引用codecs模块,来判断前三个字节是否为BOM_UTF8。如果是,则剔除\xef\xbb\xbf字节
import codecs
def download_ipurl(self,destpath):
try:
f = open(destpath,'r')
iter_f = iter(f)
lines = 0
for ipurl in iter_f:
lines = lines + 1
if ipurl[0:3] == codecs.BOM_UTF8:
self.newipurls.add((ipurl.rstrip('\r\n')).lstrip('\xef\xbb\xbf'))
#print self.newipurls
#log记录读取了多少行IP url
#print lines
finally:
if f:
f.close()