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
python 3改编自søren-løvborg的回答
from html.parser import HTMLParser
from html.entities import html5
class HTMLTextExtractor(HTMLParser):
""" Adaption of http://stackoverflow.com/a/7778368/196732 """
def __init__(self):
super().__init__()
self.result = []
def handle_data(self, d):
self.result.append(d)
def handle_charref(self, number):
codepoint = int(number[1:], 16) if number[0] in (u'x', u'X') else int(number)
self.result.append(unichr(codepoint))
def handle_entityref(self, name):
if name in html5:
self.result.append(unichr(html5[name]))
def get_text(self):
return u''.join(self.result)
def html_to_text(html):
s = HTMLTextExtractor()
s.feed(html)
return s.get_text()
其他回答
这是一个类似于目前接受的答案(https://stackoverflow.com/a/925630/95989)的解决方案，除了它直接使用内部HTMLParser类(即没有子类化)，从而使它显着更简洁:
def strip_html(text):
parts = []
parser = HTMLParser()
parser.handle_data = parts.append
parser.feed(text)
return ''.join(parts)
使用HTML-Parser的解决方案都是可破坏的，如果它们只运行一次:
html_to_text('<<b>script>alert("hacked")<</b>/script>
结果:
<script>alert("hacked")</script>
你想要阻止什么。如果你使用HTML-Parser，计数标签直到0被替换:
from HTMLParser import HTMLParser
class MLStripper(HTMLParser):
def __init__(self):
self.reset()
self.fed = []
self.containstags = False
def handle_starttag(self, tag, attrs):
self.containstags = True
def handle_data(self, d):
self.fed.append(d)
def has_tags(self):
return self.containstags
def get_data(self):
return ''.join(self.fed)
def strip_tags(html):
must_filtered = True
while ( must_filtered ):
s = MLStripper()
s.feed(html)
html = s.get_data()
must_filtered = s.has_tags()
return html
import re
def remove(text):
clean = re.compile('<.*?>')
return re.sub(clean, '', text)
# 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()
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……
