# import requests
# from bs4 import BeautifulSoup
# from selenium import webdriver
# import time
# import os
# from datetime import datetime
# import csv
# from selenium.webdriver.common.keys import Keys
# import random
# from selenium.webdriver import ActionChains
#
# import json
# import hashlib
# import base64
# import hmac
# from urllib.parse import quote_plus
# import socket
# import sys
# from selenium.webdriver.chrome.options import Options
# from selenium.webdriver.chrome.service import Service
# from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
# from selenium.webdriver.common.proxy import Proxy, ProxyType
# # 设置代理服务器
#
# 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
import time

from varargs_kong import *

sys.path.append(r"C:\多抓鱼\整合版本整合版本")



'''
更新记录：在1.1基础上新增利润和利润率过滤，符合要求的且没货的，且没加入书单的，点击加入书单
'''



#设置浏览器头
def create_proxyauth_extension(proxy_host, proxy_port,
                               proxy_username, proxy_password,
                               scheme='http', plugin_path=None):
    """Proxy Auth Extension

    args:
        proxy_host (str): domain or ip address, ie proxy.domain.com
        proxy_port (int): port
        proxy_username (str): auth username
        proxy_password (str): auth password
    kwargs:
        scheme (str): proxy scheme, default http
        plugin_path (str): absolute path of the extension

    return str -> plugin_path
    """
    import string
    import zipfile

    if plugin_path is None:
        plugin_path = 'Selenium-Chrome-HTTP-Private-Proxy.zip'

    manifest_json = """
    {
        "version": "1.0.0",
        "manifest_version": 2,
        "name": "Chrome Proxy",
        "permissions": [
            "proxy",
            "tabs",
            "unlimitedStorage",
            "storage",
            "<all_urls>",
            "webRequest",
            "webRequestBlocking"
        ],
        "background": {
            "scripts": ["background.js"]
        },
        "minimum_chrome_version":"22.0.0"
    }
    """

    background_js = string.Template(
        """
        var config = {
                mode: "fixed_servers",
                rules: {
                  singleProxy: {
                    scheme: "${scheme}",
                    host: "${host}",
                    port: parseInt(${port})
                  },
                  bypassList: ["foobar.com"]
                }
              };

        chrome.proxy.settings.set({value: config, scope: "regular"}, function() {});

        function callbackFn(details) {
            return {
                authCredentials: {
                    username: "${username}",
                    password: "${password}"
                }
            };
        }

        chrome.webRequest.onAuthRequired.addListener(
                    callbackFn,
                    {urls: ["<all_urls>"]},
                    ['blocking']
        );
        """
    ).substitute(
        host=proxy_host,
        port=proxy_port,
        username=proxy_username,
        password=proxy_password,
        scheme=scheme,
    )
    with zipfile.ZipFile(plugin_path, 'w') as zp:
        zp.writestr("manifest.json", manifest_json)
        zp.writestr("background.js", background_js)
    return plugin_path

#设置浏览器头配置函数
def configure_headless_browser(proxy_config):

    chrome_options = Options()

    prefs = {
        'profile.default_content_setting_values': {
            'images': 2
        }
    }
    chrome_options.add_experimental_option('prefs', prefs)

    chrome_options.add_argument('--disable-css-animation')
    chrome_options.add_argument('--disable-css-transitions')
    chrome_options.add_argument('--disable-javascript')

    chrome_options.add_argument("--start-maximized")
    proxyauth_plugin_path = create_proxyauth_extension(
        proxy_host=proxy_config[0],
        proxy_port=proxy_config[1],
        proxy_username=proxy_config[2],
        proxy_password=proxy_config[3]
    )
    chrome_options.add_extension(proxyauth_plugin_path)
    # chrome_options.add_argument('--headless')
    # chrome_options.add_argument(
    #     "user-agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36'")
    # chrome_service = Service("./chromedriver.exe")
    return webdriver.Chrome(options=chrome_options)


