利用BS4的select及find_all查找HTML常见的元素和属性

from bs4 import BeautifulSoup
import requests

url = 'https://www.example.com'
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')

# 找到所有的<div>标签
divs = soup.find_all('div')

# 找到所有的<p>标签，并获取其文本内容
paragraphs = [p.get_text() for p in soup.find_all('p')]

# 找到所有的<a>标签，并获取href属性
links = [(a['href']) for a in soup.find_all('a', href=True)]

# 使用CSS选择器查找class为'class-name'的所有<div>标签
divs_with_class = soup.select('div.class-name')

# 查找所有带有id='id-name'的元素
element_with_id = soup.select('#id-name')

# 查找所有的<h1>标签，并获取其文本内容
headings = [h.get_text() for h in soup.find_all('h1')]

# 打印结果
print(divs)
print(paragraphs)
print(links)
print(divs_with_class)
print(element_with_id)
print(headings)