TypeError：'instancemethod'对象在运行scrapy spider时没有属性'__getitem__'

Question

运行scrapy项目时出现此错误 我的spider.py代码是

import scrapy
import re
from tutorial.items import TutorialItem

class tutorialSpider(scrapy.Spider):
    name="tutorial"
    allowed_domain=['examble.com']
    start_urls = ["examble.com/something"]

    def parse(self, response):
        for sel in response.xpath('//*[@id="post-entry"]/div/article'):
            item = TutorialItem()
            item['Title'] = sel.xpath('div[2]/h2/a/text()').extract[0]
            item['MainPageUrl'] = sel.xpath('div[2]/h2/a/@href').extract[0]
            item['Author'] = sel.xpath('div[2]/div/span/a/text()').extract[0]
            request = scrapy.Request(item['MianPageUrl'], callback=self.parseContentDetails)            
            request.meta['item'] = item
            yield request

    def parseContentDetails(self,response):
        item = response.meta['item']
        item['Content'] = response.xpath()
        item['Count'] = response.xpath()
        print type(item)
        return item 

我的pipeline.py是

class TutorialPipeline(object):
    def __init__(self):
        #self.setupDBCon()
        #self.createTables()
    def process_item(self, item, spider):
        for key, value in item.iteritems():
            if(isinstance(value, list)):
                if value:
                    templist = []
                    for obj in value:
                        temp = self.stripHTML(obj)
                        templist.append(temp)
                    item[key] = templist
                else:
                    item[key] = ""
            else:
                item[key] = self.stripHTML(value)

        print item.get('Title', '')     
        return item

和我的items.py是

from scrapy.item import Item, Field

class TutorialItem(Item):
    Title=Field()
    Author = Field()
    MianPageUrl = Field()
    Content=Field()
    Count=Field()

请告诉我这个错误的解决方案。我搜索了很多网站。那些网站只告诉instancemethod对象在django中没有属性错误，但我想要scrapy的解决方案

Answer 1

你没有正确地调用提取，对于每个提取你必须实际调用该方法然后索引它：

item['Title'] = sel.xpath('div[2]/h2/a/text()').extract()[0]
                                                       ^^^

如果您只想要第一个元素，可以使用 extract_first 。

 item['Title'] = sel.xpath('div[2]/h2/a/text()').extract_first()