开发

使用python和selenium打开指定页面

#coding=utf-8
from selenium import webdriver
import time
import os
br=webdriver.Firefox()
baseurl=\"http://quote.eastmoney.com/\"
indexurl=\"stocklist.html\"
gourl=\"%s%s\"%(baseurl,indexurl)
br.get(gourl)
time.sleep(5)
br.quit()

获得该页全部股票链接代码

#coding=utf-8
from selenium import webdriver
import time
import os

def showlink(linklist):
    for x in linklist:
        print x.get_attribute(\'href\')
    print \"股票数:%d\"%(len(linklist))

br=webdriver.Firefox()
baseurl=\"http://quote.eastmoney.com/\"
indexurl=\"stocklist.html\"
gourl=\"%s%s\"%(baseurl,indexurl)
br.get(gourl)

shxpath=\"/html/body/div[9]/div[2]/div/ul[1]\"
szxpath=\"/html/body/div[9]/div[2]/div/ul[2]\"

shgupiao=br.find_element_by_xpath(shxpath)
szgupiao=br.find_element_by_xpath(szxpath)

shgupiaolist=shgupiao.find_elements_by_tag_name(\'a\')
szgupiaolist=szgupiao.find_elements_by_tag_name(\'a\')

showlink(shgupiaolist)
br.quit()

打开一个股票链接获得数据

#coding=utf-8
from selenium import webdriver
import time
import os
br=webdriver.Firefox()
gourl=\"http://quote.eastmoney.com/sz300401.html\"
gourlx=\"http://quote.eastmoney.com/sh166105.html\"
gourlxx=\"http://quote.eastmoney.com/sh201009.html\"
br.get(gourl)

hexinshujuxpath=\"/html/body/div[14]/div[1]/div[4]/div[1]\"
#原谅我用异常处里来代替了正常该进行判断的非股票类型数据吧
try:
    hexinshuju=br.find_element_by_class_name(\'pad5\')
    shujuhang=hexinshuju.find_elements_by_tag_name(\'tr\')
    print \"共有数据%d行\"%(len(shujuhang))
    for i in range(len(shujuhang)-2):
        shujulie=shujuhang[i].find_elements_by_tag_name(\'td\')
        print \"%s   %s\\n\"%(shujulie[0].text,shujulie[1].text)
    print \"%s\\n%s\"%(shujuhang[8].text,shujuhang[9].text)
except:
    print \"非股票数据放弃\"
finally:
    time.sleep(1)
    br.quit()