Beautifulsoup4 导入模组

from bs4 import BeautifulSoup
import requests as req

Beautifulsoup4 美化 HTML 代码

# 设定网址
url = "https://www.xyblog.cc/"

# 获取网页html 
r = req.get(url)

# 导入 html 进入 beautifulsoup4
soup = BeautifulSoup(r.text, features="html.parser")

# 美化 html 代码
print(soup.prettify())

Beautifulsoup4 获取 title 标签

# 设定网址
url = "https://www.xyblog.cc/"

# 获取网页html 
r = req.get(url)

# 导入 html 进入 beautifulsoup4
soup = BeautifulSoup(r.text, features="html.parser")

# 获取 title 标签
print(soup.title)

Beautifulsoup4 获取 title 标签内部文字

# 设定网址
url = "https://www.xyblog.cc/"

# 获取网页html 
r = req.get(url)

# 导入 html 进入 beautifulsoup4
soup = BeautifulSoup(r.text, features="html.parser")

# 获取 title 标签内部文字
print(soup.title.text)

Beautifulsoup4 获取网页第一个超链接

# 设定网址
url = "https://www.xyblog.cc/"

# 获取网页html 
r = req.get(url)

# 导入 html 进入 beautifulsoup4
soup = BeautifulSoup(r.text, features="html.parser")

# 获取网页第一个超链接
print(soup.a)

Beautifulsoup4 获取网页第一个超链接的属性

# 设定网址
url = "https://www.xyblog.cc/"

# 获取网页html 
r = req.get(url)

# 导入 html 进入 beautifulsoup4
soup = BeautifulSoup(r.text, features="html.parser")

# 获取网页第一个超链接的属性
print(soup.a.attrs)

Beautifulsoup4 获取所有的元素

# 设定网址
url = "https://www.xyblog.cc/"

# 获取网页html 
r = req.get(url)

# 导入 html 进入 beautifulsoup4
soup = BeautifulSoup(r.text, features="html.parser")

# 获取所有的元素
for ele in soup.find_all():
    print(ele)

Beautifulsoup4 只获取所有的超链接

# 设定网址
url = "https://www.xyblog.cc/"

# 获取网页html 
r = req.get(url)

# 导入 html 进入 beautifulsoup4
soup = BeautifulSoup(r.text, features="html.parser")

# 只获取所有的超链接
for ele in soup.find_all("a"):
    print(ele)

Beautifulsoup4 使用 id 获取元素

# 设定网址
url = "https://www.xyblog.cc/"

# 获取网页html 
r = req.get(url)

# 导入 html 进入 beautifulsoup4
soup = BeautifulSoup(r.text, features="html.parser")

# 使用 id 获取元素
for ele in soup.select("#main_header"):
    print(ele)

Beautifulsoup4 使用 class 获取元素

# 设定网址
url = "https://www.xyblog.cc/"

# 获取网页html 
r = req.get(url)

# 导入 html 进入 beautifulsoup4
soup = BeautifulSoup(r.text, features="html.parser")

# 使用 class 获取元素
for ele in soup.select(".mt-2"):
    print(ele)