[Python爬虫] 之一 ： Selenium+Phantomjs动态获取网站数据信息

　　本人刚才开始学习爬虫，从网上查询资料，写了一个利用Selenium+Phantomjs动态获取网站数据信息的例子，当然首先要安装Selenium+Phantomjs，具体的看

http://www.cnblogs.com/shaosks/p/6526817.html   Selenium下载： https://pypi.python.org/pypi/selenium/

phantomjs使用参考：http://javascript.ruanyifeng.com/tool/phantomjs.html 及官网：http://phantomjs.org/quick-start.html

 源代码如下：

# coding=utf-8
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import selenium.webdriver.support.ui as ui
from selenium.webdriver.common.action_chains import ActionChains
import time
import re
import os

class Crawler:
    def __init__(self, firstUrl = "https://list.jd.com/list.html?cat=9987,653,655",
                 nextUrl = "https://list.jd.com/list.html?cat=9987,653,655&page=%d&sort=sort_rank_asc&trans=1&JL=6_0_0#J_main"):
        self.firstUrl = firstUrl
        self.nextUrl = nextUrl

    def getDetails(self,pageIndex,id = "plist"):
        '''
        获取详细信息
        :param pageIndex: 页索引
        :param id: 标签对应的id
        :return:
        '''
        element = self.driver.find_element_by_id(id)
        txt = element.text.encode('utf8')
        items = txt.split('¥')

        for item in items:
            if len(item) > 0:
                details = item.split('\n')
                print '¥' + item
                # print '单价：¥'+ details[0]
                # print '品牌：' + details[1]
                # print '参与评价：' + details[2]
                # print '店铺：' + details[3]
        print ' '
        print '第 ' + str(pageIndex) + '页'

    def CatchData(self,id = "plist",totalpageCountLable = "//span[@class='p-skip']/em/b"):
        '''
        抓取数据
        :param id:获取数据的标签id
        :param totalpageCountLable:获取总页数标记
        :return:
        '''
        start = time.clock()
        self.driver = webdriver.PhantomJS()
        wait = ui.WebDriverWait(self.driver, 10)
        self.driver.get(self.firstUrl)
        #在等待页面元素加载全部完成后才进行下一步操作
        wait.until(lambda driver: self.driver.find_element_by_xpath(totalpageCountLable))
        # 获取总页数
        pcount = self.driver.find_element_by_xpath(totalpageCountLable)
        txt = pcount.text.encode('utf8')
        print '总页数：' + txt
        print '第1页'
        print ' '
        pageNum = int(txt)
        pageNum = 3  # 只执行三次
        i = 2
        while (i <= pageNum):
            self.getDetails(i,id)
            print ' '
            time.sleep(5)  # 延迟5秒,防止获取数据过快而被封ＩＰ
            wait = ui.WebDriverWait(self.driver, 10)
            self.driver.get(self.nextUrl % i)
            # driver.find_element_by_id("submit").click()
            i = i + 1
        else:
            print 'Load Over'
        end = time.clock()
        print "Time: %f s" % (end - start)

def main():
    # 首页的url
    firstUrl = "https://list.jd.com/list.html?cat=9987,653,655"
    #下一页的url
    nextUrl = "https://list.jd.com/list.html?cat=9987,653,655&page=%d&sort=sort_rank_asc&trans=1&JL=6_0_0#J_main"
    cw = Crawler(firstUrl, nextUrl)
    #总页数标签
    totalpageCountLable = "//span[@class='p-skip']/em/b"
    #获取数据的标签ID
    id = "plist"
    cw.CatchData(id,totalpageCountLable)
#测试
main()

参考：http://blog.csdn.net/eastmount/article/details/47907341