# -*- conding:utf-8 -*-

import requests,re
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from pyquery import PyQuery as pq

browers = webdriver.Chrome()
wait = WebDriverWait(browers, 10)
def search():
    try:
        browers.get('http://www.taobao.com/')
        input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#q')))
        sub = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'#J_TSearchForm > div.search-button > button')))
        input.send_keys('金融书籍')
        sub.click()
        page_num = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-pager > div > div > div > div.total')))
        list_content()
        return page_num.text
    except TimeoutException:
        return search()

def page_next(page_num):
    try:
        input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.form > input')))
        sub = 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_num)
        sub.click()
        wait.until(EC.text_to_be_present_in_element((By.CSS_SELECTOR,'#mainsrp-pager > div > div > div > ul > li.item.active > span'),str(page_num)))
        list_content()
    except TimeoutException:
        page_next(page_num)

def list_content():
    wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-itemlist > div > div')))
    html = browers.page_source
    doc = pq(html)
    items = doc('#mainsrp-itemlist > div > div').items() #得到所有选择的内容
    for item in items:
        content = {
            'image':item.find('.pic .img').attr('src'), #选择img的src属性。选择class或者标签在前面加.点，属性用attr
            'price':item.find('.price').text(),
            'deal':item.find('deal-cnt').text()[:-3],#切片，从最前面到倒数的三个字符删除
            'title':item.find('.title').text(),
            #'J_ClickStat':item.find('.J_ClickStat').attr('href'),
            #'shopinfo':item.find('.J_ShopInfo').attr('href'),
            'shop':item.find('.shop').text(),
            'location':item.find('.location').text()
        }
        print(content)

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


if __name__ == '__main__':
    main()

能正常运行，翻页，但是为啥没有print出内容呢？list_content()应该是把一些字段信息打印出来呀...