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
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).
其他回答
import re
def remove(text):
clean = re.compile('<.*?>')
return re.sub(clean, '', text)
我总是使用这个函数来剥离HTML标签，因为它只需要Python标准库:
对于Python 3:
from io import StringIO
from html.parser import HTMLParser
class MLStripper(HTMLParser):
def __init__(self):
super().__init__()
self.reset()
self.strict = False
self.convert_charrefs= True
self.text = StringIO()
def handle_data(self, d):
self.text.write(d)
def get_data(self):
return self.text.getvalue()
def strip_tags(html):
s = MLStripper()
s.feed(html)
return s.get_data()
对于Python 2:
from HTMLParser import HTMLParser
from StringIO import StringIO
class MLStripper(HTMLParser):
def __init__(self):
self.reset()
self.text = StringIO()
def handle_data(self, d):
self.text.write(d)
def get_data(self):
return self.text.getvalue()
def strip_tags(html):
s = MLStripper()
s.feed(html)
return s.get_data()
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。
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。
