from mechanize import Browser
br = Browser()
br.open('http://somewebpage')
html = br.response().readlines()
for line in html:
  print line

当在HTML文件中打印一行时,我试图找到一种方法,只显示每个HTML元素的内容,而不是格式本身。如果它发现'<a href="等等。例如">some text</a>',它只会打印'some text', '<b>hello</b>'打印'hello',等等。该怎么做呢?


当前回答

# This is a regex solution.
import re
def removeHtml(html):
  if not html: return html
  # Remove comments first
  innerText = re.compile('<!--[\s\S]*?-->').sub('',html)
  while innerText.find('>')>=0: # Loop through nested Tags
    text = re.compile('<[^<>]+?>').sub('',innerText)
    if text == innerText:
      break
    innerText = text

  return innerText.strip()

其他回答

我需要一种方法来剥离标签和解码HTML实体为纯文本。下面的解决方案是基于Eloff的答案(我不能使用,因为它剥离实体)。

import html.parser

class HTMLTextExtractor(html.parser.HTMLParser):
    def __init__(self):
        super(HTMLTextExtractor, self).__init__()
        self.result = [ ]

    def handle_data(self, d):
        self.result.append(d)

    def get_text(self):
        return ''.join(self.result)

def html_to_text(html):
    """Converts HTML to plain text (stripping tags and converting entities).
    >>> html_to_text('<a href="#">Demo<!--...--> <em>(&not; \u0394&#x03b7;&#956;&#x03CE;)</em></a>')
    'Demo (\xac \u0394\u03b7\u03bc\u03ce)'

    "Plain text" doesn't mean result can safely be used as-is in HTML.
    >>> html_to_text('&lt;script&gt;alert("Hello");&lt;/script&gt;')
    '<script>alert("Hello");</script>'

    Always use html.escape to sanitize text before using in an HTML context!

    HTMLParser will do its best to make sense of invalid HTML.
    >>> html_to_text('x < y &lt z <!--b')
    'x < y < z '

    Named entities are handled as per HTML 5.
    >>> html_to_text('&nosuchentity; &apos; ')
    "&nosuchentity; ' "
    """
    s = HTMLTextExtractor()
    s.feed(html)
    return s.get_text()

快速测试:

html = '<a href="#">Demo <em>(&not; \u0394&#x03b7;&#956;&#x03CE;)</em></a>'
print(repr(html_to_text(html)))

结果:

'Demo (¬ Δημώ)'

安全提示:不要混淆HTML剥离(将HTML转换为纯文本)和HTML消毒(将纯文本转换为HTML)。这个答案将删除HTML并将实体解码为纯文本——这并不能使结果在HTML上下文中安全使用。

例子:& lt; script&gt警报(“Hello”);& lt; / script&gt;将转换为<script>alert("Hello");</script>,这是100%正确的行为,但如果结果纯文本按原样插入到HTML页面中,显然是不够的。

这个规则并不难:任何时候你插入一个纯文本字符串到HTML输出,总是HTML转义它(使用HTML .escape(s)),即使你“知道”它不包含HTML(例如,因为你剥离了HTML内容)。

但是,OP询问是否将结果打印到控制台,在这种情况下不需要HTML转义。相反,你可能想要剥离ASCII控制字符,因为它们会触发不需要的行为(特别是在Unix系统上):

import re
text = html_to_text(untrusted_html_input)
clean_text = re.sub(r'[\0-\x1f\x7f]+', '', text)
# Alternatively, if you want to allow newlines:
# clean_text = re.sub(r'[\0-\x09\x0b-\x1f\x7f]+', '', text)
print(clean_text)

这个方法对我来说完美无缺,不需要额外的安装:

import re
import htmlentitydefs

def convertentity(m):
    if m.group(1)=='#':
        try:
            return unichr(int(m.group(2)))
        except ValueError:
            return '&#%s;' % m.group(2)
        try:
            return htmlentitydefs.entitydefs[m.group(2)]
        except KeyError:
            return '&%s;' % m.group(2)

def converthtml(s):
    return re.sub(r'&(#?)(.+?);',convertentity,s)

html =  converthtml(html)
html.replace("&nbsp;", " ") ## Get rid of the remnants of certain formatting(subscript,superscript,etc).

这是一个快速修复,甚至可以更优化,但它将工作良好。这段代码将用""替换所有非空标记,并从给定的输入文本中剥离所有html标记。你可以使用./file.py输入输出运行它

    #!/usr/bin/python
import sys

def replace(strng,replaceText):
    rpl = 0
    while rpl > -1:
        rpl = strng.find(replaceText)
        if rpl != -1:
            strng = strng[0:rpl] + strng[rpl + len(replaceText):]
    return strng


lessThanPos = -1
count = 0
listOf = []

try:
    #write File
    writeto = open(sys.argv[2],'w')

    #read file and store it in list
    f = open(sys.argv[1],'r')
    for readLine in f.readlines():
        listOf.append(readLine)         
    f.close()

    #remove all tags  
    for line in listOf:
        count = 0;  
        lessThanPos = -1  
        lineTemp =  line

            for char in lineTemp:

            if char == "<":
                lessThanPos = count
            if char == ">":
                if lessThanPos > -1:
                    if line[lessThanPos:count + 1] != '<>':
                        lineTemp = replace(lineTemp,line[lessThanPos:count + 1])
                        lessThanPos = -1
            count = count + 1
        lineTemp = lineTemp.replace("&lt","<")
        lineTemp = lineTemp.replace("&gt",">")                  
        writeto.write(lineTemp)  
    writeto.close() 
    print "Write To --- >" , sys.argv[2]
except:
    print "Help: invalid arguments or exception"
    print "Usage : ",sys.argv[0]," inputfile outputfile"

使用HTML-Parser的解决方案都是可破坏的,如果它们只运行一次:

html_to_text('<<b>script>alert("hacked")<</b>/script>

结果:

<script>alert("hacked")</script>

你想要阻止什么。如果你使用HTML-Parser,计数标签直到0被替换:

from HTMLParser import HTMLParser

class MLStripper(HTMLParser):
    def __init__(self):
        self.reset()
        self.fed = []
        self.containstags = False

    def handle_starttag(self, tag, attrs):
       self.containstags = True

    def handle_data(self, d):
        self.fed.append(d)

    def has_tags(self):
        return self.containstags

    def get_data(self):
        return ''.join(self.fed)

def strip_tags(html):
    must_filtered = True
    while ( must_filtered ):
        s = MLStripper()
        s.feed(html)
        html = s.get_data()
        must_filtered = s.has_tags()
    return html

对于一个项目,我需要这样剥离HTML,但也css和js。因此,我对eloff的回答做了一个变化:

class MLStripper(HTMLParser):
    def __init__(self):
        self.reset()
        self.strict = False
        self.convert_charrefs= True
        self.fed = []
        self.css = False
    def handle_starttag(self, tag, attrs):
        if tag == "style" or tag=="script":
            self.css = True
    def handle_endtag(self, tag):
        if tag=="style" or tag=="script":
            self.css=False
    def handle_data(self, d):
        if not self.css:
            self.fed.append(d)
    def get_data(self):
        return ''.join(self.fed)

def strip_tags(html):
    s = MLStripper()
    s.feed(html)
    return s.get_data()