python--爬取最好大学信息

在B站上学习python，写的代码。

python--爬取最好大学信息

import requests
from bs4 import BeautifulSoup
import bs4
def getHTMLText(url):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "网页信息获取失败"

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[4].string])

    pass
def printUnivList(ulist, num):
    tplt = "{0:^10}\t{1:{3}^8}\t{2:^10}"
    print(tplt.format("排名", "学校", "总分", chr(12288)))
    #print("{:^10}\t{:^6}\t{:^15}".format("排名", "学校名称", "总分"), chr(12288))
    #print(tplt.format("排名", "学校名称", "总分"))
    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.com/subject-ranking/computer-science-engineering.html"
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20) #  只列出前20

main()

getHTMLText(url): 获取内容

fillUnivList(ulist, html)：提取信息，存放到合理的数据结构中

printUnivList(ulist, num) : 格式化输出，num控制输出多少

tplt = "{0:^10}\t{1:{3}^8}\t{2:^10}" -- 0代表第一个位置，^代表右对齐方式，{3}空三个格。

其中还有，chr（12288）代表utf-8字符集合