import requests
from bs4 import BeautifulSoup #引入BeautifulSoup类

url = "https://python123.io/ws/demo.html"

r = requests.get(url)

print(r.status_code)

print("\n")

#demo = r.text    #html格式信息

#soup = BeautifulSoup(demo,"html.parser")#使用html.parser对demo进行html解析
soup = BeautifulSoup(open(r"C:\Users\Administrator\Desktop\beautifulsoup\demo.html"))
print(soup.prettify())

# Tag的Comment元素

from bs4 import BeautifulSoup

soup = BeautifulSoup("<b><!--This is a comment--></b><p>This is not a comment</p>","html.parser")

print(soup.b.string)
print(type(soup.b.string))

print(soup.p.string)
print(type(soup.p.string))

# 标签树的下行遍历

import requests
from bs4 import BeautifulSoup

url = "https://python123.io/ws/demo.html"

r = requests.get(url)

demo = r.text
soup = BeautifulSoup(demo,"html.parser")

'''for child in soup.body.children:  #遍历儿子节点
    print(child)
'''

for child in soup.body.descendants:  #遍历子孙节点
    print(child)

# 标签树的上行遍历

import requests
from bs4 import BeautifulSoup

url = "https://python123.io/ws/demo.html"

r = requests.get(url)

demo = r.text
soup = BeautifulSoup(demo,"html.parser")

for parent in soup.a.parents:  #遍历所有先辈节点，包括soup本身，soup的先辈不存在name信息
    if parent is None:
        print(parent)
    else:
        print(parent.name)

# 标签树的平行遍历

import requests
from bs4 import BeautifulSoup

url = "https://python123.io/ws/demo.html"

r = requests.get(url)

demo = r.text
soup = BeautifulSoup(demo,"html.parser")

for sibling in soup.a.next_sibling:
    print(sibling)                  #遍历后续节点

'''for sibling in soup.a.previous_sibling:
    print(sibling)                  #遍历前续节点
'''