python爬虫 爬取斗鱼直播数据

from time import sleep

import requests
from bs4 import BeautifulSoup

# 爬取分类页面数据

#获取斗鱼分类页面数据
def get_directory():
    #获取网页
    url = 'https://www.douyu.com/directory'
    html = requests.get(url).text
    # print(html)
    #解析网页
    soup = BeautifulSoup(html, 'lxml')
    unit_list = soup.find_all('li', class_='unit')
    # print(unit_list)
    #抓取想要的数据
    results = []
    for unit in unit_list:
        href = 'https://www.douyu.com' + unit.find('a')['href']
        # print(href)
        images = unit.find('img')['data-original']
        # print(images)
        title = unit.find('p').text
        # print(title)
        #生成字典
        dict1 = {
            'href': href,
            'image': images,
            'title': title
        }
        sleep(2)
        results.append(dict1)
    return results


def main():
    results = get_directory()
    for result in results:
        href = result['href']
        directory_image = result['image']
        directory_title = result['title']

        detail_list = get_zhibo(href, directory_title, directory_image)


if __name__ == '__main__':
    m