added chinaz spider

This commit is contained in:
Marvin Zhang
2019-05-10 12:39:10 +08:00
parent 93f9612b9b
commit 69e2e2f3c5

View File

@@ -23,5 +23,6 @@ class MongoPipeline(object):
def process_item(self, item, spider):
item['task_id'] = os.environ.get('CRAWLAB_TASK_ID')
item['_id'] = item['domain']
self.col.save(item)
if self.col.find_one({'_id': item['_id']}) is not None:
self.col.save(item)
return item