selenium爬商品淘宝信息

from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
from urllib.parse import quote
from pyquery import PyQuery as pq
import pymongo

browser = webdriver.Chrome()
#初始化
wait = WebDriverWait(browser,10)
#显示等待，时间设为10s
keyword = 'ipad'
#关键词

def index_page(page):
    print('正在爬取第',page,'页')
    try:
         url = "https://s.taobao.com/search?q=" + quote(keyword)
         browser.get(url)
         if page > 1:
             input = wait.until(EC.presence_of_all_elements_located((By.CSS_SELECTOR,'#mainsrp-pager div.form > input')))
             #传入搜素框的条件及定位元组
             submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'#mainsrp-pager div.form > span.btn.J_Submit')))
             #定位和获取确定按钮
             input.clear()
             #清空输入框
             input.send_keys(page)
             #输入页码
             submit.click()
             #点击确定
         wait.until(EC.text_to_be_present_in_element((By.CSS_SELECTOR,'#mainsrp-page li.item.active > span'),str(page)))
         #等待商品块信息加载
         wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'.m-itemlist .items .item')))
         #等待商品信息加载
         get_products()
    except TimeoutException:
        index_page(page)

#解析商品列表
def get_products():
    html = browser.page_source
    doc = pq(html)
    #构造pyquery解析对象，CSS解析器提取商品列表
    items = doc('#mainsrp-itemlist .items .item').items()
    for item in items:
        product = {
            'image':item.find('.pic .img').attr('data-src'),
            'price':item.find('price').text(),
            'deal':item.find('deal-cnt').text(),
            'title':item.find('.title').text(),
            'shop':item.find('.shop').text(),
            'location':item.find('location').text()
        }
        print(product)
        save_to_monge(product)

#保存到MongoDB
MONGO_URL = 'lacalhost'
MONGO_DB = 'taobao'
MONGO_COLLECTION = 'products'

client = pymongo.MongoClient(MONGO_URL)
db = client.MONGO_DB
#创建MongoDB的连接对象，并指定数据库

def save_to_mongo(result):
    try:
        if db[MONGO_COLLECTION].insert(result):
            print('存储到MongoDB成功')
    except Exception:
        print('存储到MongoDB失败')
#保存结果到MongoDB

max_page = 100
def main():
    for i in range(1,max_page):
        index_page(i)

main()

登录问题需要解决，我研究研究！