Python-BeautifulSoup用法详解

import requests
import re

r = requests.get("http://python123.io/ws/demo.html")
demo = r.text

from bs4 import BeautifulSoup
soup = BeautifulSoup(demo, "html.parser")
print(soup.prettify())
print("----------------打印匹配b的标签名-------------------------")
for tag in soup.find_all(re.compile('b')):
    print(tag.name)
print("----------------打印所有的标签名-------------------------")
for tag in soup.find(True):
    print(tag.name)

print(soup.find_all('p', 'course'))
print(soup.find_all(id='link1'))
print(soup.find_all(id='link')) # 匹配link
print(soup.find_all(id=re.compile('link'))) # 匹配link*
print(soup.find_all('a', recursive=False))   # 
print(soup.find_all(string = "Basic Python"))   # 匹配字符串为Basic Python的标签
print(soup.find_all(string = re.compile("Python"))) # 匹配字符串带有Python的标签