python爬虫使用scrapy框架爬取股票数据

使用scrapy爬取东方财富网

spiders部分

# -*- coding: utf-8 -*-
import scrapy
import re
from BaiduStocks.items import BaidustocksItem

class StocksSpider(scrapy.Spider):
    name = 'stocks'
    start_urls = ['http://quote.eastmoney.com/stock_list.html#sh']

    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 = 'http://so.cfi.cn/so.aspx?txquery='+stock+'.html'
                yield scrapy.Request(url,callback=self.parse_stock)
            except:
                continue
    def parse_stock(self,response):
        try:
            item = BaidustocksItem()
            stock = response.xpath('//td[@id="tdquote"]/table/tr/td/text()').extract()
            name = stock[0]
            number = stock[1]
            details = stock[2:]
            item['name'] = name
            item['number'] = number
            item['details'] = details
            yield item
        except:
            pass

item部分

import scrapy


class BaidustocksItem(scrapy.Item):
    # define the fields for your item here like:
    name = scrapy.Field()
    number = scrapy.Field()
    details = scrapy.Field()

pipelines部分

import json

class BaidustocksPipeline(object):
    def process_item(self, item, spider):
        return item


class BaidustocksInfoPipeline(object):
    def open_spider(self,spider):
        self.f = open('BaiduSTocks.json','w',encoding='utf-8')
    def close_spider(self,spider):
        self.f.close()



    def process_item(self,item,spider):
        if item == {}:
            pass
        text = json.dumps(dict(item), ensure_ascii = False) + "\n"
        text.encode('utf-8')
        self.f.write(text)
        return item

setting部分

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

# Scrapy settings for BaiduStocks project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'BaiduStocks'

SPIDER_MODULES = ['BaiduStocks.spiders']
NEWSPIDER_MODULE = 'BaiduStocks.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'BaiduStocks (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False


# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
#}

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'BaiduStocks.middlewares.BaidustocksSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'BaiduStocks.middlewares.BaidustocksDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    'BaiduStocks.pipelines.BaidustocksInfoPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'