大学排名爬虫

# 利用 requests 库爬取网页内容
import requests
from bs4 import BeautifulSoup
import bs4


def get_text(url):
    try:
        r = requests.get(url)
        r.raise_for_status()   # 判断状态码是否为200
        r.encoding = r.apparent_encoding  # 使返回的编码准确
        return r.text
    except:
        print("异常")   # 如果状态码不是200就会产生异常
        return " "


def university_list(ulist, html):
    soup = BeautifulSoup(html, "html.parser")
    for tr in soup.find('tbody').children:   # 查找的子节点
        if isinstance(tr, bs4.element.Tag):  # 剔除不需要的信息
            tds = tr('td')
            # 要用strip（）去除文本中的空格，不然内容为none时会报错
            # 把td信息存入ulist中
            ulist.append([tds[0].text.strip(), tds[1].text.strip(), tds[2].text.strip(), tds[3].text.strip(), tds[4].text.strip()])


def university_rank(ulist, num):
    # {5}：中间的部分用第五个元素填充，即chr（12288）所表示的空格
    template = "{0:^10}\t{1:{5}^10}\t{2:{5}^10}\t{3:{5}^10}\t{4:^10}"
    print(template.format("排名", "学校名称", "省市", "类型", "总分", chr(12288)))  # chr（12288）中文空格
    for i in range(num):
        u = ulist[i]
        print(template.format(u[0], u[1], u[2], u[3], u[4], chr(12288)))


def main():
    university_info = []
    url = "http://www.shanghairanking.cn/rankings/bcur/2020"
    html = get_text(url)
    university_list(university_info, html)
    university_rank(university_info, 76)


if __name__ == '__main__':
    main()

转载https://blog.csdn.net/cjx_up/article/details/77883892