#设置浏览器
def open_chrome():
    # proxy = requests.get(
    #     "http://19157751061.user.xiecaiyun.com/api/proxies?action=getJSON&key=NP14F9A7FC&count=&word=&rand=false&norepeat=false&detail=false&ltime=&idshow=false")
    # j = json.loads(proxy.text)
    # p = j["result"][0]
    # proxyip = p["ip"]
    # proxyprot = str(p["port"])
    # # 设置代理IP
    # proxy_config = [proxyip, proxyprot, proxyusernm, proxypasswd]
    # # 启动浏览器
    # browser = configure_headless_browser(proxy_config)
    # return browser
    #user_data_dir = r'--user-data-dir=C:\Users\ZhuanZ\Local\Google\Chrome\User Data3'
    # # # 加载配置数据
    user_data_dir = r'--user-data-dir=C:\Users\S2020\AppData\Local\Google\Chrome\User Data3'
    option = webdriver.ChromeOptions()
    option.add_argument(user_data_dir)
    browser = webdriver.Chrome(chrome_options=option)  # => 注意这里的参数

    # browser = webdriver.Chrome()  # => 注意这里的参数
    # browser.get('https://www.duozhuayu.com/search/book')
    # browser.maximize_window()

    #browser = webdriver.Chrome()  # => 注意这里的参数

    return browser




    # #获取浏览器cookie
    # user_data_dir = r'--user-data-dir=C:\Users\S2020\AppData\Local\Google\Chrome\User Data'
    # # # # 加载配置数据
    # option = webdriver.ChromeOptions()
    # option.add_argument(user_data_dir)
    # browser = webdriver.Chrome(chrome_options=option)  # => 注意这里的参数
    # #
    #
    # #browser = webdriver.Chrome()  # => 注意这里的参数
    #
    # return browser




def get_now_date():
    # 获取当前日期和时间
    now = datetime.now()

    # 格式化日期和时间
    formatted_date = now.strftime("%Y%m%d")
    formatted_time = now.strftime("%H:%M:%S")

    # 输出格式化后的日期和时间
    #print("格式化后的日期：", formatted_date)
    return formatted_date



def get_bak_data(data,month_num):
    year = data[0:4]
    month = data[4:6]
    date = data[6:8]
    # print(year,month,date)
    if int(month) > month_num:
        bakmonth = int(month) - month_num
        if len(str(bakmonth)) == 1:
            bakmonth = '0' + str(bakmonth)
        else:
            bakmonth = str(bakmonth)
        new_date = year + bakmonth + date
    else:
        bakmonth = 12 - month_num + int(month)
        bakyear = int(year) - 1
        if len(str(bakmonth)) == 1:
            bakmonth = '0' + str(bakmonth)
        else:
            bakmonth = str(bakmonth)
        new_date = str(bakyear) + str(bakmonth) + str(date)
    return new_date

#日期
# date = int(get_bak_data(get_now_date(),month_num))


# def get_now_time():
#     # 获取当前日期和时间
#     now = datetime.now()
#
#     # 格式化日期和时间
#     formatted_date = now.strftime("%Y%m%d")
#     formatted_time = now.strftime("%H:%M")
#
#     # 输出格式化后的日期和时间
#     print("格式化后的日期：", formatted_time)
#     return formatted_time


def shop_url_comb(url_shop_id,url_page):
    '''
    获取获取店铺数据链接
    :param url_shop_id:
    :param url_page:
    :return:
    '''
    url_website = "http://shop.kongfz.com/"
    url_shop_id = str(url_shop_id)
    url_term = "/all/0_50_0_0_"
    url_page = url_page
    "http://shop.kongfz.com/472611/all/0_50_0_0_1_sort_desc_10_0/"
    #下面的30-200是价格过滤
    url_suffix = "_sort_desc_" + str(mix_price) +  "_0/"
    url = url_website + url_shop_id + url_term + str(url_page) + url_suffix
    return url


def get_book_name_isbn(url,url_shop_id):
    '''
    获取书籍信息和上书时间
    :param url:
    :param url_shop_id:
    :return:
    '''

    requests.adapters.DEFAULT_RETRIES = 5
    s = requests.session()
    s.keep_alive = False
    ret = requests.get(url, headers=headers)
    ret.encoding = ret.apparent_encoding
    soup = BeautifulSoup(ret.text, 'html.parser')
    book_names = soup.findAll(name='a',attrs={"class":"row-name"})  #获取书名
    book_content = []
    book_url = 'https://book.kongfz.com/'
    onload_book_final = 0

    for i in book_names:
        itemid = i['href'].replace(book_url+url_shop_id, '').replace('/', '')

