Python이 정규식을 사용하여 HTML 태그를 필터링하거나 바꾸는 방법 소개

#-*- coding:utf-8 -*-
import re
##过滤HTML中的标签
# 将HTML中标签等信息去掉
# @param htmlstr HTML字符串.
def filter_tags(htmlstr):
  # 先过滤CDATA
  re_cdata = re.compile("//<!
CDATA\[[>]∗//
\]>", re.I) #匹配CDATA
  re_script = re.compile(&#39;<\s*script[^>]*>[^<]*<\s*/\s*script\s*>&#39;, re.I) # Script
  re_style = re.compile(&#39;<\s*style[^>]*>[^<]*<\s*/\s*style\s*>&#39;, re.I) # style
  re_br = re.compile(&#39;<br\s*?/?>&#39;) # 处理换行
  re_h = re.compile(&#39;</?\w+[^>]*>&#39;) # HTML标签
  re_comment = re.compile(&#39;<!--[^>]*-->&#39;) # HTML注释
  s = re_cdata.sub(&#39;&#39;, htmlstr) # 去掉CDATA
  s = re_script.sub(&#39;&#39;, s) # 去掉SCRIPT
  s = re_style.sub(&#39;&#39;, s) # 去掉style
  s = re_br.sub(&#39;\n&#39;, s) # 将br转换为换行
  s = re_h.sub(&#39;&#39;, s) # 去掉HTML 标签
  s = re_comment.sub(&#39;&#39;, s) # 去掉HTML注释
  # 去掉多余的空行
  blank_line = re.compile(&#39;\n+&#39;)
  s = blank_line.sub(&#39;\n&#39;, s)
  s = replaceCharEntity(s) # 替换实体
  return s
##替换常用HTML字符实体.
# 使用正常的字符替换HTML中特殊的字符实体.
# 你可以添加新的实体字符到CHAR_ENTITIES中,处理更多HTML字符实体.
# @param htmlstr HTML字符串.
def replaceCharEntity(htmlstr):
  CHAR_ENTITIES = {&#39;nbsp&#39;: &#39; &#39;, &#39;160&#39;: &#39; &#39;,
           &#39;lt&#39;: &#39;<&#39;, &#39;60&#39;: &#39;<&#39;,
           &#39;gt&#39;: &#39;>&#39;, &#39;62&#39;: &#39;>&#39;,
           &#39;amp&#39;: &#39;&&#39;, &#39;38&#39;: &#39;&&#39;,
           &#39;quot&#39;: &#39;"&#39;&#39;"&#39;, &#39;34&#39;: &#39;"&#39;, }
  re_charEntity = re.compile(r&#39;?(?P<name>\w+);&#39;)
  sz = re_charEntity.search(htmlstr)
  while sz:
    entity = sz.group() # entity全称，如>
    key = sz.group(&#39;name&#39;) # 去除&;后entity,如>为gt
    try:
      htmlstr = re_charEntity.sub(CHAR_ENTITIES[key], htmlstr, 1)
      sz = re_charEntity.search(htmlstr)
    except KeyError:
      # 以空串代替
      htmlstr = re_charEntity.sub(&#39;&#39;, htmlstr, 1)
      sz = re_charEntity.search(htmlstr)
  return htmlstr
def repalce(s, re_exp, repl_string):
  return re_exp.sub(repl_string, s)
if __name__ == &#39;__main__&#39;:
  s = file(&#39;test.html&#39;).read()
  news = filter_tags(s)
  print news