def __getValue(self,url):
isHaveManyQueryInUrl = False
for value in self.valuedict:
div_by_value = url.split(value.rstrip('\n'))
mm = div_by_value[0]
if mm in self.seen:
raise DropItem('Duplicate link %s' % url)
elif len(div_by_value) > 1 and not isHaveManyQueryInUrl:
self.seen.add(mm)
isHaveManyQueryInUrl = True
line = url+'\n'
print url
self.file.write(line)
评论列表
文章目录