When i use scrapy to get some stocks information from 'http://quote.eastmoney.com/stocklist.html',I can't get right response. Actually, I get nothing when I run it. Here is the contents of stocks.py:
import scrapy
from scrapy.selector import Selector
import re
class StocksSpider(scrapy.Spider):
name = "stocks"
start_urls = ['http://quote.eastmoney.com/stocklist.html']
def parse(self, response):
for i in Selector(response).xpath('//div[@id="quotesearch"]/ul/li/a/@href').extract():
try:
stock=re.split(r'[./]',i)[5]
url='https://gupiao.baidu.com/stock/'+stock+'.html'
yield scrapy.Rquest(url,callback=self.parse_stock)
except:
continue
def parse_stock(self,response):
infoDict={}
name=Selector(response).xpath('//a[@class="bets-name"]/text()').extract()[0]
keylist=Selector(response).xpath('//dl/dt/text()').extract()
for i in range(len(keylist)):
try:
val=Selector(response).xpath('//dl/dd/text()').extract()[0]
except:
val='--'
infoDict[keylist[i]]=val
infoDict.update({'股票名称':name[0].split()[0]+'('+Selector(response).xpath('//a[@class="bets-name"]/span/text()')[0].extract()[0]+')'})
yield infoDict
Here is what I get when I run it:
2017-06-05 20:28:32 [scrapy.utils.log] INFO: Scrapy 1.3.3 started (bot: BaiduStocks)
2017-06-05 20:28:32 [scrapy.utils.log] INFO: Overridden settings: {'BOT_NAME': 'BaiduStocks', 'FEED_EXPORT_ENCODING': 'utf-8', 'NEWSPIDER_MODULE': 'BaiduStocks.spiders', 'ROBOTSTXT_OBEY': True, 'SPIDER_MODULES': ['BaiduStocks.spiders']}
2017-06-05 20:28:32 [scrapy.middleware] INFO: Enabled extensions:
['scrapy.extensions.corestats.CoreStats',
'scrapy.extensions.telnet.TelnetConsole',
'scrapy.extensions.logstats.LogStats']
2017-06-05 20:28:33 [scrapy.middleware] INFO: Enabled downloader middlewares:
['scrapy.downloadermiddlewares.robotstxt.RobotsTxtMiddleware',
'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.stats.DownloaderStats']
2017-06-05 20:28:33 [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']
2017-06-05 20:28:33 [scrapy.middleware] INFO: Enabled item pipelines:
['BaiduStocks.pipelines.BaidustocksInfoPipeline']
2017-06-05 20:28:33 [scrapy.core.engine] INFO: Spider opened
2017-06-05 20:28:33 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
2017-06-05 20:28:33 [scrapy.extensions.telnet] DEBUG: Telnet console listening on 127.0.0.1:6023
2017-06-05 20:28:33 [scrapy.core.engine] DEBUG: Crawled (404) <GET http://quote.eastmoney.com/robots.txt> (referer: None)
2017-06-05 20:28:33 [scrapy.core.engine] DEBUG: Crawled (200) <GET http://quote.eastmoney.com/stocklist.html> (referer: None)
2017-06-05 20:28:33 [scrapy.core.engine] INFO: Closing spider (finished)
2017-06-05 20:28:33 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
{'downloader/request_bytes': 458,
'downloader/request_count': 2,
'downloader/request_method_count/GET': 2,
'downloader/response_bytes': 570201,
'downloader/response_count': 2,
'downloader/response_status_count/200': 1,
'downloader/response_status_count/404': 1,
'finish_reason': 'finished',
'finish_time': datetime.datetime(2017, 6, 5, 12, 28, 33, 930937),
'log_count/DEBUG': 3,
'log_count/INFO': 7,
'response_received_count': 2,
'scheduler/dequeued': 1,
'scheduler/dequeued/memory': 1,
'scheduler/enqueued': 1,
'scheduler/enqueued/memory': 1,
'start_time': datetime.datetime(2017, 6, 5, 12, 28, 33, 28477)}
2017-06-05 20:28:33 [scrapy.core.engine] INFO: Spider closed (finished)
I have been working on it for a few days, but I can't tell what's wrong. So I really need your help. Thank you all!
Here, I did a short code review:
import scrapy
from scrapy.selector import Selector
import re
class StocksSpider(scrapy.Spider):
name = "stocks"
start_urls = ['http://quote.eastmoney.com/stocklist.html']
def parse(self, response):
# response has a shortcut for selector
for i in response.xpath('//div[@id="quotesearch"]/ul/li/a/@href').extract():
# never silently catch and drop errors
stock = re.split(r'[./]', i)[5]
url = 'https://gupiao.baidu.com/stock/' + stock + '.html'
yield scrapy.Request(url, callback=self.parse_stock)
def parse_stock(self, response):
# objects should be lowercase in python
item = dict()
# there's extract_first shortcut for extract()[0]
name = response.xpath('//a[@class="bets-name"]/text()').extract_first('')
keylist = response.xpath('//dl/dt/text()').extract()
# for each is preferred loop style.
for key in keylist:
# extract_first allows a default argument to be set
item[key] = response.xpath('//dl/dd/text()').extract_first('--')
data = Selector(response).xpath('//a[@class="bets-name"]/span/text()').extract_first('') + ')'
item['data'] = '{}({})'.format(name.split()[0], data)
yield item
Aside from minor issues the biggest one was that your try/except clause in parse() method just quit silenty and you had a typo Rquest, so the spider just went on - you should never have silent blanket exceptions for this very reason :)
Collected from the Internet
Please contact [email protected] to delete if infringement.
Comments