        isbn = soup.find(name='div',attrs={"itemid":itemid})['isbn']
        # price =  soup.find(name='div',attrs={"itemid":itemid})['price']
        # price = price[price.find("￥")+1:]
        # price = price[:price.find("\n")]
        book_content.append(isbn)
    onload_time = soup.findAll(name='div',attrs={"class":"add-time-box"})
    for i in onload_time:
        onload_book_final = i.text
        onload_book_final = onload_book_final.replace("上书","")
        onload_book_final = onload_book_final.replace("-","")
    print("上书日期："+onload_book_final)
    return book_content,onload_book_final


def write_content_to_txt(contents,url):
    '''
    获取到的isbn写入表格
    :param contents:
    :param url:
    :return:
    '''
    url_csv = url + '.csv'
    with open(url_csv, 'a') as f:
        try:
            for i in contents[0]:
                print("contents:"+i)
                if len(i) == 13:
                
                # if len(i[0]) == 13 and i[1] > mix_number:
                    f.write(i)
                # f.write(',')
                # f.write(str(i[1]))
                    # f.write(',')
                    # f.write(str(i[2]))
                    # f.write(',')
                    # f.write(str(i[3]))
                    f.write('\n')
        except:
            print('continue')
    f.close()

def read_scv(path):
    '''
    获取表格文件内容
    :param path:
    :return:
    '''
    con = []
    with open(path, 'r') as f:
        content = csv.reader(f)
        for i in content:
            con.append(i)
        f.close()
        
    return con


def deal_shop_id(shop_list1,shop_list2):
    '''
    返回新的表格数据,更新表格
    :param shop_list1:已采集过的数据
    :param shop_list2:老的数据
    :return:
    '''
    new_list = []
    flag = 0
    for i in shop_list2:
        for j in shop_list1:
            if i[0] == j[0]:
                flag = 1
        if flag == 0:
            new_list.append(i)
        else:
            flag = 0
    for j in shop_list1:
        new_list.append(j)
    return new_list


def rm_shop_csv(path):
    '''
    获取删除文件
    :param path:
    :return:
    '''
    os.remove(path)

def write_new_csv(path,data):
    '''
    将店铺数据写入表格
    :param path:
    :param data:
    :return:
    '''
    f = open(path, 'a')
    for i in data:
        f.write(i[0])
        f.write(',')
        f.write(i[1])
        f.write(',')
        f.write(i[2])
        f.write('\n')




# def get_book_msg(url,browser):
#     '''
#     获取书籍信息，名称，出版社等
#     :param url:
#     :param browser:
#     :return:
#     '''
#     try:
#         browser.switch_to.window(Handles2[0])
#         # print("切换后的新窗口是：" + browser.title)
#         time.sleep(1)
#         browser.get(url)
#         browser.implicitly_wait(5)
#         browser.execute_script("window.stop()")
#         time.sleep(2)
#     except:
#         time.sleep(2)
#         return 0,'0',('0',"暂无出版社信息",'','0.00')
#     if browser.find_element_by_class_name("forbidden-con-box"):
#         print("出发告警")
#         return "forbidden"
#
#
#     global first_flag
#     if first_flag == 0:
#         first_flag = 1
#         time.sleep(10)
#
#     try:
#         result = browser.find_element_by_class_name("result-list")
#     except:
#         print("暂无出版社信息")
#         return 0,'0',('0',"暂无出版社信息",'','0.00')
#     #img = browser.find_element_by_id("mainInmg")
#
#     book_name = result.find_element_by_class_name("title").text
#     book_url = result.find_element_by_class_name("title").find_element_by_class_name("link").get_attribute("href")
#
#     for i in '\/:*?”<>|"':
#         book_name = book_name.replace(i,"")
#     book_name = book_name.replace(" ", "")
#     book_content = result.find_element_by_class_name( "zl-isbn-info").text
#
#     book_content = book_content[book_content.find('/')+1:].replace(" ","")
#     # print(book_content)
#     book_press = book_content[:book_content.find('/')]
#     book_content = book_content[book_content.find('/') + 1:].replace(" ","")
#     book_press_time = book_content[:book_content.find('/')]
#     sale_price = book_content[book_content.rfind("￥")+1:].replace(" ","")
#     # print(book_press,book_press_time,sale_price)
#
#     return book_name,book_press,book_press_time,sale_price,book_url


def get_book_sale(browser,url):
    try:
        browser.get(url)
        element = WebDriverWait(browser, 10).until(
            EC.presence_of_element_located((By.CLASS_NAME, 'sold-time'))
        )
        content = browser.find_elements_by_class_name("sold-time")
        num = 0

