def _decode_htmlescapes(self, s):
"""Unescape HTML code."""
# In case of bad formated html you can import MinimalSoup etc.. see btflsoup source code
from bs4 import BeautifulSoup as btflsoup
# my sm2004 also ecaped & char in escaped sequences.
s = re.sub("&", "&", s)
# unescaped solitary chars < or > that were ok for minidom confuse btfl soup
# s = re.sub(u'>',u'>',s)
# s = re.sub(u'<',u'<',s)
return str(btflsoup(s, "html.parser"))
def _decode_htmlescapes(self,s):
"""Unescape HTML code."""
#In case of bad formated html you can import MinimalSoup etc.. see btflsoup source code
from bs4 import BeautifulSoup as btflsoup
#my sm2004 also ecaped & char in escaped sequences.
s = re.sub('&','&',s)
#unescaped solitary chars < or > that were ok for minidom confuse btfl soup
#s = re.sub(u'>',u'>',s)
#s = re.sub(u'<',u'<',s)
return str(btflsoup(s, "html.parser"))
def _decode_htmlescapes(self,s):
"""Unescape HTML code."""
#In case of bad formated html you can import MinimalSoup etc.. see btflsoup source code
from bs4 import BeautifulStoneSoup as btflsoup
#my sm2004 also ecaped & char in escaped sequences.
s = re.sub(u'&',u'&',s)
#unescaped solitary chars < or > that were ok for minidom confuse btfl soup
s = re.sub(u'>',u'>',s)
s = re.sub(u'<',u'<',s)
return unicode(btflsoup(s,convertEntities=btflsoup.HTML_ENTITIES ))
