（２）请用requests库的get()函数访问必应主页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。
import requests
for i in range(20):
r = requests.get("https://cn.bing.com/?intlf=&mkt=zh-cn", timeout=30) #网页链接可换
r.raise_for_status()
r.encoding = 'utf-8'
print('状态={}'.format(r.status_code))
print(r.text)
print('text属性长度{}，content属性长度{}'.format(len(r.text), len(r.content)))
（３）这是一个简单的html页面,请保持为字符串，完成后面的计算要求。（良好）
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>菜鸟教程(runoob.com)</title>
</head>
<body>
<h1>我的第一个标题</h1>
<p id="first">我的第一个段落。</p>
</body>
<table border="1">
<tr>
<td>row 1, cell 1</td>
<td>row 1, cell 2</td>
</tr>
<tr>
<td>row 2, cell 1</td>
<td>row 2, cell 2</td>
</tr>
</table>
</html>
要求：a 打印head标签内容和你的学号后两位
b,获取body标签的内容
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
from bs4 import BeautifulSoup
r = '''
<!DOCTYPE html>
<html>
<head>29号的作业
<meta charset="utf-8">
<title>菜鸟教程(runoob.com) </title>
</head>
<body>
<h1>我的第一个标题</h1>
<p id="first">我的第一个段落。</p>
</body>
<table border="1">
<tr>
<td>row 1, cell 1</td>
<td>row 1, cell 2</td>
</tr>
</table>
</html>
'''
demo = BeautifulSoup(r, "html.parser")
print(demo.head)
print(demo.title)
print(demo.body)
print(demo.p)
print(demo.string)
(4) 爬中国大学排名网站内容，
import requests
from bs4 import BeautifulSoup
import csv
import os
ALL = []
def getHTMLtext(url):
try:
r = requests.get(url, timeout=30)
r.raise_for_status()
r.encoding = 'utf-8'
return r.text
except:
return ""
def fillUni(soup):
data = soup.find_all('tr')
for tr in data:
td1 = tr.find_all('td')
if len(td1) == 0:
continue
Single = []
for td in td1:
Single.append(td.string)
ALL.append(Single)
def writercsv(save_road, num, title):
if os.path.isfile(save_road):
with open(save_road, 'a', newline='') as f:
csv_write = csv.writer(f, dialect='excel')
for i in range(num):
u = ALL[i]
csv_write.writerow(u)
else:
with open(save_road, 'w', newline='') as f:
csv_write = csv.writer(f, dialect='excel')
csv_write.writerow(title)
for i in range(num):
u = ALL[i]
csv_write.writerow(u)
title = ["排名", "学校名称", "省市", "总分", "生源质量", "培养结果", "科研规模", "科研质量", "顶尖成果", "顶尖人才",
"科技服务", "产学研究合作", "成果转化"]
save_road = "D:\\html.csv"
def main(num):
url = "https://www.shanghairanking.cn/rankings/bcur/201911"
html = getHTMLtext(url)
soup = BeautifulSoup(html, "html.parser")
fillUni(soup)
writercsv(save_road, num, title)
main(10)