使用正则公式来爬取豆瓣top250

        使用re软件包来进行爬取电影的排序、电影图片、名称、导演、主演、得分、评分人数

        下面是我运行的代码

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


def get_one_page(url):
    try:
        headers = {
            'User-Agent': ''
        }
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            #print(response.text)
            return response.text
        return None
    except RequestException:
        return None


def parse_one_page(html):
    pattern = re.compile('<li>.*?="">(\d+)</em>.*?src="(.*?)".*?"title">(.*?)</span>.*?"">.*?导演:(.*?)<br>.*?average">(.*?)</span>.*?<span>(.*?)</span>', re.S)
    items = re.findall(pattern, html)
    print(items)

    for item in items:
        yield {
            'index': item[0],
            'image': item[1],
            'title': item[2],
            '导演': item[3],
            'score': item[4],
            'number': item[5]
        }


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


def main(offset):
    url = 'https://movie.douban.com/top250?start=0' + 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(offset=i * 25)
        time.sleep(1)

        运行结果展示