使用scrapy抓取股票代码

pip install Scrapy

scrapy startproject tutorial

class StockItem(scrapy.Item):
    stock_id = scrapy.Field()

class StockSpider(scrapy.Spider):
    name = 'stock'

    def start_requests(self):
        url = 'http://quote.eastmoney.com/stocklist.html'
        yield Request(url)

    def parse(self, response):
        item = StockItem()
        print "===============上海================"
        stocks_sh = response.css('div#quotesearch ul li a[href*="http://quote.eastmoney.com/sh"]::text')
        for stock in stocks_sh:
            item['stock_id'] = 's_sh' + re.findall('\((.*?)\)', stock.extract())[0]
            yield item

        print "===============深圳================"
        stocks_sz = response.css('div#quotesearch ul li a[href*="http://quote.eastmoney.com/sz"]::text')
        for stock in stocks_sz:
            item['stock_id'] = 's_sz' + re.findall('\((.*?)\)', stock.extract())[0]
            yield item

scrapy crawl stock -o stock.csv

stock_id
s_sh201000
s_sh201001
s_sh201002
s_sh201003
s_sh201004
s_sh201005
s_sh201008
s_sh201009
s_sh201010
s_sh202001
s_sh202003
s_sh202007
s_sh203007
s_sh203008
s_sh203009
…

var hq_str_s_sh600756="浪潮软件,19.790,1.140,6.11,365843,70869";