html_doc = """ <html><head><title>The Dormouse's story</title></head> <body> <p class="title"><b>The Dormouse's story</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> """
#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 html_doc = """ <html><head><title>The Dormouse's story</title></head> <body> <p id="my p" class="title"><b id="bbb" class="boldest">The Dormouse's story</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> """
#1、用法 from bs4 import BeautifulSoup soup=BeautifulSoup(html_doc,'lxml') # soup=BeautifulSoup(open('a.html'),'lxml')
#4、获取标签的内容 print(soup.p.string) # p下的文本只有一个时,取到,否则为None print(soup.p.strings) #拿到一个生成器对象, 取到p下所有的文本内容 print(soup.p.text) #取到p下所有的文本内容 for line in soup.stripped_strings: #去掉空白 print(line)
#搜索文档树:BeautifulSoup定义了很多搜索方法,这里着重介绍2个: find() 和 find_all() .其它方法的参数和用法类似 html_doc = """ <html><head><title>The Dormouse's story</title></head> <body> <p id="my p" class="title"><b id="bbb" class="boldest">The Dormouse's story</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> """
from bs4 import BeautifulSoup soup=BeautifulSoup(html_doc,'lxml')
#该模块提供了select方法来支持css,详见官网:https://www.crummy.com/software/BeautifulSoup/bs4/doc/index.zh.html#id37 html_doc = """ <html><head><title>The Dormouse's story</title></head> <body> <p class="title"> <b>The Dormouse's story</b> Once upon a time there were three little sisters; and their names were <a href="http://example.com/elsie" class="sister" id="link1"> <span>Elsie</span> </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>; <div class='panel-1'> <ul class='list' id='list-1'> <li class='element'>Foo</li> <li class='element'>Bar</li> <li class='element'>Jay</li> </ul> <ul class='list list-small' id='list-2'> <li class='element'><h1 class='yyyy'>Foo</h1></li> <li class='element xxx'>Bar</li> <li class='element'>Jay</li> </ul> </div> and they lived at the bottom of a well. </p> <p class="story">...</p> """ from bs4 import BeautifulSoup soup=BeautifulSoup(html_doc,'lxml')