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
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))
其他回答
# 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()
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).
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(' ', ' ')
return s
但如果文本中包含<>符号，则不会给出完整结果。
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))
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。
