Question

所以我的问题是信息被刮掉了，不会出现在数据库中。

我的蜘蛛可以很好地打印出信息，例如在.json文件中。

pipelines.py

import sys
import MySQLdb
import hashlib
from scrapy.exceptions import DropItem
from scrapy.http import Request

class MySQLStorePipeline(object):
  def __init__(self):
   self.conn = MySQLdb.connect(host="10.0.2.2", user='root', passwd='', db='mpmf', charset="utf8", use_unicode=True)
   self.cursor = self.conn.cursor()

def process_item(self, item, stack):    
    try:
        self.cursor.execute("""INSERT INTO test (pen, name)  
                    VALUES (%s, %s)""", 
                   (item['pen'].encode('utf-8'), item['name'].encode('utf-8')))

    self.conn.commit()


except MySQLdb.Error, e:
    print "Error %d: %s" % (e.args[0], e.args[1])


return item

并在settings.py中添加了

ITEM_PIPELINES = {
'stack.pipelines.MySQLStorePipeline': 300,
}

并且我的日志显示了这些错误，但您仍然可以看到信息收集工作，即使它显示了这个。

 File "/usr/lib/python2.7/dist-packages/twisted/internet/defer.py", line   577, in _runCallbacks
 current.result = callback(current.result, *args, **kw)
 File "/root/stack/stack/pipelines.py", line 14, in process_item
 self.cursor.execute("""INSERT INTO test (pen, name) VALUES (%s, %s)""",  (item['pen'].encode('utf-8'), item['name'].encode('utf-8')))
 AttributeError: 'list' object has no attribute 'encode'

因此没有结果导入数据库

Answer 1

解决了它问题是缩进，列表对象没有属性

import sys
import MySQLdb
import hashlib
from scrapy.exceptions import DropItem
from scrapy.http import Request

class MySQLStorePipeline(object):
def __init__(self):
self.conn = MySQLdb.connect(host="10.0.2.2", user='root', passwd='', db='mpmf', charset="utf8", use_unicode=True)
self.cursor = self.conn.cursor()

def process_item(self, item, stack):    
try:
    self.cursor.execute("""INSERT INTO test (pen, name) VALUES (%s, %s)""", (item['pen'][0].encode('utf-8'), item['name'][0].encode('utf-8')))

    self.conn.commit()


except MySQLdb.Error, e:
    print "Error %d: %s" % (e.args[0], e.args[1])


return item

scrapy mysql返回空结果

1 个答案: