python3 selenium动态获取唯品会商品

# -*- coding:utf-8 -*-
import re
import urllib.request, urllib.parse, http.cookiejar
import os, time,re
import http.cookies
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException

##    说明
##         安装包
##  pip3 install bs4
##  pip3 install -U selenium
## 抓取不会变的网址用getHtml,否则getFirefox()


## 得到原始网页
def getHtml(url,daili=‘‘,postdata={}):
    """
    抓取网页：支持cookie
    第一个参数为网址，第二个为POST的数据
    """
    # COOKIE文件保存路径
    filename = ‘cookie.txt‘

    # 声明一个MozillaCookieJar对象实例保存在文件中
    cj = http.cookiejar.MozillaCookieJar(filename)
    # cj =http.cookiejar.LWPCookieJar(filename)

    # 从文件中读取cookie内容到变量
    # ignore_discard的意思是即使cookies将被丢弃也将它保存下来
    # ignore_expires的意思是如果在该文件中 cookies已经存在，则覆盖原文件写
    # 如果存在，则读取主要COOKIE
    if os.path.exists(filename):
        cj.load(filename, ignore_discard=True, ignore_expires=True)
    # 建造带有COOKIE处理器的打开专家
    proxy_support = urllib.request.ProxyHandler({‘http‘:‘http://‘+daili})
    # 开启代理支持
    if daili:
        print(‘代理:‘+daili+‘启动‘)
        opener = urllib.request.build_opener(proxy_support, urllib.request.HTTPCookieProcessor(cj), urllib.request.HTTPHandler)
    else:
        opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj))

    # 打开专家加头部
    opener.addheaders = [(‘User-Agent‘,
                          ‘Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5‘),
                        ]

    # 分配专家
    urllib.request.install_opener(opener)
    # 有数据需要POST
    if postdata:
        # 数据URL编码
        postdata = urllib.parse.urlencode(postdata)

        # 抓取网页
        html_bytes = urllib.request.urlopen(url, postdata.encode()).read()
    else:
        html_bytes = urllib.request.urlopen(url).read()

    # 保存COOKIE到文件中
    cj.save(ignore_discard=True, ignore_expires=True)
    return html_bytes


## 从火狐获取动态js，然后根据total得到页面数据，total表示全部，否则只能得到可视化的部分
def getFirefox(url,total=1,times=1):
        data=""
        browser = webdriver.Firefox()
        browser.get(url)
        time.sleep(times) 
        try:
            if total==1:
                data=browser.page_source
            else:
                data=browser.find_element_by_xpath("html").text
        except NoSuchElementException:
            print("神马都没有")
        return browser,data

def parse(data):
    # print(data)
    bai=re.compile(r‘<script>(.+)</script>‘)
    data=bai.match(data)
    if data:
        print(m.group())
    else:
        print("神马都没有")
    print(data)
    #var config = {...}
    #</script>
    # soup = BeautifulSoup(data, ‘html.parser‘) 
    # return soup.find_all("h4")



if __name__ == ‘__main__‘:
    for i in range(246,247):
        url = "http://list.vip.com/766479.html?q=0|0|0|0|0|2"
        browers,data=getFirefox(url,0)
        
        maindata=browers.find_element_by_id("J_wrap_pro_add").text
    
        print(maindata)
        browers.close()
        #browser.quit()
        # url = "http://list.vip.com/766479.html?q=0|0|0|0|0|2"
        # try:
        #     data =getHtml(url)
        #     data = data.decode(‘utf-8‘,"ignore")     
        #     data=parse(data)
        #     print(data)                                                  #解析网站用的
        # except Exception as e:
        #     if hasattr(e, ‘code‘):
        #         print(‘页面不存在或时间太长.‘)
        #         print(‘Error code:‘, e.code)
        #     elif hasattr(e, ‘reason‘):
        #         print("无法到达主机.")
        #         print(‘Reason:  ‘, e.reason)
        #     else:
        #         print(e)