python爬虫之爬取猫眼榜单

import requests
from bs4 import BeautifulSoup
headers = {
    ‘user-agent‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko)     Chrome/70.0.3538.102 Safari/537.36‘
}


def open_url(url):
    r = requests.get(url, headers=headers)
    r.encoding = ‘utf-8‘
    html = r.text
    return html


def get_info(html):
    # num = 1
    soup = BeautifulSoup(html, ‘lxml‘)
    text_info = soup.find_all(‘div‘, class_="movie-item-info")
    # for i in text_info:
    #     info = str(num) + ‘.‘ + i.text.replace(‘ ‘, ‘‘).replace(‘\n‘, ‘  ‘) + ‘\n‘
    #     print(info)
    #     num += 1
    return text_info


def main():
    num = 1
    for i in range(0, 10):
        url = ‘https://maoyan.com/board/4?offset=‘ + str(0+i*10)
        html = open_url(url)
        info_list = get_info(html)
        for info in info_list:
            info = str(num) + ‘.‘ + info.text.replace(‘ ‘, ‘‘).replace(‘\n‘, ‘  ‘) + ‘\n‘
            num += 1
            with open(‘猫眼TOP100榜.txt‘, ‘a+‘) as file:
                file.write(info)
    print(‘猫眼TOP100榜下载完成！‘)


if __name__ == ‘__main__‘:
    main()