0
下午好, 我尝试从Web中获取数据并在SQLServer中存储数据。使用lib pymssql,连接已建立。但是当处理项目时,错误“太多的解包值”出来了,所以我也附加了MyItem类。我看不到明显的错误? 这里是代码pipelines.py当将scrapy管道数据写入数据库时,错误值太高以致无法解压
-*- coding: utf-8 -*-
import pymssql
from scrapy import signals
import json
import codecs
class MyPipeline(object):
def __init__(self):
self.conn = pymssql.connect(host=r".\\MyPC",user='sa',password='XXXX',database='Webmining')
self.cursor = self.conn.cursor()
def process_item(self, item, spider):
try:
self.cursor.executemany("INSERT INTO RecruitInformation(recruitNumber,name,detailLink,publishTime,catalog,worklocation) VALUES (%d,%s,%s,%t,%s,%s)",(item['recruitNumber'],item['name'],item['detailLink'],item['publishTime'],item['catalog'],item['worklocation']))
self.conn.commit()
except pymssql.InterfaceError, e:
print ("pymssql.InterfaceError")
except pymssql.DataError, e:
print ("pymssql.DataError")
except pymssql.OperationalError, e:
print ("pymssql.OperationalError")
except pymssql.IntegrityError, e:
print ("pymssql.IntegrityError")
except pymssql.InternalError, e:
print ("pymssql.InternalError")
except pymssql.ProgrammingError, e:
print ("pymssql.ProgrammingError")
except pymssql.NotSupportedError, e:
print ("pymssql.NotSupportedError")
return item
def spider_closed(self, spider):
self.conn.close()
//the code in item.py is as follow
import scrapy
from scrapy.item import Item, Field
class MyItem(Item):
name = Field()
catalog = Field()
workLocation = Field()
recruitNumber = Field()
detailLink = Field()
publishTime = Field()
class MySpider(CrawlSpider):
name = "xxxx"
allowed_domains = ["xxxx.com"]
start_urls = [ "http://xx.xxxx.com/position.php"]
rules = [Rule(sle(allow=("/position.php\?&start=\d{,4}#a")), follow=True,callback='parse_item')]
def parse_item(self, response):
items = []
sel = Selector(response)
base_url = get_base_url(response)
sites_even = sel.css('table.tablelist tr.even')
for site in sites_even:
item = MyItem()
item['name'] = site.css('.l.square a').xpath('text()').extract()
relative_url = site.css('.l.square a').xpath('@href').extract()[0]
item['detailLink'] = urljoin_rfc(base_url, relative_url)
item['catalog'] = site.css('tr > td:nth-child(2)::text').extract()
item['workLocation'] = site.css('tr > td:nth-child(4)::text').extract()
item['recruitNumber'] = site.css('tr > td:nth-child(3)::text').extract()
item['publishTime'] = site.css('tr > td:nth-child(5)::text').extract()
items.append(item)
sites_odd = sel.css('table.tablelist tr.odd')
for site in sites_odd:
item = MyItem()
item['name'] = site.css('.l.square a').xpath('text()').extract()
relative_url = site.css('.l.square a').xpath('@href').extract()[0]
item['detailLink'] = urljoin_rfc(base_url, relative_url)
item['catalog'] = site.css('tr > td:nth-child(2)::text').extract()
item['workLocation'] = site.css('tr > td:nth-child(4)::text').extract()
item['recruitNumber'] = site.css('tr > td:nth-child(3)::text').extract()
item['publishTime'] = site.css('tr > td:nth-child(5)::text').extract()
items.append(item)
return items
def _process_request(self, request):
info('process ' + str(request))
return request
由于我不熟悉Scrapy,只能看到item的定义,它是字典式的,并且不仅包含一个值。所以它不能在sql中使用。但如何让它一个接一个地取出? – SnailBai
在这种情况下,填充元素的代码将非常重要,因为我认为您可以用列表填充一个“Field”而不是单个值。请编辑您的问题,并从蜘蛛中添加代码。 – GHajba
我已经添加了蜘蛛代码,我也用executemany()取代了函数execute,它可以处理字典@GHajba – SnailBai