The method of python to html filtering
- 2021-01-02 21:53:59
- OfStack
As shown below:
## filter HTML In the label
# will HTML Remove tags and other information from
#@param htmlstr HTML string .
def filter_tags(htmlstr):
# To filter CDATA
re_cdata=re.compile('//<!\[CDATA\[[^>]*//\]\]>',re.I) # matching CDATA
re_script=re.compile('<\s*script[^>]*>[^<]*<\s*/\s*script\s*>',re.I)#Script
re_style=re.compile('<\s*style[^>]*>[^<]*<\s*/\s*style\s*>',re.I)#style
re_br=re.compile('<br\s*?/?>')# Processing line
re_h=re.compile('</?\w+[^>]*>')#HTML The label
re_comment=re.compile('<!--[^>]*-->')#HTML annotation
re_stopwords=re.compile('\u3000')# Remove useless '\u3000' character
s=re_cdata.sub('',htmlstr)# To get rid of CDATA
s=re_script.sub('',s) # To get rid of SCRIPT
s=re_style.sub('',s)# To get rid of style
s=re_br.sub('\n',s)# will br Convert to newline
s=re_h.sub('',s) # To get rid of HTML The label
s=re_comment.sub('',s)# To get rid of HTML annotation
s=re_stopwords.sub('',s)
# Remove excess blank lines
blank_line=re.compile('\n+')
s=blank_line.sub('\n',s)
s=replaceCharEntity(s)# Replace the entity
return s
## Replace the commonly used HTML Character entities .
# Use the normal character substitution HTML A special character entity in .
# You can add new entity characters to CHAR_ENTITIES In the , Deal with more HTML Character entities .
#@param htmlstr HTML string .
def replaceCharEntity(htmlstr):
CHAR_ENTITIES={'nbsp':' ','160':' ',
'lt':'<','60':'<',
'gt':'>','62':'>',
'amp':'&','38':'&',
'quot':'"','34':'"',}
re_charEntity=re.compile(r'&#?(?P<name>\w+);')
sz=re_charEntity.search(htmlstr)
while sz:
entity=sz.group()#entity The full name, such as >
key=sz.group('name')# Get rid of &; after entity, Such as > for gt
try:
htmlstr=re_charEntity.sub(CHAR_ENTITIES[key],htmlstr,1)
sz=re_charEntity.search(htmlstr)
except KeyError:
# Empty string instead
htmlstr=re_charEntity.sub('',htmlstr,1)
sz=re_charEntity.search(htmlstr)
return htmlstr