前面有介绍过Selenium作为开源的自动化测试框架,其实Selenium还可以作为爬虫工具。
举个例子,我想爬取中国概念股的一些信息,例如这样的:http://app.finance.ifeng.com/list/usstock_cn.php
先建个SeleniumUtil.py的文件
![](https://i-blog.csdnimg.cn/blog_migrate/8f900a89c6347c561fdf2122f13be562.gif)
![ExpandedBlockStart.gif](https://i-blog.csdnimg.cn/blog_migrate/961ddebeb323a10fe0623af514929fc1.gif)
#
!/usr/bin/python2.5.2
# -*- coding: utf8 -*-
from selenium import selenium
class SeleniumUtil:
seleniums = {}
def StartSeleniumForUrl(self, url):
sel = selenium( " localhost " , 4444 , " *chrome " , url)
sel.start()
sel.set_timeout( " 90000 " )
return sel
def GetSelenium(self, websiteName, url):
# if websiteName in self.seleniums:
# return self.seleniums[websiteName]
self.seleniums[websiteName] = self.StartSeleniumForUrl(url)
return self.seleniums[websiteName]
def StopSelenium(self, websiteName):
if websiteName in self.seleniums:
self.seleniums[websiteName].stop()
# -*- coding: utf8 -*-
from selenium import selenium
class SeleniumUtil:
seleniums = {}
def StartSeleniumForUrl(self, url):
sel = selenium( " localhost " , 4444 , " *chrome " , url)
sel.start()
sel.set_timeout( " 90000 " )
return sel
def GetSelenium(self, websiteName, url):
# if websiteName in self.seleniums:
# return self.seleniums[websiteName]
self.seleniums[websiteName] = self.StartSeleniumForUrl(url)
return self.seleniums[websiteName]
def StopSelenium(self, websiteName):
if websiteName in self.seleniums:
self.seleniums[websiteName].stop()
接着写个IfengFinanceSite.py文件来爬取需要的信息,例子如下,
![](https://i-blog.csdnimg.cn/blog_migrate/8f900a89c6347c561fdf2122f13be562.gif)
![ExpandedBlockStart.gif](https://i-blog.csdnimg.cn/blog_migrate/961ddebeb323a10fe0623af514929fc1.gif)
#
!/usr/bin/python2.4
# -*- coding: utf8 -*-
# Ifeng Site
#
import codecs,time
from SeleniumUtil import SeleniumUtil
ExchangeUrlMap = {
" CCS " : " http://app.finance.ifeng.com/list/usstock_cn.php " ,
# "SHA_B": "http://stock.finance.sina.com.cn/stock/quote/shb%s.html",
}
ExchangeXPath = " //html/body/div[4]/div/div[2]/div/table/tbody/tr[%s]/td[1] "
class IfengFinanceSite:
# result file for diff exchanges
def GetAllTickers(self, exchange, resultFiles):
sln = SeleniumUtil().GetSelenium( " Ifeng " , " http://app.finance.ifeng.com/ " )
myfile = codecs.open(resultFiles % exchange, ' w ' , ' utf-8 ' )
count = 0
sln.open(ExchangeUrlMap[exchange])
time.sleep( 5 )
for j in range( 2 , 200 ):
if sln.is_element_present(ExchangeXPath % j):
context = sln.get_text(ExchangeXPath % j).strip()
print >> myfile, context, ' \r '
count = count + 1
else : break
print " %s companies for exchange %s recorded. " % (count, exchange)
sln.stop()
exchangelist = [ " CCS " ] # "SHA_A","SHA_B","SHE_A","SHE_B","SHA_Q","SHA_CEF","SHE_CEF","SHA_Bond","SHE_Bond"
for exchange in exchangelist:
print exchange
resultFiles = " Ifeng_company_list_%s.txt "
IfengFinanceSite().GetAllTickers(exchange, resultFiles)
# -*- coding: utf8 -*-
# Ifeng Site
#
import codecs,time
from SeleniumUtil import SeleniumUtil
ExchangeUrlMap = {
" CCS " : " http://app.finance.ifeng.com/list/usstock_cn.php " ,
# "SHA_B": "http://stock.finance.sina.com.cn/stock/quote/shb%s.html",
}
ExchangeXPath = " //html/body/div[4]/div/div[2]/div/table/tbody/tr[%s]/td[1] "
class IfengFinanceSite:
# result file for diff exchanges
def GetAllTickers(self, exchange, resultFiles):
sln = SeleniumUtil().GetSelenium( " Ifeng " , " http://app.finance.ifeng.com/ " )
myfile = codecs.open(resultFiles % exchange, ' w ' , ' utf-8 ' )
count = 0
sln.open(ExchangeUrlMap[exchange])
time.sleep( 5 )
for j in range( 2 , 200 ):
if sln.is_element_present(ExchangeXPath % j):
context = sln.get_text(ExchangeXPath % j).strip()
print >> myfile, context, ' \r '
count = count + 1
else : break
print " %s companies for exchange %s recorded. " % (count, exchange)
sln.stop()
exchangelist = [ " CCS " ] # "SHA_A","SHA_B","SHE_A","SHE_B","SHA_Q","SHA_CEF","SHE_CEF","SHA_Bond","SHE_Bond"
for exchange in exchangelist:
print exchange
resultFiles = " Ifeng_company_list_%s.txt "
IfengFinanceSite().GetAllTickers(exchange, resultFiles)
之后启动Selenium服务,调动浏览器就能获取所有中国概念股股票代码,如果还需要其他的信息如名称、价格,只需要取得Xpath就行了。
再扩展开就是可以用Selenium做diff工具了,前后版本的对比,自有产品与竞争对手信息的对比。
当然,Selenium RC因为要调出浏览器,所以效率还是很一般,可以考虑用Selenium其他产品。