股票数据scrapy爬虫

Posted on | In , , | |
Words count in article: 490 | Reading time ≈ 2

目标：获取上交所和深交所所有股票的名称和交易信息

输出：保存到文件中

技术路线：scrapy

数据网站的确定：

1
2
3
4
5
获取股票列表：
东方财富网：http://quote.eastmoney.com/stocklist.html
获取个股信息：
百度股票：https://gupiao.baidu.com/stock/
单个股票：https://gupiao.baidu.com/stock/sz002439.html

步骤：

  • 步骤1：建立工程和Spider模板
  • 步骤2：编写Spider
  • 步骤3：编写ITEM Pipelines

步骤1：建立工程和Spider模板

1
2
3
4
\>scrapy startproject BaiduStocks
\>cd BaiduStocks
\>scrapy genspider stocks baidu.com
进一步修改spiders/stocks.py文件

步骤2：编写Spider

  • 配置stocks.py文件
  • 修改对返回页面的处理
  • 修改对新增URL爬取请求的处理
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
# stocks.py
# -*- coding: utf-8 -*-
import scrapy
import re
 
 
class StocksSpider(scrapy.Spider):
    name = "stocks"
    start_urls = ['https://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)[0]
                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]
            try:
                val = re.findall(r'\d+\.?.*</dd>', valueList[i])[0][0:-5]
            except:
                val = '--'
            infoDict[key]=val
 
        infoDict.update(
            {'股票名称': re.findall('\s.*\(',name)[0].split()[0] + \
             re.findall('\>.*\<', name)[0][1:-1]})
        yield infoDict

步骤3：编写ITEM Pipelines

  • 配置pipelines.py文件
  • 定义对爬取项（Scraped Item）的处理类
  • 配置ITEM_PIPELINES选项
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
# pipelines.py
# -*- coding: utf-8 -*-
 
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
 
 
class BaidustocksPipeline(object):
    def process_item(self, item, spider):
        return item
 
class BaidustocksInfoPipeline(object):
    def open_spider(self, spider):
        self.f = open('BaiduStockInfo.txt', 'w')
 
    def close_spider(self, spider):
        self.f.close()
 
    def process_item(self, item, spider):
        try:
            line = str(dict(item)) + '\n'
            self.f.write(line)
        except:
            pass
        return item

配置settings.py文件

1
2
3
4
5
# Configure item pipelines
# See https://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    'BaiduStocks.pipelines.BaidustocksInfoPipeline': 300,
}

如何进一步提高scrapy爬虫爬取速度？

2

Donate? comment?