1、使用requests的get()函数访问必应网站20次，打印返回状态，text()内容，计算text属性和content属性所返回网页内容的长度。
代码如下：
import requests
for i in range(20):
r = requests.get('https://cn.bing.com', verify=False)
r.encoding="utf-8"
print(r.status_code)
print(r.text)
r.content
print(len(r.text))
print(len(r.content))
2、
a.打印head标签内容和学号后两位
b.获取body标签内容
c.获取id为first的标签对象
d.获取并打印html页面中的中文字符
代码如下：
import re
from bs4 import BeautifulSoup
file=open('D:/python/pythonfile/onepa.html','r').read()
soup=BeautifulSoup(file,'html.parser')
print(soup.head,'30')
print(soup.body)
print(soup.find_all(id="first"))
print(re.findall('[\u4e00-\u9fa5]+',soup.text))
3、从中国大学排名网站爬取2019年大学排名
代码如下：
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:
print("获取失败")
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[2].string,tds[3].string])
pass
def printUnivlist(ulist,num):
print("{:^4}\t{:<15}\t{:<8}\t{:<8}".format("排名","学校名称","省市","总分"))
for i in range(num):
u = ulist[i]
print("{:^4}\t{:<15}\t{:<8}\t{:<8}".format(u[0],u[1],u[2],u[3]))
def main(num):
allUniv=[]
url="https://www.shanghairanking.cn/rankings/bcur/201911.html"
html = getHTMLText(url)
fillUnivlist(allUniv,html)
printUnivlist(allUniv,num)
main(20)
