def parseLine(line):
pos = [m.start() for m in re.finditer("\t", line)]
if len(pos) < 4:
Utils.error("len(pos)<4")
url = line[0:pos[0]]
category = line[pos[0] + 1:pos[1]]
subcategory = line[pos[1] + 1:pos[2]]
title = line[pos[2] + 1:pos[3]]
if len(pos) > 4:
content = line[pos[3] + 1:pos[4]]
else:
content = line[pos[3] + 1:]
#
url = url.strip()
category = category.strip()
title = title.strip()
content = content.strip()
subcategory = subcategory.strip()
return category, url, title, content, subcategory
