利用requests和正则爬取猫眼前一百评分电影，并保存到本地

import requests, re, json
from requests.exceptions import RequestException
from multiprocessing import Pool #引入一个进程池
from tqdm import tqdm
def get_one_page(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.92 Safari/537.36'
    }  # 反反爬，模拟游览器登录
    try:
        response = requests.get(url,headers=headers)
        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">(.*?)
.*?integer">(.*?).*?fraction">(.*?).*?
',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]
        }


def write_to_file(content):
    with open('result.txt','a',encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False)+'\n')  # 利用json.dumps将字典形式的content转化为字符串形式

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

    
if __name__ == '__main__':
#     for i in tqdm(range(10)):  # tqdm可以用来显示进度条
#         main(i*10)
    pool = Pool()
    pool.map(main,[i*10 for i in range(10)])  # 将每次爬取都放到一个进程池中