用一种简单的方式

import re

html_text = open('html_file.html').read()
text_filtered = re.sub(r'<(.*?)>', '', html_text)

这段代码找到了html_text中以'<'开头，以'>'结尾的所有部分，并将所有找到的部分替换为空字符串

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

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，&#39;)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)

在Python 3中。X，你可以通过导入“imaplib”和“电子邮件”包，以非常简单的方式做到这一点。虽然这是一个老帖子，但也许我的答案可以帮助到这个帖子的新人。

status, data = self.imap.fetch(num, '(RFC822)')
email_msg = email.message_from_bytes(data[0][1]) 
#email.message_from_string(data[0][1])

#If message is multi part we only want the text version of the body, this walks the message and gets the body.

if email_msg.is_multipart():
    for part in email_msg.walk():       
        if part.get_content_type() == "text/plain":
            body = part.get_payload(decode=True) #to control automatic email-style MIME decoding (e.g., Base64, uuencode, quoted-printable)
            body = body.decode()
        elif part.get_content_type() == "text/html":
            continue

现在你可以打印主体变量，它将是明文格式:)如果它对你来说足够好，那么它将很好地选择它作为接受的答案。

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

如果您需要更高的速度和更低的准确性，那么您可以使用原始lxml。

import lxml.html as lh
from lxml.html.clean import clean_html

def lxml_to_text(html):
    doc = lh.fromstring(html)
    doc = clean_html(doc)
    return doc.text_content()