步骤
- 获取网页文本
- 将网页文本中所需内容存入列表
- 打印列表
注意 - BeautifulSoup类中string与text的区别：在标签的子标签中有不止一个标签含有字符串时，string会返回none，text可以以字符串形式返回所有标签
- 获取网页文本框架：别忘了判断状态
- 遍历子标签时需过滤掉字符串类型
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 "Error"
def fillUnivList(ulist, html):
soup = BeautifulSoup(html, "html.parser")
for tr in soup.find('tbody').children:
# filter strings, preserve tags
if isinstance(tr, bs4.element.Tag):
tds = tr('td')
ulist.append([tds[0].text, tds[1].text.split(' ')[1], tds[4].text])
def printUnivList(ulist, num):
'''
# 排版：用中文空格替代西文字符
tplt = "{0:^10}\t{1:^{3}10}\t{2:^10}"
print(tplt.format("排名", "学校", "总分", chr(12288))
for i in range(num):
u = ulist[i]
print(tplt.format(u[0].strip(), u[1].strip(), u[2].strip(), chr(12288)))
'''
print("{:^10}\t{:^30}\t{:^10}".format("排名", "学校", "总分"))
for i in range(num):
u = ulist[i]
print("{:^10}\t{:^30}\t{:^10}".format(u[0].strip(), u[1].strip(), u[2].strip()))
def main():
uinfo = []
url = "https://www.shanghairanking.cn/rankings/bcur/2020"
html = getHTMLText(url)
fillUnivList(uinfo, html)
printUnivList(uinfo, 20)
# 20 univs
main()
