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
import re
def remove(text):
clean = re.compile('<.*?>')
return re.sub(clean, '', text)
其他回答
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))
我就是这么做的，但我不知道我在做什么。我通过剥离HTML标记从HTML表中获取数据。
它接受字符串“name”并返回不带HTML标记的字符串“name1”。
x = 0
anglebrackets = 0
name1 = ""
while x < len(name):
if name[x] == "<":
anglebrackets = anglebrackets + 1
if name[x] == ">":
anglebrackets = anglebrackets - 1
if anglebrackets == 0:
if name[x] != ">":
name1 = name1 + name[x]
x = x + 1
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()
如果你需要保留HTML实体(即&)，我在Eloff的答案中添加了“handle_entityref”方法。
from HTMLParser import HTMLParser
class MLStripper(HTMLParser):
def __init__(self):
self.reset()
self.fed = []
def handle_data(self, d):
self.fed.append(d)
def handle_entityref(self, name):
self.fed.append('&%s;' % name)
def get_data(self):
return ''.join(self.fed)
def html_to_text(html):
s = MLStripper()
s.feed(html)
return s.get_data()
