pip3 install scrapy -i https://pypi.tuna.tsinghua.edu.cn/simple
安装库scrapy startproject Stocks
创建工程cd Stocks/
scrapy genspider stocks qq.com
创建爬虫- 东方财富网 + 腾讯证券
stocks.py
# -*- coding: utf-8 -*-
import scrapy
import re
class StocksSpider(scrapy.Spider):
name = 'stocks'
start_urls = ['http://quote.eastmoney.com/stock_list.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 = 'http://gu.qq.com/' + stock + '/gp'
yield scrapy.Request(url, callback = self.parse_stock)
except:
continue
def parse_stock(self, response):
infoDict = {}
stockName = response.css('.title_bg')
stockInfo = response.css('.col-2.fr')
name = stockName.css('.col-1-1').extract()[0]
code = stockName.css('.col-1-2').extract()[0]
info = stockInfo.css('li').extract()
for i in info[:13]:
key = re.findall('>.*?<', i)[1][1:-1]
key = key.replace('\u2003','')
key = key.replace('\xa0','')
try:
val = re.findall('>.*?<', i)[3][1:-1]
except:
val = '--'
infoDict[key] = val
infoDict.update({ '股票名称':re.findall('\>.*\<', name)[0][1:-1] + \
re.findall('\>.*\<', code)[0][1:-1]})
yield infoDict
pipelines.py
需修改文件路径
# -*- 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 StocksPipeline(object):
def process_item(self, item, spider):
return item
class StocksInfoPipeline(object):
def open_spider(self, spider):
self.f = open('/home/lwy/Spiders/Stocks/Stocks/spiders/StockInfo.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
settings.py
打开文件,找到如下内容并修改
ITEM_PIPELINES = {
'Stocks.pipelines.StocksInfoPipeline': 300,
}
scrapy crawl stocks
运行爬虫