from bs4 import BeautifulSoup
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b>The Dormouse's story<span>lqz</span></b><b>adfasdf<b></p>
<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>
<p class="story">...</p>
"""
soup = BeautifulSoup(html_doc, 'lxml')
# print(soup.prettify())
# 遍历 搜索
###遍历文档树
# 遍历文档树:即直接通过标签名字选择,特点是选择速度快,但如果存在多个相同的标签则只返回第一个
# 1、用法 通过 . 遍历
# a=soup.html.body.a
# a=soup.a
# print(a)
# 2、获取标签的名称
# soup.a 对象
# a=soup.a.name
# print(a)
# 3、获取标签的属性
# a=soup.a.attrs
# a=soup.a.attrs.get('id')
# print(a)
# a=soup.a.attrs.get('href')
# print(a)
# 4、获取标签的内容---文本内容
# p=soup.p.text # text 会把当前标签的子子孙孙的文本内容都拿出来,拼到一起
# print(p)
# s1=soup.p.string # 当前标签有且只有自己(没有子标签),把文本内容拿出来
# print(s1)
# s1=list(soup.p.strings) #generator 把子子孙孙的文本内容放到生成器中
# print(s1)
# 5、嵌套选择 . 完后可以继续再 .
# print(soup.head.title.text)
# # 6、子节点、子孙节点
# print(soup.p.contents) # p下所有直接子节点
# print(list(soup.p.children)) # 得到一个迭代器,包含p下所有直接子节点
# print(list(soup.p.descendants)) #
# 7、父节点、祖先节点
# print(soup.a.parent) #获取a标签的父节点
# print(list(soup.a.parents)) #找到a标签所有的祖先节点,父亲的父亲,父亲的父亲的父亲...
# 8、兄弟节点
# print(soup.a.next_sibling) #下一个兄弟
# print(soup.a.previous_sibling) #上一个兄弟
# print(list(soup.a.next_siblings)) #下面的兄弟们=>生成器对象
# print(list(soup.a.previous_siblings)) #上面的兄弟们=>生成器对象
css选择器
from bs4 import BeautifulSoup
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b class ='baby'>The Dormouse's story<span>lqz</span></b><b>adfasdf<b></p>
<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" id="link1" xx="xx">Elsie</a>
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3" name="zzz">Tillie</a>;
and they lived at the bottom of a well.</p>
<p class="story">...</p>
"""
soup = BeautifulSoup(html_doc, 'lxml')
# css选择器
'''
div
.类名
#id号
div a # div下的子子孙孙中得a
div>a #div直接子节点
'''
# res=soup.select('.sister')
# res=soup.select('#link1')
# res=soup.p.find(name='b').select('span')
# print(res)
# 以后,基本所有的解析器都会支持两种解析:css,xpath,都可以去页面中复制
import requests
res=requests.get('http://it028.com/css-selectors.html')
# res.encoding=res.apparent_encoding
res.encoding='utf-8'
# print(res.text)
soup=BeautifulSoup(res.text,'lxml')
res=soup.select('#content > table > tbody > tr:nth-child(14) > td:nth-child(3)')
# //*[@id="content"]/table/tbody/tr[14]/td[3]
print(res)