python爬虫练习之soup1

import re
import requests
from bs4 import BeautifulSoup
import bs4


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


def fillUnivList(ulist, html):
    soup = BeautifulSoup(html, "html.parser")
    for tr in soup.find('tbody').children:
        if isinstance(tr, bs4.element.Tag):     #有可能是字符串，判断成为标签时才用
            tds = tr('td')
            ulist.append([tds[0].string, tds[1].string, tds[3].string])


def printUnivList(ulist, num):
    plpl = "{0:^10}\t{1:{3}^12}\t{2:^10}"
    print(plpl.format("排名", "学校", "总分", chr(12288)))  #应用全角空格进行填充格式化
    for i in range(num):
        u = ulist[i]
        print(plpl.format(u[0], u[1], u[2], chr(12288)))


def main():
    uinfo = []
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36'}
    url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html'
    html = getHTMLText(url, headers)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20)  # 20个大学


main()

plpl = “{0:^10}\t{1:{3}12}\t{2:^10}”
print(plpl.format(“排名”, “学校”, “总分”, chr(12288))) #应用全角空格进行填充格式化

soup = BeautifulSoup(html, "html.parser")
for tr in soup.find('tbody').children:
    if isinstance(tr, bs4.element.Tag):

判断标签