使用PyCharm，Python版本3.6手写一个10线程秒抓爬虫

纯属娱乐，不过python是当下一门值得学的脚本语言
正则根据的是http://maoyan.com/board/4的h5页面
记得request.get中的headers要写自己浏览器的
选取排名的一部分内容爬取，保存到result.txt文件下

import re
from multiprocessing.dummy import Pool
import requests
from flask import json
from   requests.exceptions import RequestException
def get_one_page(url,headers):
    try:
       response = requests.get(url,headers=headers)
       if response.status_code == 200:
           return response.text
       return None
    except RequestException:
       return None
# 正则匹配
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>.*?</dd>',re.S)
    items = re.findall(pattern,html)
    for item in items:
        yield {
            'index': item[0],
            'image': item[1],
            'title': item[2],
            'actor': item[3].strip()[3:],
            'time' : item[4].strip()[5:],
            'score': item[5]+item[6]
        }
# 写入txt文件
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()
# 循环爬取
def main(offset):
    url = 'http://maoyan.com/board/4?offset=' + str(offset)
    headers = {"User-Agent":"Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36"}
    html = get_one_page(url,headers)
    for item in parse_one_page(html):
        print(item)
        write_to_file(item)
# 主方法
if  __name__  == "__main__":
    pool = Pool()
    pool.map(main, [i*10 for i in range(10)])