爬虫作业-526互联

import requests


url = 'https://www.baidu.com'
for i in range(20):
    response = requests.get(url)
    print(f"第{i+1}次访问")
    print(f'Response status: {response.status_code}')
    print(f'Text content length: {len(response.text)}')
    print(f'Content length: {len(response.content)}')
    print(response

.text)

运行结果

from bs4 import BeautifulSoup
import re


text = """
<!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>
"""
# 创建BeautifulSoup对象
soup = BeautifulSoup(text, features="html.parser")

# 打印head标签和学号后两位
print(soup.head.prettify())
print("学号: 22\n")

# 获取body标签对象
print(soup.body.prettify())

# 获取id为first的对象
first_p = soup.find(id="first")
print(first_p)

# 获取打印中文字符
pattern = re.compile(u'[\u4e00-\u9fff]+')
chinese_chars = pattern.findall(text)
print(chinese_chars)

运行结果