-3 定向爬取中国大学排名

最新推荐文章于 2024-05-20 17:16:40 发布

Name:LIJIAN

最新推荐文章于 2024-05-20 17:16:40 发布

阅读量135

点赞数

本文链接：https://blog.csdn.net/weixin_44393116/article/details/95732123

版权

import requests
from bs4 import BeautifulSoup
import bs4

def getHTMLText(url):
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

def fillUnivList(ulist, html):
            soup = BeautifulSoup(html, "html.parser")
            for tr in soup.find('tbody').children:
                if isinstance(tr, bs4.element.Tag):
                    tds = tr('td')
                    ulist.append([tds[0].string, tds[1].string, tds[3].string])

# def printUnivList(ulist, num):
#     print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","总分"))
#     for i in range(num):
#         u=ulist[i]
#         print("{:^10}\t{:^6}\t{:^10}".format(u[0],u[1],u[2]))

def printUnivList(ulist, num):
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
    print(tplt.format("排名","学校名称","总分",chr(12288)))
    for i in range(num):      
        u=ulist[i]
        print(tplt.format(u[0],u[1],u[2],chr(12288)))


def main():
    uinfo = []
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20) # 20 univs main()

if __name__ == '__main__':
    main()

要点一：

了解： for tr in soup.find('tbody').children: #遍历标签树
if isinstance(tr, bs4.element.Tag):

tds = tr('td')

#简写，等价于 #tds = tr.find_all('td')

ulist.append([tds[0].string, tds[1].string, tds[3].string])

要点二：了解format函数的应用

print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","总分"))
print("{:^10}\t{:^6}\t{:^10}".format(u[0],u[1],u[2]))

要点三：

def printUnivList(ulist, num):
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"   #（{3}用format中第三个变量来填充，就是中文填充）
    print(tplt.format("排名","学校名称","总分",chr(12288)))
    for i in range(num):
        u=ulist[i]
        print(tplt.format(u[0],u[1],u[2],chr(12288)))