简单的代码!这将删除其中的所有类型的标签和内容。

def rm(s):
    start=False
    end=False
    s=' '+s
    for i in range(len(s)-1):
        if i<len(s):
            if start!=False:
                if s[i]=='>':
                    end=i
                    s=s[:start]+s[end+1:]
                    start=end=False
            else:
                if s[i]=='<':
                    start=i
    if s.count('<')>0:
        self.rm(s)
    else:
        s=s.replace('&nbsp;', ' ')
        return s

但如果文本中包含<>符号，则不会给出完整结果。

你可以使用BeautifulSoup get_text()特性。

from bs4 import BeautifulSoup

html_str = '''
<td><a href="http://www.fakewebsite.example">Please can you strip me?</a>
<br/><a href="http://www.fakewebsite.example">I am waiting....</a>
</td>
'''
soup = BeautifulSoup(html_str)

print(soup.get_text())
#or via attribute of Soup Object: print(soup.text)

建议显式地指定解析器，例如BeautifulSoup(html_str, features="html.parser")，以便输出可重现。

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"

我总是使用这个函数来剥离HTML标签，因为它只需要Python标准库:

对于Python 3:

from io import StringIO
from html.parser import HTMLParser

class MLStripper(HTMLParser):
    def __init__(self):
        super().__init__()
        self.reset()
        self.strict = False
        self.convert_charrefs= True
        self.text = StringIO()
    def handle_data(self, d):
        self.text.write(d)
    def get_data(self):
        return self.text.getvalue()

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

对于Python 2:

from HTMLParser import HTMLParser
from StringIO import StringIO

class MLStripper(HTMLParser):
    def __init__(self):
        self.reset()
        self.text = StringIO()
    def handle_data(self, d):
        self.text.write(d)
    def get_data(self):
        return self.text.getvalue()

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

我正在解析Github自述，我发现下面的工作真的很好:

import re
import lxml.html

def strip_markdown(x):
    links_sub = re.sub(r'\[(.+)\]\([^\)]+\)', r'\1', x)
    bold_sub = re.sub(r'\*\*([^*]+)\*\*', r'\1', links_sub)
    emph_sub = re.sub(r'\*([^*]+)\*', r'\1', bold_sub)
    return emph_sub

def strip_html(x):
    return lxml.html.fromstring(x).text_content() if x else ''

然后

readme = """<img src="https://raw.githubusercontent.com/kootenpv/sky/master/resources/skylogo.png" />

            sky is a web scraping framework, implemented with the latest python versions in mind (3.4+). 
            It uses the asynchronous `asyncio` framework, as well as many popular modules 
            and extensions.

            Most importantly, it aims for **next generation** web crawling where machine intelligence 
            is used to speed up the development/maintainance/reliability of crawling.

            It mainly does this by considering the user to be interested in content 
            from *domains*, not just a collection of *single pages*
            ([templating approach](#templating-approach))."""

strip_markdown(strip_html(readme))

正确移除所有markdown和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()