目錄
三、“股票數據Scrapy爬蟲”實例
1、“股票數據Scrapy爬蟲”實例介紹
(1)功能描述
技術路線:scrapy。
目標:獲取上交所和深交所所有股票的名稱和交易信息。
輸出:保存到文件中。
(2)數據網站的確定
獲取股票列表:
東方財富網:http://quote.eastmoney.com/stocklist.html。
獲取個股信息:
百度股票:https://gupiao.baidu.com/stock/。
單個股票:https://gupiao.baidu.com/stock/sz002439.html。
備註:原來的百度股票、單個股票網頁鏈接均已失效;故更改爲https://so.cfi.cn/so.aspx?txquery=。原來的東方財富網網頁鏈接已無法爬取數據;故更改爲http://quote.eastmoney.com/stock_list.html#sh。
2、“股票數據Scrapy爬蟲”實例編寫
步驟1:建立工程和Spider模板
管理員權限啓動cmd。
輸入:
scrapy startproject BaiduStocks
cd BaiduStocks
scrapy genspider stocks baidu.com
進一步修改spiders/stocks.py文件。
備註:原來的第二行命令是BaiduStocks,有誤;故更改爲cd BaiduStocks。
步驟2:編寫Spider
配置stocks.py文件。
修改對返回頁面的處理。
修改對新增URL爬取請求的處理(stocks.py)。
# 錯誤
# -*- coding: utf-8 -*-
import scrapy
import re
class StocksSpider(scrapy.Spider):
name = 'stocks'
start_urls = ['http://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(
{'股票名稱': re.findall('\s.*\(', name)[0].split()[0] + \
re.findall('\>.*\<', name)[0][1:-1]}) # 兩個字典合併到一起。
yield infoDict
# 正確
# -*- 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
步驟3:編寫ITEM Pipelines
配置pipelines.py文件。
定義對爬取項(Scrapy Item)的處理類(pipelines.py)。
配置ITEM_PIPELINES選項(settings.py)。
①items.py:
# 錯誤
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/items.html
import scrapy
class BaidustocksItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
pass
# 正確
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/items.html
import scrapy
class BaidustocksItem(scrapy.Item):
# define the fields for your item here like:
name = scrapy.Field()
number = scrapy.Field()
details = scrapy.Field()
②pipelines.py:
# 錯誤
# -*- 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
# 正確
# -*- 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
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
③settings.py:
# 錯誤
# -*- 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://doc.scrapy.org/en/latest/topics/settings.html
# https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
# https://doc.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 = 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://doc.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://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'BaiduStocks.middlewares.BaidustocksSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'BaiduStocks.middlewares.BaidustocksDownloaderMiddleware': 543,
#}
# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
# Configure item pipelines
# See https://doc.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://doc.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://doc.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'
# 正確
# -*- 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://doc.scrapy.org/en/latest/topics/settings.html
# https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
# https://doc.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://doc.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://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'BaiduStocks.middlewares.BaidustocksSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'BaiduStocks.middlewares.BaidustocksDownloaderMiddleware': 543,
#}
# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
# Configure item pipelines
# See https://doc.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://doc.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://doc.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'
備註:原來的ROBOTSTXT_OBEY = True更改爲ROBOTSTXT_OBEY = False,只有這一處改動。
執行程序:scrapy crawl stocks。
3、“股票數據Scrapy爬蟲”實例優化
配置併發連接選項(settings.py)。
選項 | 說明 |
CONCURRENT_REQUESTS | Downloader最大併發請求下載數量,默認32 |
CONCURRENT_ITEMS | Item Pipeline最大併發ITEM處理數量,默認100 |
CONCURRENT_REQUESTS_PER_DOMAI N |
每個目標域名最大的併發請求數量,默認8 |
CONCURRENT_REQUESTS_PER_IP |
每個目標IP最大的併發請求數量,默認0,非0有效 |