保存信息到本地,使用了requests库和正则表达式

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Author: Aiker Zhao
# @Date  : 2019/4/2 2:52 AM
# @File  : pamaoyan.py
# @Desc  : 
import requests
from requests.exceptions import RequestException
import re
import json
from multiprocessing import Pool

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('
.*?board-index.*?>(\d+).*?data-src="(.*?)".*?name">(.*?).*?star">(.*?)
'
                         + '.*?releasetime">(.*?)(.*?).*?fraction">(.*?).*?
', re.S)
    pattern1 = re.compile('board-index.*?>(\d+).*?data-src="(.*?)".*?name">(.*?).*?star">(.*?)
', re.S)

    items = re.findall(pattern, html)
    # print(items)
    for item in items:
        yield {
            'index': item[0],
            'score': item[5] + item[6],
            'image': item[1],
            'title': item[2],
            'actor': item[3].strip()[3:],
            'time': item[4][5:]
        }

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

def main(offset):
    url = 'https://maoyan.com/board/4?offset=' + str(offset)
    html = get_one_page(url)
    # print(html)
    for item in parse_one_page(html):
        print(item)
        write_to_file(item)

if __name__ == '__main__':
    # for i in range(10):
    #     main(i*10)
    pool = Pool()
    pool.map(main, [i * 10 for i in range(10)])