爬取猫眼电影榜单Top100

废话不多说，直接上代码

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

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('<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],
            'name':item[2],
            'actor':item[3].strip()[3:],
            'time':item[4].strip()[5:],
            'score':item[5]+item[6]
        }

def write_to_file(content):#将爬取到的电影信息保存到本地文件夹
    with open('result.txt','a',encoding='utf-8') as f:#将编码格式设置为utf-8
        f.write(json.dumps(content,ensure_ascii=False)+'\n')
        f.close()

def main(offset):
    url = 'http://maoyan.com/board/4?offset='+str(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 range(10):
        main(i*10)