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
2020年更新
使用Mozilla Bleach库，它确实允许您自定义保留哪些标记和保留哪些属性，并且还可以根据值过滤属性
这里有两个例子来说明
1)不允许任何HTML标签或属性
获取原始文本样本
raw_text = """
<p><img width="696" height="392" src="https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-768x432.jpg" class="attachment-medium_large size-medium_large wp-post-image" alt="Ethereum Classic 51% Attack: Okex Crypto Exchange Suffers $5.6 Million Loss, Contemplates Delisting ETC" style="float:left; margin:0 15px 15px 0;" srcset="https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-768x432.jpg 768w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-300x169.jpg 300w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-1024x576.jpg 1024w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-696x392.jpg 696w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-1068x601.jpg 1068w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-747x420.jpg 747w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-190x107.jpg 190w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-380x214.jpg 380w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-760x428.jpg 760w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc.jpg 1280w" sizes="(max-width: 696px) 100vw, 696px" />Cryptocurrency exchange Okex reveals it suffered the $5.6 million loss as a result of the double-spend carried out by the attacker(s) in Ethereum Classic 51% attack. Okex says it fully absorbed the loss as per its user-protection policy while insisting that the attack did not cause any loss to the platform’s users. Also as part […]</p>
<p>The post <a rel="nofollow" href="https://news.bitcoin.com/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc/">Ethereum Classic 51% Attack: Okex Crypto Exchange Suffers $5.6 Million Loss, Contemplates Delisting ETC</a> appeared first on <a rel="nofollow" href="https://news.bitcoin.com">Bitcoin News</a>.</p>
"""
2)从原始文本中删除所有HTML标签和属性
# DO NOT ALLOW any tags or any attributes
from bleach.sanitizer import Cleaner
cleaner = Cleaner(tags=[], attributes={}, styles=[], protocols=[], strip=True, strip_comments=True, filters=None)
print(cleaner.clean(raw_text))
输出
Cryptocurrency exchange Okex reveals it suffered the $5.6 million loss as a result of the double-spend carried out by the attacker(s) in Ethereum Classic 51% attack. Okex says it fully absorbed the loss as per its user-protection policy while insisting that the attack did not cause any loss to the platform’s users. Also as part […]
The post Ethereum Classic 51% Attack: Okex Crypto Exchange Suffers $5.6 Million Loss, Contemplates Delisting ETC appeared first on Bitcoin News.
3只允许带有srcset属性的img标签
from bleach.sanitizer import Cleaner
# ALLOW ONLY img tags with src attribute
cleaner = Cleaner(tags=['img'], attributes={'img': ['srcset']}, styles=[], protocols=[], strip=True, strip_comments=True, filters=None)
print(cleaner.clean(raw_text))
输出
<img srcset="https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-768x432.jpg 768w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-300x169.jpg 300w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-1024x576.jpg 1024w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-696x392.jpg 696w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-1068x601.jpg 1068w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-747x420.jpg 747w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-190x107.jpg 190w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-380x214.jpg 380w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc-760x428.jpg 760w, https://news.bitcoin.com/wp-content/uploads/2020/08/ethereum-classic-51-attack-okex-crypto-exchange-suffers-5-6-million-loss-contemplates-delisting-etc.jpg 1280w">Cryptocurrency exchange Okex reveals it suffered the $5.6 million loss as a result of the double-spend carried out by the attacker(s) in Ethereum Classic 51% attack. Okex says it fully absorbed the loss as per its user-protection policy while insisting that the attack did not cause any loss to the platform’s users. Also as part […]
The post Ethereum Classic 51% Attack: Okex Crypto Exchange Suffers $5.6 Million Loss, Contemplates Delisting ETC appeared first on Bitcoin News.
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>(¬ \u0394ημώ)</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('<script>alert("Hello");</script>')
'<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 < z <!--b')
'x < y < z '
Named entities are handled as per HTML 5.
>>> html_to_text('&nosuchentity; ' ')
"&nosuchentity; ' "
"""
s = HTMLTextExtractor()
s.feed(html)
return s.get_text()
快速测试:
html = '<a href="#">Demo <em>(¬ \u0394ημώ)</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>警报(“Hello”);& lt; / script>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)
基于lxml.html的解决方案(lxml是一个原生库，比纯python解决方案性能更好)。
要安装lxml模块，使用pip install lxml
移除所有标签
from lxml import html
## from file-like object or URL
tree = html.parse(file_like_object_or_url)
## from string
tree = html.fromstring('safe <script>unsafe</script> safe')
print(tree.text_content().strip())
### OUTPUT: 'safe unsafe safe'
删除预消毒HTML的所有标签(删除一些标签)
from lxml import html
from lxml.html.clean import clean_html
tree = html.fromstring("""<script>dangerous</script><span class="item-summary">
Detailed answers to any questions you might have
</span>""")
## text only
print(clean_html(tree).text_content().strip())
### OUTPUT: 'Detailed answers to any questions you might have'
还请参阅http://lxml.de/lxmlhtml.html#cleaning-up-html了解lxml. xml的具体内容。清洁。
如果你需要更多的控制哪些特定的标签应该在转换为文本之前删除，然后创建一个自定义的lxml Cleaner与所需的选项，例如:
cleaner = Cleaner(page_structure=True,
meta=True,
embedded=True,
links=True,
style=True,
processing_instructions=True,
inline_style=True,
scripts=True,
javascript=True,
comments=True,
frames=True,
forms=True,
annoying_tags=True,
remove_unknown_tags=True,
safe_attrs_only=True,
safe_attrs=frozenset(['src','color', 'href', 'title', 'class', 'name', 'id']),
remove_tags=('span', 'font', 'div')
)
sanitized_html = cleaner.clean_html(unsafe_html)
要自定义如何生成纯文本，您可以使用lxml.etree.tostring而不是text_content():
from lxml.etree import tostring
print(tostring(tree, method='text', encoding=str))
使用BeautifulSoup, html2text或来自@Eloff的代码，大多数时候，它仍然是一些html元素，javascript代码…
所以你可以使用这些库的组合并删除markdown格式(Python 3):
import re
import html2text
from bs4 import BeautifulSoup
def html2Text(html):
def removeMarkdown(text):
for current in ["^[ #*]{2,30}", "^[ ]{0,30}\d\\\.", "^[ ]{0,30}\d\."]:
markdown = re.compile(current, flags=re.MULTILINE)
text = markdown.sub(" ", text)
return text
def removeAngular(text):
angular = re.compile("[{][|].{2,40}[|][}]|[{][*].{2,40}[*][}]|[{][{].{2,40}[}][}]|\[\[.{2,40}\]\]")
text = angular.sub(" ", text)
return text
h = html2text.HTML2Text()
h.images_to_alt = True
h.ignore_links = True
h.ignore_emphasis = False
h.skip_internal_links = True
text = h.handle(html)
soup = BeautifulSoup(text, "html.parser")
text = soup.text
text = removeAngular(text)
text = removeMarkdown(text)
return text
这对我来说很有效，但当然还可以增强……
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(" ", " ") ## Get rid of the remnants of certain formatting(subscript,superscript,etc).
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()
