我发现的最好的一段代码提取文本没有javascript或不想要的东西:

from urllib.request import urlopen
from bs4 import BeautifulSoup

url = "http://news.bbc.co.uk/2/hi/health/2284783.stm"
html = urlopen(url).read()
soup = BeautifulSoup(html, features="html.parser")

# kill all script and style elements
for script in soup(["script", "style"]):
    script.extract()    # rip it out

# get text
text = soup.get_text()

# break into lines and remove leading and trailing space on each
lines = (line.strip() for line in text.splitlines())
# break multi-headlines into a line each
chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
# drop blank lines
text = '\n'.join(chunk for chunk in chunks if chunk)

print(text)

你只需要安装BeautifulSoup:

pip install beautifulsoup4

Beautiful soup可以转换html实体。考虑到HTML经常有bug并且充满unicode和HTML编码问题，这可能是您最好的选择。这是我用来将html转换为原始文本的代码:

import BeautifulSoup
def getsoup(data, to_unicode=False):
    data = data.replace(" ", " ")
    # Fixes for bad markup I've seen in the wild.  Remove if not applicable.
    masssage_bad_comments = [
        (re.compile('<!-([^-])'), lambda match: '<!--' + match.group(1)),
        (re.compile('<!WWWAnswer T[=\w\d\s]*>'), lambda match: '<!--' + match.group(0) + '-->'),
    ]
    myNewMassage = copy.copy(BeautifulSoup.BeautifulSoup.MARKUP_MASSAGE)
    myNewMassage.extend(masssage_bad_comments)
    return BeautifulSoup.BeautifulSoup(data, markupMassage=myNewMassage,
        convertEntities=BeautifulSoup.BeautifulSoup.ALL_ENTITIES 
                    if to_unicode else None)

remove_html = lambda c: getsoup(c, to_unicode=True).getText(separator=u' ') if c else ""

下面是xperroni回答的一个版本，它更完整一些。它跳过脚本和样式部分，并翻译charref(例如，')和HTML实体(例如，&)。

它还包括一个简单的纯文本到html的反向转换器。

"""
HTML <-> text conversions.
"""
from HTMLParser import HTMLParser, HTMLParseError
from htmlentitydefs import name2codepoint
import re

class _HTMLToText(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
        self._buf = []
        self.hide_output = False

    def handle_starttag(self, tag, attrs):
        if tag in ('p', 'br') and not self.hide_output:
            self._buf.append('\n')
        elif tag in ('script', 'style'):
            self.hide_output = True

    def handle_startendtag(self, tag, attrs):
        if tag == 'br':
            self._buf.append('\n')

    def handle_endtag(self, tag):
        if tag == 'p':
            self._buf.append('\n')
        elif tag in ('script', 'style'):
            self.hide_output = False

    def handle_data(self, text):
        if text and not self.hide_output:
            self._buf.append(re.sub(r'\s+', ' ', text))

    def handle_entityref(self, name):
        if name in name2codepoint and not self.hide_output:
            c = unichr(name2codepoint[name])
            self._buf.append(c)

    def handle_charref(self, name):
        if not self.hide_output:
            n = int(name[1:], 16) if name.startswith('x') else int(name)
            self._buf.append(unichr(n))

    def get_text(self):
        return re.sub(r' +', ' ', ''.join(self._buf))

def html_to_text(html):
    """
    Given a piece of HTML, return the plain text it contains.
    This handles entities and char refs, but not javascript and stylesheets.
    """
    parser = _HTMLToText()
    try:
        parser.feed(html)
        parser.close()
    except HTMLParseError:
        pass
    return parser.get_text()

def text_to_html(text):
    """
    Convert the given text to html, wrapping what looks like URLs with <a> tags,
    converting newlines to <br> tags and converting confusing chars into html
    entities.
    """
    def f(mo):
        t = mo.group()
        if len(t) == 1:
            return {'&':'&amp;', "'":'&#39;', '"':'&quot;', '<':'&lt;', '>':'&gt;'}.get(t)
        return '<a href="%s">%s</a>' % (t, t)
    return re.sub(r'https?://[^] ()"\';]+|[&\'"<>]', f, text)

我有一个类似的问题，实际上我用了BeautifulSoup的一个答案。 问题是它真的很慢。我最终使用了一个叫做selectolax的库。 虽然它的功能很有限，但它对这个任务很有效。 唯一的问题是我手动删除了不必要的空白。 但BeautifulSoup的效果似乎要快得多。

from selectolax.parser import HTMLParser

def get_text_selectolax(html):
    tree = HTMLParser(html)

    if tree.body is None:
        return None

    for tag in tree.css('script'):
        tag.decompose()
    for tag in tree.css('style'):
        tag.decompose()

    text = tree.body.text(separator='')
    text = " ".join(text.split()) # this will remove all the whitespaces
    return text

这不是一个完全的Python解决方案，但它会将Javascript生成的文本转换为文本，我认为这是重要的(例如google.com)。浏览器Links(不是Lynx)有一个Javascript引擎，可以通过-dump选项将源代码转换为文本。

所以你可以这样做:

fname = os.tmpnam()
fname.write(html_source)
proc = subprocess.Popen(['links', '-dump', fname], 
                        stdout=subprocess.PIPE,
                        stderr=open('/dev/null','w'))
text = proc.stdout.read()

而不是HTMLParser模块，签出htmllib。它有一个类似的界面，但是为您做了更多的工作。(它非常古老，所以在摆脱javascript和css方面没有多大帮助。你可以创建一个派生类，但是可以添加start_script和end_style这样的方法(详见python文档)，但对于格式不正确的html来说，很难可靠地做到这一点。)不管怎样，这里有一些简单的东西，它将纯文本打印到控制台

from htmllib import HTMLParser, HTMLParseError
from formatter import AbstractFormatter, DumbWriter
p = HTMLParser(AbstractFormatter(DumbWriter()))
try: p.feed('hello<br>there'); p.close() #calling close is not usually needed, but let's play it safe
except HTMLParseError: print ':(' #the html is badly malformed (or you found a bug)