Question

我是python的初学者，我正在使用scrapy。我使用xmlitemexporter将我的已删除数据导出到xml文件。但我只在xml文件中得到“＆lt;”/ item“”＆gt;“。我的items.py如下：

from scrapy.item import Item, Field

class WorkwithitemsItem(Item):
    title = Field()
    link = Field()
    publish = Field()
    description = Field()

蜘蛛就像：

from scrapy import log
from scrapy.spider import BaseSpider
from scrapy.selector import Selector
from workwithitems.items import WorkwithitemsItem


class MySpider(BaseSpider):
    name = 'spidey'
    allowed_domains = ['ekantipur.com']
    start_urls = [
    'http://www.ekantipur.com/en/rss',
                  ]
    def parse(self, response):
        self.log('A response from %s just arrived!' % response.url)
        sel = Selector(response)
        title = sel.xpath('//title/text()').extract()
        link = sel.xpath('//link/text()').extract()
        publish = sel.xpath('//pubDate/text()').extract()
        description = sel.xpath('//description/text()').extract()
        WorkwithitemsItem(title = title[2:], link = link[2:], 
              publish = publish, description = description[1:])

pipelines.py是：

from scrapy import signals
from scrapy.contrib.exporter import XmlItemExporter


class XmlExportPipeline(object):
    def __init__(self):
        self.files = {}

    @classmethod
    def from_crawler(cls, crawler):
        pipeline = cls()
        crawler.signals.connect(pipeline.spider_opened, signals.spider_opened)
        crawler.signals.connect(pipeline.spider_closed, signals.spider_closed)
        return pipeline

    def spider_opened(self, spider):
        file = open('%s_products.xml' % spider.name, 'w+b')
        self.files[spider] = file
        self.exporter = XmlItemExporter(file)
        self.exporter.start_exporting()

    def spider_closed(self, spider):
        self.exporter.finish_exporting()
        file = self.files.pop(spider)
        file.close()

    def process_item(self, item, spider):
        self.exporter.export_item(item)
        return item

settings.py是：

BOT_NAME = 'workwithitems'
SPIDER_MODULES = ['workwithitems.spiders']
NEWSPIDER_MODULE = 'workwithitems.spiders'
FEED_EXPORTERS_BASE = {
    'xml': 'scrapy.contrib.exporter.XmlItemExporter',
}
ITEM_PIPELINES = {
    'workwithitems.pipelines.XmlExportPipeline': 800,
}

我无法弄清楚我的问题在哪里。

Answer 1

确定！我发现了这个问题。我所做的只是在spider.py

的最后一行放一个'return'

return WorkwithitemsItem(title = title[2:], link = link[2:], 
                                publish = publish, description = description[1:]
                                )

使用XMLITEMEXPORTER在XML文件中没有输出

1 个答案: