700字范文 > python 正则表达式过滤文本中的html标签源代码解析

python 正则表达式过滤文本中的html标签源代码解析

时间：2020-06-02 07:06:32

#py2.7#coding:utf-8import reimport osimport chardetdef filter_tag(htmlstr):re_cdata = pile('<!DOCTYPE HTML PUBLIC[^>]*>', re.I)re_script = pile('<\s*script[^>]*>[^<]*<\s*/\s*script\s*>', re.I) #过滤脚本re_style = pile('<\s*style[^>]*>[^<]*<\s*/\s*style\s*>', re.I) #过滤stylere_br = pile('<br\s*?/?>')re_h = pile('</?\w+[^>]*>')re_comment = pile('')s = re_cdata.sub('', htmlstr)s = re_script.sub('', s)s=re_style.sub('',s)s=re_br.sub('\n',s)s=re_h.sub(' ',s)s=re_comment.sub('',s)blank_line=pile('\n+')s=blank_line.sub('\n',s)s=re.sub('\s+',' ',s)s=replaceCharEntity(s)return sdef replaceCharEntity(htmlstr):CHAR_ENTITIES={'nbsp':'','160':'','lt':'<','60':'<','gt':'>','62':'>','amp':'&','38':'&','quot':'"','34':'"'}re_charEntity=pile(r'&#?(?P<name>\w+);') #命名组,把匹配字段中\w+的部分命名为name,可以用group函数获取sz=re_charEntity.search(htmlstr)while sz:#entity=sz.group()key=sz.group('name') #命名组的获取try:htmlstr=re_charEntity.sub(CHAR_ENTITIES[key],htmlstr,1) #1表示替换第一个匹配sz=re_charEntity.search(htmlstr)except KeyError:htmlstr=re_charEntity.sub('',htmlstr,1)sz=re_charEntity.search(htmlstr)return htmlstrif __name__=='__main__':cpath=os.getcwd()for root,dirs,files in os.walk(cpath):for file in files:if file.endswith('htm') or file.endswith('html'):f=open(root+os.path.sep+file)stream=f.read()htmlstr =stream.decode(chardet.detect(stream)['encoding'])rs=filter_tag(htmlstr)f.close()txtname=re.sub(r'.htm*$','.txt',file)print txtnamef=open(root+os.path.sep+txtname,'w')f.write(rs.encode('utf-8'))f.close()