爬取猫眼top100

import json
import multiprocessing
import time

import requests
from requests.exceptions import RequestException
import re


def get_one_page(url):
    try:
        headers = {"Referer": "https://maoyan.com/board/4?offset=0", "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:93.0) Gecko/20100101 Firefox/93.0"}
        resp = requests.get(url, headers=headers)
        if resp.status_code == 200:
            return resp.content.decode()
        return None
    except RequestException:
        return None


def parse_one_page(html):
    pattern = re.compile(r'<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)
    if len(items) == 0:
        print(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(dict_):
    with open("douban1.txt", 'a', encoding='utf-8') as f:
        f.write(json.dumps(dict_, ensure_ascii=False) + '\n')



def main(offset):
    url = "https://maoyan.com/board/4?offset="

    print(url + str(offset))
    html = get_one_page(url + str(offset))

    # if html == None:
    #     print("None")
    # print(html)
    for dict_ in parse_one_page(html):
        print(dict_)
        write_to_file(dict_)


if __name__ == '__main__':
    # p = multiprocessing.Pool()
    # p.map(main, [i*10 for i in range(10)])
    for i in range(10):
        main(i*10)
        time.sleep(2)