Requests库+正则表达式爬取猫眼Top100

import requests
from requests.exceptions import RequestException
import re
import json
from multiprocessing import Pool

# 定义抓取一页信息的函数
def get_one_page(url):
    try:
        response = requests.get(url) # 获取网页信息
        if response.status_code == 200: #根据状态码确认获取状态
            return response.text
        return None
    except RequestException:
        return None

# 解析获取到的信息
def parse_one_parse(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]
               }
# 将解析出来的信息写入文件
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
# 爬虫程序的主函数
def main(offset):
    url = 'https://maoyan.com/board/4?offset='+str(offset)
    html = get_one_page(url)
    for item in parse_one_parse(html):
        print(item)
        write_to_file(item)

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