这段代码可能对某些人有用，
def parsefile(path):
try:
file = open(path, "r")
fileread = file.read()
fileread = unescape(fileread.decode('utf-8')).encode('utf-8')
file.close()
except:
print "Reading File Bug"
sys.exit(1)
return ET.fromstring(fileread)
该吃UNESCAPE HTML实体程序已于弗雷德里克Lundh开发网站上找到。代码做得太多了，因为它正在转换&，& gt;而且<。我希望将这些保存在URL中以及我已转义代码段的位置。所以我稍微修改了它以满足我自己的需要。
def unescape(text):
"""Removes HTML or XML character references
and entities from a text string.
keep &，& gt; <in the source code.
from Fredrik Lundh
http://effbot.org/zone/re-sub.htm#unescape-html
"""
def fixup(m):
text = m.group(0)
if text[:2] == "&#":
# character reference
try:
if text[:3] == "&#x":
return unichr(int(text[3:-1], 16))
else:
return unichr(int(text[2:-1]))
except ValueError:
print "erreur de valeur"
pass
else:
# named entity
try:
if text[1:-1] == "amp":
text = "&"
elif text[1:-1] == "gt":
text = ">"
elif text[1:-1] == "lt":
text = "<"
else:
print text[1:-1]
text = unichr(htmlentitydefs.name2codepoint])
except KeyError:
print "keyerror"
pass
return text # leave as is
return re.sub("&#?w+;", fixup, text)
希望能帮助到你。
