request re 250

import re
from multiprocessing.pool import Pool

import requests
from requests 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(
        '<li>.*?alt="(.*?)".*?src="(.*?)".*?<p class="">(.*?)</p>.*?<span>(.*?)</span>.*?class="inq">(.*?)</span>.*?</li>',
        re.S)
正则的写法尽量用非贪婪匹配，即.*?并且最后加上re.S表示。可代表换行，匹配先找前面的类似于
关键字如src class=‘’等匹配完还要加上本标签的闭标签<p class="">(.*?)</p>
 items = re.findall(pattern, html)查找所有的
    for item in items:
        yield { yield 可理解为一个每一次调用就返回这些值
            item[0],括号中的第几个
            # 'pic': item[1],
            # 'actor': item[2].strip(' '),
            # 'commentSum': item[3],
            item[4]
        }


def write_to_file(content):
    with open('result.tx', 'a', encoding='utf-8') as ff: encoding中文
        ff.write(str(content) + '\n')
        ff.close()


def main(start):
    url = 'https://movie.douban.com/top250?start=' + str(start)
    html = get_one_page(url)
    # parse_one_page(html)
    for item in parse_one_page(html):for 循环迭代yield返回值
        print(item)
        write_to_file(item)


if __name__ == '__main__':类似于main方法，开头
    pool = Pool()线程池
    pool.map(main, [i * 25 for i in range(10)])方法名，迭代for