问答博客标签用户活动
logo极客观点logo项目管理logoHarmonyOS
javascript
php
java
vue.js
git
html5
python
node.js
android
mysql
react.js
linux
ios
css
golang
spring
docker
程序员
logoONES 研发管理logo思否企业问答logo安谋科技 XPU

python中怎么获取某个网页元素之前的所有源码?

头像
smfsir
    14933145
    <html>
    <head>
        <title>The Dormouse's story </title>
    </head> 
    <body> 
        <p id="p1">p1p1p1
            <b id='b1'>b1b1b1</b>
        </p> 
        <p id="p2">p2p2p2
            <ul id='u1'>u1u1u1</ul>
            <a id="a1">a1a1a1</a>
            <div id='d1'>
                <a id="a2">a2a2a2 </a>
                <b id='b2'>b2b2b2</b>
                <p id='p3'>p3p3p3</p>
            </div>
            <a id="a3">a3a3a3 </a>
        </p> 
        <p id="p4">p4p4p4</p>
    </body>
</html>

    比如第一个a元素:a#a1,要获取这个元素以上的所有网页源码:

    <html>
    <head>
        <title>The Dormouse's story </title>
    </head> 
    <body> 
        <p id="p1">p1p1p1
            <b id='b1'>b1b1b1</b>
        </p> 
        <p id="p2">p2p2p2
            <ul id='u1'>u1u1u1</ul>
            <a id="a1">a1a1a1</a>
        </p>
    </body>
</html>
    pythonhtml
    阅读 6.9k
    5 个回答
    得票最新
    头像
    同意并接受
      7.2k21127
      ✓ 已被采纳

      由于你原来的html不合规范，我改了点。
      下面是用 lxml 做的。

      doc = '''
<html>
    <head>
        <title>The Dormouse's story </title>
    </head> 
    <body> 
        <p id="p1">p1p1p1
            <b id='b1'>b1b1b1</b>
        </p> 
        <p id="p2">p2p2p2</p>
        <div id='d1'>
            <ul id='u1'>u1u1u1</ul>
            <a id="a1">a1a1a1</a>
            <div id='d2'>
                <a id="a2">a2a2a2 </a>
                <b id='b2'>b2b2b2</b>
                <p id='p3'>p3p3p3</p>
            </div>
            <a id="a3">a3a3a3 </a>
        </div> 
        <p id="p4">p4p4p4</p>
    </body>
</html>
'''

from lxml import html

tree = html.fromstring(doc)
a = tree.get_element_by_id("a1")
print(html.tostring(a))
print(html.tostring(tree).decode())

def dropnode(e=None):
    if e is None: return
    if e.tag == 'body': return
    nd = e.getnext()
    while nd is not None:
        nd.drop_tree()
        nd = e.getnext()
    dropnode(e.getparent())

dropnode(a)
print(html.tostring(tree).decode())
      头像
      deeplearn
        251

        使用bs4去提取

        头像
        smfsir
          14933145
          from bs4 import BeautifulSoup as bs

def dropAllNextEle(eleOfBS, returnTrueOrFalseToKeepOrDropEleFunc = None):
    # 删除ele元素之后的所有节点元素(其实就是递归删除eleOfBS及由近及远历代父元素的兄弟元素);第二个参数是个函数,以第一个参数的各级兄弟元素为参数,返回true,保留ele,否则删除ele.
    if eleOfBS is None: return
    if eleOfBS.name == 'body': return
    next_siblings = eleOfBS.next_siblings
    if next_siblings:
        next_siblings_list = []
        for item in next_siblings:
            if item:
                next_siblings_list.insert(0, item)

        for item in next_siblings_list:
            if returnTrueOrFalseToKeepOrDropEleFunc:
                if not returnTrueOrFalseToKeepOrDropEleFunc(item):
                    item.replace_with('')
            else:
                item.replace_with('')

        dropAllNextEle(eleOfBS.parent, returnTrueOrFalseToKeepOrDropEleFunc)
    else:
        dropAllNextEle(eleOfBS.parent, returnTrueOrFalseToKeepOrDropEleFunc)
        
soup = bs(html_source, 'html5lib')
a1_ele = soup.find('a', id = 'a1')
dropAllNextEle(a1_ele, lambda item: type(item) == type(soup.new_string('strstr')))
print soup
          头像
          here小可
            4214

            新手,我只学了re模块，所以只用re模块+普通方式来提取

            >>> html = '''
<html>
    <head>
        <title>The Dormouse's story </title>
    </head> 
    <body> 
        <p id="p1">p1p1p1
            <b id='b1'>b1b1b1</b>
        </p> 
        <p id="p2">p2p2p2
            <ul id='u1'>u1u1u1</ul>
            <a id="a1">a1a1a1</a>
            <div id='d1'>
                <a id="a2">a2a2a2 </a>
                <b id='b2'>b2b2b2</b>
                <p id='p3'>p3p3p3</p>
            </div>
            <a id="a3">a3a3a3 </a>
        </p> 
        <p id="p4">p4p4p4</p>
    </body>
</html>
'''
>>> html_1 = re.search(r'<a',html)
>>> html_1 = html_1.span()
>>> print(html[:html_1[0]])

<html>
    <head>
        <title>The Dormouse's story </title>
    </head> 
    <body> 
        <p id="p1">p1p1p1
            <b id='b1'>b1b1b1</b>
        </p> 
        <p id="p2">p2p2p2
            <ul id='u1'>u1u1u1</ul>
            
>>>
            头像
            angellaugh
              31312

              be模块最顺手

              撰写回答
              你尚未登录，登录后可以
              • 和开发者交流问题的细节
              • 关注并接收问题和回答的更新提醒
              • 参与内容的编辑和改进，让解决方法与时俱进
              被 1 篇内容引用
              推荐问题
              宣传栏