I am hoping to write a script that will go through a directory and check if the html files are badly formed. Please see my code
directory = "html"
for root, dirs, files in os.walk(directory):
for file in files:
if str(file).endswith('.html'):
#Help needed here
if file is badly formed:
print "Badly Formed"
else:
print "Well Formed"
import xml.etree.ElementTree as ETree
....
try:
self.doc = ETree.parse( file )
# do stuff with it ...
except ETree.ParseError :
print( "ERROR in {0} : {1}".format( ETree.ParseError.filename, ETree.ParseError.msg ) )