Python爬虫之BeautifulSoup库——爬取大学排名

这个实例解决了输出的中文对齐的问题

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):
    tplt="{0:^10}\t{1:{3}^10}\t{2:^10}"
    # print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","总分"))
    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.com/zuihaodaxuepaiming2019.html"
    html=getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20)
main()

以下是对上面代码的一些改进,使其可以输出指定排名段的大学

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,start,end):
    tplt="{0:^10}\t{1:{3}^10}\t{2:^10}"
    # print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","总分"))
    print(tplt.format("排名", "学校名称", "总分",chr(12288)))
    for i in range(start-1,end):
        u=ulist[i]
        print(tplt.format(u[0],u[1],u[2],chr(12288)))

def main():
    uinfo=[]
    start=int(input('输入起始排名:'))
    end=int(input('输入最后排名:'))
    url="http://www.zuihaodaxue.com/zuihaodaxuepaiming2016.html"
    html=getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,start,end)
main()


你可能感兴趣的:(Python爬虫之BeautifulSoup库——爬取大学排名)