网络爬虫之提取（BeautifulSoup）

选取非文本类型节点，需要import bs4
<>.() 等价于 <>.find_all()#查询该<>节点下全部某节点
soup() 等价于 souo.find_all()#查询全部某节点
输出中文对齐问题

#CrawUnivRankingB.py
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):#选取非文本节点类型，需要import bs4
            tds = tr('td')#tds = tr.find_all('td')
            ulist.append([tds[0].string, tds[1].string, tds[3].string])#列表
 
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)))#chr(12288),表示以中文空格字符填充
    for i in range(num):
        u=ulist[i]
        print(tplt.format(u[0],u[1],u[2],chr(12288)))
     
def main():
    uinfo = []
    url = 'https://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20) # 20 univs
main()