# -*-  coding:utf-8 -*-
import re
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
import time
from pyquery import PyQuery as pq
from config_taobao import *
import pymongo

###数据库设置###
client = pymongo.MongoClient(MONGO_URL)
#client后的数据库用[]
db = client[MONGO_DB]

#公共参数
driver = webdriver.Chrome()
url = 'https://www.taobao.com'
wait = WebDriverWait(driver, 10)

def search():
    driver.get(url)
    #显式等待参考了官方api文档 http://selenium-python.readthedocs.io/waits.html
    searchbox = wait.until(EC.presence_of_element_located((By.ID, "q")))
    submit = driver.find_element_by_xpath('//*[@id="J_TSearchForm"]/div[1]/button')
    #下面是测试代码，验证提交按钮是否可用
    submit1 = wait.until(EC.element_to_be_clickable((By.XPATH,'//*[@id="J_TSearchForm"]/div[1]/button')))
#    print(submit1.text)
    #搜索关键字可以设置为用户收入，在公共参数表用Python的input函数
    searchbox.send_keys('美食')
    submit.click()
    #等待页面加载出搜索结果的总页数
    total = wait.until(EC.presence_of_element_located((By.XPATH,'//*[@class="total"]')))
    #页码加载完成后，获取商品信息
    get_products()
    return total.text

def next_page(page_number):

    try:
        input = wait.until(EC.presence_of_element_located((By.XPATH,'//*[@id="mainsrp-pager"]/div/div/div/div[2]/input')))
        submit = driver.find_element_by_css_selector('#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit')#wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit')))
        input.clear()
        input.send_keys(page_number)
        #此处设置等待时间是因为我本地的网速过快，不休眠一下，无法正常点击
        time.sleep(3)
        submit.click()
        time.sleep(3)
        #验证输入页页码和高亮页是否匹配
        wait.until(
            EC.text_to_be_present_in_element(
                (By.CSS_SELECTOR,'#mainsrp-pager > div > div > div > ul > li.item.active > span'),str(page_number)
            )
        )
        get_products()
    #下面的异常抓取是函数递归，点击确定按钮失败后，重新加载此函数
    except TimeoutException:
        next_page(page_number)

def get_products():
    #pyquery的用法，我也不是很了解，后续加强学习，现在知道这么用
    wait.until(
        EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-itemlist .items .item'))
    )
    html = driver.page_source
    doc = pq(html)
    items = doc('#mainsrp-itemlist .items .item').items()
    for item in items:
        product = {
            'image':item.find('.pic .img').attr('src'),
            'price':item.find('.price').text().strip()[3:],
            'name':item.find('.title').text(),
            'shopname':item.find('.shop').text()

        }
        print(product)
        save_product_info(product)

##保存信息至MongoDB
def save_product_info(result):
    if db[MONGO_Table].insert(result):
        print('存储成功')

def main():
    total = search()
    total = int(re.compile('(\d+)').search(total).group(1))
    print(total)
    for i in range(2,total+1):
        next_page(i)

if __name__ == '__main__':
    main()

# -*-  coding:utf-8 -*-

MONGO_URL = 'localhost'
MONGO_DB = 'taobao'
MONGO_Table = 'product'