# -*- encoding:utf-8 -*-
'''
@Author : dingjiawen
@Date : 2023/11/8 16:08
@Usage :
@Desc :参考 https://github.com/Python3WebSpider/BeautifulSoupTest
'''
html = """
The Dormouse's story
The Dormouse's story
Once upon a time there were three little sisters; and their names were
,
Lacie and
Tillie;
and they lived at the bottom of a well.
...
"""
from bs4 import BeautifulSoup
def baseUse():
soup = BeautifulSoup(html, 'lxml')
print(soup.title) # The Dormouse's story
print(type(soup.title)) #
print(soup.title.string) # The Dormouse's story
print(soup.head) # The Dormouse's story
print(soup.p) # The Dormouse's story
print(soup.p.name) # 获取节点名称 p
print(soup.p.attrs) # 获取属性 {'class': ['title'], 'name': 'dromouse'}
print(soup.p.attrs['name']) # 获取属性值 dromouse
print(soup.p['name']) # 获取属性值 dromouse
print(soup.body.p['name']) # 嵌套选择 dromouse
print("==========================")
def child():
html = """
The Dormouse's story
Once upon a time there were three little sisters; and their names were
Elsie
Lacie
and
Tillie
and they lived at the bottom of a well.
...
"""
soup = BeautifulSoup(html, 'lxml')
# 子结点
for i, child in enumerate(soup.p.children):
print(i, child)
print("===============================")
# 子孙节点
for i, child in enumerate(soup.p.descendants):
print(i, child)
print("===============================")
def parent():
soup = BeautifulSoup(html, 'lxml')
# 父节点
print(soup.a.parent)
print("===============================")
# 祖父节点
print(type(soup.a.parents))
print(list(enumerate(soup.a.parents)))
print("=============================")
def brother():
html = """
Once upon a time there were three little sisters; and their names were
Elsie
Hello
Lacie
and
Tillie
and they lived at the bottom of a well.
"""
# 兄弟节点
soup = BeautifulSoup(html, 'lxml')
print('Next Sibling', soup.a.next_sibling)
print('Prev Sibling', soup.a.previous_sibling)
print('Next Siblings', list(enumerate(soup.a.next_siblings)))
print('Prev Siblings', list(enumerate(soup.a.previous_siblings)))
# 找到所有满足条件的
def findAll():
html = '''
'''
soup = BeautifulSoup(html, 'lxml')
print(soup.find_all(name='ul'))
print(type(soup.find_all(name='ul')[0]))
for ul in soup.find_all(name='ul'):
print(ul.find_all(name='li'))
for ul in soup.find_all(name='ul'):
print(ul.find_all(name='li'))
for li in ul.find_all(name='li'):
print(li.string)
# 找属性满足匹配得到
def attrs():
html = '''
'''
soup = BeautifulSoup(html, 'lxml')
print(soup.find_all(attrs={'id': 'list-1'}))
print(soup.find_all(attrs={'name': 'elements'}))
# 常用的属性可以不用attrs传递
soup = BeautifulSoup(html, 'lxml')
print(soup.find_all(id='list-1'))
print(soup.find_all(class_='element'))
import re
print(soup.find_all(string=re.compile('Foo')))# string等同于text,即里面的具体内容
# 返回匹配到的第一个元素
def find():
html = '''
'''
soup = BeautifulSoup(html, 'lxml')
print(soup.find(name='ul'))
print(type(soup.find(name='ul')))
print(soup.find(class_='list'))
# css选择器
def cssSelect():
html = '''
'''
soup = BeautifulSoup(html, 'lxml')
print(soup.select('.panel .panel-heading'))
print(soup.select('ul li'))
print(soup.select('#list-2 .element'))
print(type(soup.select('ul')[0]))
# 嵌套选择
soup = BeautifulSoup(html, 'lxml')
for ul in soup.select('ul'):
print(ul.select('li'))
# 获取属性
soup = BeautifulSoup(html, 'lxml')
for ul in soup.select('ul'):
print(ul['id'])
print(ul.attrs['id'])
# 获取文本
soup = BeautifulSoup(html, 'lxml')
for li in soup.select('li'):
print('Get Text:', li.get_text())
print('String:', li.string)
if __name__ == '__main__':
cssSelect()