phantomjs 抓取房产信息

　　　　抓取https://sf.taobao.com/item_list.htm信息

　　　　

　　　　

　　　　driver=webdriver.PhantomJS(service_args=['--ssl-protocol=any'])  
　　　　or
　　　　driver = webdriver.PhantomJS( service_args=['--ignore-ssl-errors=true'])
　　　　cur_driver=webdriver.PhantomJS(service_args=['--ssl-protocol=any', '--load-images=false']) 
　　　　
　　　　service_args=['--load-images=false']

　　抓取代码

# coding=utf-8
import os
import re
from selenium import webdriver
# from selenium.common.exceptions import TimeoutException
import selenium.webdriver.support.ui as ui
import time
from datetime import datetime
from selenium.webdriver.common.action_chains import ActionChains
import IniFile
# from threading import Thread
from pyquery import PyQuery as pq
import LogFile
import mongoDB
import urllib

class taobao(object):
    def __init__(self):
　　　　　　
        self.driver = webdriver.PhantomJS(service_args=['--ssl-protocol=any'])
        self.driver.set_page_load_timeout(10)
        self.driver.maximize_window()
        self.url ='https://sf.taobao.com/item_list.htm'



    def scrapy_date(self):
        try:
            self.driver.get(self.url)

            selenium_html = self.driver.execute_script("return document.documentElement.outerHTML")
            doc = pq(selenium_html)
            Elements = doc('ul[class="sf-pai-item-list"]').find('li[class="pai-item pai-status-doing"]')
            for element in Elements.items():
                priceinfo = element('div[class="info-section"]').find('p').text().encode('utf8').strip()
                title = element('div[class="header-section "]').find('p').text().encode('utf8').strip()
                print title
                print priceinfo
                print '--------------------------------------------------------------------------------'


        except Exception, e:
            print e.message
        finally:
            pass


obj = taobao()
obj.scrapy_date()

 　　抓取结果