Selenimu做爬虫 oscarxie 博客园

classSeleniumUtil:
seleniums={}

defStartSeleniumForUrl(self,url):
sel=selenium("localhost",4444,"*chrome",url)
sel.start()
sel.set_timeout("90000")
returnsel

defGetSelenium(self,websiteName,url):
#ifwebsiteNameinself.seleniums:
#returnself.seleniums[websiteName]
self.seleniums[websiteName]=self.StartSeleniumForUrl(url)
returnself.seleniums[websiteName]

defStopSelenium(self,websiteName):
ifwebsiteNameinself.seleniums:
self.seleniums[websiteName].stop()

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]"

classIfengFinanceSite:

#resultfilefordiffexchanges
defGetAllTickers(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)

forjinrange(2,200):
ifsln.is_element_present(ExchangeXPath%j):
context=sln.get_text(ExchangeXPath%j).strip()
print>>myfile,context,'\r'
count=count+1
else:break
print"%scompaniesforexchange%srecorded."%(count,exchange)
sln.stop()

exchangelist=["CCS"]#"SHA_A","SHA_B","SHE_A","SHE_B","SHA_Q","SHA_CEF","SHE_CEF","SHA_Bond","SHE_Bond"
forexchangeinexchangelist:
printexchange
resultFiles="Ifeng_company_list_%s.txt"
IfengFinanceSite().GetAllTickers(exchange,resultFiles)