Scrapy 爬虫实战1—股票数据爬取

功能描述

获取股票列表：

http://quote.eastmoney.com/stock_list.html\'

获取个股信息：

https://www.laohu8.com/stock/

步骤

步骤1：建立工程和Spider模板

> scrapy startproject laohustocks

> laohustocks

> scrapy genspider stocks laohu

> 进一步修改spiders/stocks.py

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（stocks.py）

# -*- coding: utf-8 -*-
import scrapy
import re
import collections
class StocksSpider(scrapy.Spider):
    name = \'stocks\'
    #allowed_domains = [\'laohu\']
    start_urls = [\'http://quote.eastmoney.com/stock_list.html\']
    def parse(self, response):
        for href in response.css(\'a::attr(href)\').extract():#返回列表
            try:
                stock = re.findall(r\'\d{6}\',href)[0]
                url = \'https://www.laohu8.com/stock/\' +stock
                yield scrapy.Request(url,callback=self.parse_stock)
            except:
                continue
    def parse_stock(self,response):
        #infodict = {}
        infodict = collections.OrderedDict()#按照插入顺序更新infodict
        name = response.css(\'.name\').extract()[0]
        print(\'name: \',name)
        infodict.update({\'股票名称\': re.findall(\'\>.*?\<\', name)[0][1:-1] + \'-\'
                                 + re.findall(\'\(.*\)\', name)[0][1:-1]})
        stocksinfo = response.css(\'.detail-data\')
        keylist = stocksinfo.css(\'dt\').extract()
        valuelist = stocksinfo.css(\'dd\').extract()
        for i in range(len(keylist)):
            key = re.findall(r\'>.*</dt>\', keylist[i])[0][1:-5]
            try:
                value =re.findall(r\'>.*</dd>\', valuelist[i])[0][1:-5]
            except:
                   value =\'--\'
            print(\'key : value\',key,value)
            infodict[key] = value
        yield infodict

name = response.css(\'.name\').extract()[0]

   print(\'name: \',name)

        stocksinfo = response.css(\'.detail-data\')
        keylist = stocksinfo.css(\'dt\').extract()
        valuelist = stocksinfo.css(\'dd\').extract()

步骤3：编写ITEM Pipelines

配置pipelines.py文件

定义对爬取项（Scrapy Item）的处理类（pipelines.py）

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

# Define your item pipelines here
#
# Don\'t forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html


class LaohustocksPipeline(object):
    def process_item(self, item, spider):
        return item
class LaohustocksInfoPipeline(object):
    def open_spider(self,spider):
        self.f = open(\'LaohuStockInfo.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

步骤四：配置ITEM_PIPELINES选项（settings.py）

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

# Scrapy settings for laohustocks 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 = \'laohustocks\'

SPIDER_MODULES = [\'laohustocks.spiders\']
NEWSPIDER_MODULE = \'laohustocks.spiders\'


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

# Obey robots.txt rules
ROBOTSTXT_OBEY = True

# 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 = {
#    \'laohustocks.middlewares.LaohustocksSpiderMiddleware\': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    \'laohustocks.middlewares.LaohustocksDownloaderMiddleware\': 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 = {
   \'laohustocks.pipelines.LaohustocksInfoPipeline\': 300,
}
#一定按照自己部署顺序写
# 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\'

爬取数据的部分内容