抓取猫眼电影排行

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

def get_one_page(url):
    try:
        headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36"
        }
        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('<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)
    print(items)
    for items in items:
        yield {
            '排名': items[0],
            '图片地址': items[1],
            '电影名称': items[2],
            '演员': items[3].strip()[3:],
            '时间': items[4].strip()[5:],
            '评分': items[5]+items[6]
        }


def write_to_file(content):
    with open("maoyan.txt",'a',encoding='utf-8')as f:
        f.write(json.dumps(content,ensure_ascii=False)+'
')




def main(page):
    url = "https://maoyan.com/board/4"
    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(page=i*10)
        time.sleep(1)