使用BeautifulSoup庫提取HTML頁面信息

#!/usr/bin/python3
import requests
from bs4 import BeautifulSoup

url=‘http://python123.io/ws/demo.html‘
r=requests.get(url)
if r.status_code==200:
    print(‘網絡請求成功‘)

demo=r.text
soup=BeautifulSoup(demo,‘html.parser‘)
print(soup.prettify())

BeautifulSoup類的基本屬性

#!/usr/bin/python3
import requests
from bs4 import BeautifulSoup

url=‘http://python123.io/ws/demo.html‘
r=requests.get(url)
if r.status_code==200:
    print(‘網絡請求成功‘)

demo=r.text
soup=BeautifulSoup(demo,‘html.parser‘)
tag_title=soup.title
print(tag_title)
tag_a_attrs=soup.a.attrs
print(soup.p.
 
string)