股票数据scrapy爬虫（出自MOOC的课程《python网络爬虫与信息提取》），抓取数据失败

# -*- coding: utf-8 -*-

import scrapy

import re





class StocksSpider(scrapy.Spider):

    name = 'stocks'

    start_urls = ['http://quote.eastmoney.com/stocklist.html']



    def parse(self, response):

        for href in response.css('a::attr(href)').extract():

            try:

                stock=re.findall(r'[s][hz]\d{6}',href)

                url='https://gupiao.baidu.com/stock/'+stock+'.html'

                yield scrapy.Request(url,callback=self.parse_stock)

            except:

                continue

    

    def parse_stock(self,response):

        infoDict={}

        stockInfo=response.css('.stock-bets')

        name=stockInfo.css('.bets-name').extract()[0]

        keyList=stockInfo.css('dt').extract()

        valueList=stockInfo.css('dd').extract()

        for i in range(len(keyList)):

            key=re.findall(r'>.*</dt>',keyList[i])[0][1:-5]#

            #key=keyList[i][0]

            try:

                val=re.findall(r'\d+\.?.*</dd>',valueList[i])[0][0:-5]#

                #val=valueList[i][0]

            except:

                val='--'

            infoDict[key]=val

                    

        infoDict.update({'股票名称':re.findall(r'\s.*\(',name)[0].split()[0]+re.findall(r'\>.*\<',name)[0][1:-1]})#

        #infoDict.update({'股票名称':name.split()[0]})

        yield infoDict

        

        

C:\Users\DONG LONG RUI\.spyder-py3\myscrapy\BaiduStocks>scrapy crawl stocks

2017-10-16 22:46:55 [scrapy.utils.log] INFO: Scrapy 1.4.0 started (bot: BaiduStocks)

2017-10-16 22:46:55 [scrapy.utils.log] INFO: Overridden settings: {'BOT_NAME': 'BaiduStocks', 'NEWSPIDER_MODULE': 'BaiduStocks.spiders', 'SPIDER_MODULES': ['BaiduStocks.spiders']}

2017-10-16 22:46:55 [scrapy.middleware] INFO: Enabled extensions:

['scrapy.extensions.corestats.CoreStats',

 'scrapy.extensions.telnet.TelnetConsole',

 'scrapy.extensions.logstats.LogStats']

2017-10-16 22:46:55 [scrapy.middleware] INFO: Enabled downloader middlewares:

['scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware',

 'scrapy.downloadermiddlewares.downloadtimeout.DownloadTimeoutMiddleware',

 'scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware',

 'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware',

 'scrapy.downloadermiddlewares.retry.RetryMiddleware',

 'scrapy.downloadermiddlewares.redirect.MetaRefreshMiddleware',

 'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware',

 'scrapy.downloadermiddlewares.redirect.RedirectMiddleware',

 'scrapy.downloadermiddlewares.cookies.CookiesMiddleware',

 'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware',

 'scrapy.downloadermiddlewares.stats.DownloaderStats']

2017-10-16 22:46:55 [scrapy.middleware] INFO: Enabled spider middlewares:

['scrapy.spidermiddlewares.httperror.HttpErrorMiddleware',

 'scrapy.spidermiddlewares.offsite.OffsiteMiddleware',

 'scrapy.spidermiddlewares.referer.RefererMiddleware',

 'scrapy.spidermiddlewares.urllength.UrlLengthMiddleware',

 'scrapy.spidermiddlewares.depth.DepthMiddleware']

2017-10-16 22:46:55 [scrapy.middleware] INFO: Enabled item pipelines:

['BaiduStocks.pipelines.BaidustocksInfoPipeline']

2017-10-16 22:46:55 [scrapy.core.engine] INFO: Spider opened

2017-10-16 22:46:55 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)

2017-10-16 22:46:55 [scrapy.extensions.telnet] DEBUG: Telnet console listening on 127.0.0.1:6023

2017-10-16 22:46:55 [scrapy.core.engine] DEBUG: Crawled (200) <GET http://quote.eastmoney.com/stocklist.html> (referer: None)

2017-10-16 22:46:55 [scrapy.core.engine] INFO: Closing spider (finished)

2017-10-16 22:46:55 [scrapy.statscollectors] INFO: Dumping Scrapy stats:

{'downloader/request_bytes': 231,

 'downloader/request_count': 1,

 'downloader/request_method_count/GET': 1,

 'downloader/response_bytes': 90141,

 'downloader/response_count': 1,

 'downloader/response_status_count/200': 1,

 'finish_reason': 'finished',

 'finish_time': datetime.datetime(2017, 10, 16, 14, 46, 55, 946144),

 'log_count/DEBUG': 2,

 'log_count/INFO': 7,

 'response_received_count': 1,

 'scheduler/dequeued': 1,

 'scheduler/dequeued/memory': 1,

 'scheduler/enqueued': 1,

 'scheduler/enqueued/memory': 1,

 'start_time': datetime.datetime(2017, 10, 16, 14, 46, 55, 345506)}

2017-10-16 22:46:55 [scrapy.core.engine] INFO: Spider closed (finished)