猫眼电影北美票房爬虫 Request + 正则 加强训练

import json
import re
from multiprocessing.pool import Pool

import requests
from requests import RequestException


def get_one_page(url):
    try:
        response =requests.get(url)
        # print(response.text)
        if response.status_code==200:
            return response.text
    except RequestException:
        return None

def parse(html):
    '''
    对界面进行解析
    :param html:
    :return:
    '''
    # pattern=re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a .*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?realtime">(.*?)<span>.*?stonefont">(.*?);</span></span>(.*?)</p>.*?office">(.*?)<span>.*?stonefont">(.*?);</span></span>(.*?)</p>',re.S)#正则表达式
    pattern=re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a .*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?realtime">(.*?)<span>',re.S)#正则表达式
    items=re.findall(pattern,html)
    for item in items:
        yield {
            '序号':item[0],
            '图片':item[1],
            '电影名': item[2],
            '主演': item[3].strip()[3:],
            '上映时间': item[4].strip()[5:],
        }

def write_to_file(content):
    '''
    写入文本
    :param content:
    :return:
    '''
    with open('北美票房榜.txt', 'a',encoding='utf-8')as f:#打开文件，如果没有就创建，encoding 指定编码方式
        f.write(json.dumps(content,ensure_ascii=False)+'\n')#ensure_ascii=False以指定的方式编码


def main():
    url='https://maoyan.com/board/2'
    html=get_one_page(url)
    for item in parse(html):

        print(item)
        write_to_file(item)
if __name__ == '__main__':
    main()
    # pool=Pool()#多线程 进程池
    # pool.map(main,[i*10 for i in range (10)])