        # price_total = []
        for index, i in enumerate(content):
            # print(i.text)
            x = i.text.replace('-', '').replace(' 已售', '')
            if int(x) >= int(get_bak_data(get_now_date(),month_num)):
                num = num + 1
    except:
        num = 0
    print(num)
    return num


def get_book_sale_price(url,browser):
    '''
    获取价格
    :param url:
    :param browser:
    :param book_title:
    :return:
    '''
    try:
        browser.get(url)
        # time.sleep(6)

        element = WebDriverWait(browser, 10).until(
            EC.presence_of_element_located((By.CLASS_NAME, 'product-item-box'))
        )
        result_list = browser.find_element_by_class_name("product-item-box")
        price = float(result_list.find_element_by_class_name("price-info").text.replace("￥", ""))
        price2 = float(result_list.find_elements_by_class_name("price-info")[1].text.replace("￥", ""))
        price3 = float(result_list.find_elements_by_class_name("price-info")[2].text.replace("￥", ""))
        try:
            kuaidi = result_list.find_element_by_class_name("ship-fee-box").text
            if "包邮" not in kuaidi:
                kuaidi = float(kuaidi[kuaidi.index("￥") + 1:kuaidi.index(".") + 2])
            else:
                kuaidi = 0
        except:
            kuaidi = kuaidi_price

        try:
            kuaidi2 = result_list.find_elements_by_class_name("ship-fee-box")[1].text
            if "包邮" not in kuaidi2:
                kuaidi2 = float(kuaidi2[kuaidi2.index("￥") + 1:kuaidi2.index(".") + 2])
            else:
                kuaidi2 = 0
        except:
            kuaidi2 = kuaidi_price

        try:
            kuaidi3 = result_list.find_elements_by_class_name("ship-fee-box")[2].text
            if "包邮" not in kuaidi3:
                kuaidi3 = float(kuaidi3[kuaidi3.index("￥") + 1:kuaidi3.index(".") + 2])
            else:
                kuaidi3 = 0
        except:
            kuaidi3 = kuaidi_price
        price_final = 0
        price_final1 = price + kuaidi
        price_final2 = price2 + kuaidi2
        price_final3 = price3 + kuaidi3
        if price_final2 - price_final1 > 5:
            price_final = price_final2
        elif price_final3 - price_final2 > 5:
            price_final = price_final3
        else:
            price_final = price_final1

        print(price_final1, price_final2, price_final3)
        book_name = result_list.find_element_by_class_name("item-name").text
        book_press = result_list.find_elements_by_class_name("zl-info")[1].text
        book_press_time = result_list.find_elements_by_class_name("zl-info")[2].text

        return price_final
    except:
        return 0


index_404 = 0
sale_num_404 = 0

def get_book_content(book_con,browser):
    '''
    第二步，获取每个书籍的图片，作者，出版社,价格等信息
    :param url:
    :return:
    '''
    # url = "https://search.kongfz.com/item_result/?status=0&key="+book_con
    if len(book_con) == 13:
        # book_name = get_book_msg(url,browser)
        # if book_name == "forbidden":
        #     return "forbidden"
        try:
            url1 = 'https://search.kongfz.com/product/?keyword='
            url2 = '&quality=90~&quaSelect=2&page=1&actionPath=quality,sortType&sortType=7'
            url_t = url1 + str(book_con) + url2
            book_sale_price = get_book_sale_price(url_t, browser)
        except:
            book_sale_price = 0
        global index_404,sale_num_404
        if book_sale_price == 0:
            index_404 = index_404 + 1
        else:
            index_404 = 0
        print("------------------------------")
        print("book_sale_price："+str(book_sale_price))
        # print(type(book_sale_price))
        if book_sale_price < book_mix_price and book_sale_price >= 0:
            time.sleep(5)
            return False

        time.sleep(3)

        #获取已售数据
        sale_url1 = 'https://search.kongfz.com/product/?dataType=1&keyword='
        sale_url2 = '&sortType=10&page=1&actionPath=sortType'

        sale_url = sale_url1 + str(book_con) + sale_url2
        num = get_book_sale(browser,sale_url)
        print("sale_num:"+str(num))
        time.sleep(2)


        price_url1 = 'https://search.kongfz.com/product/?keyword='
        price_url2 = '&quality=90~&quaSelect=2&page=1&actionPath=quality,sortType&sortType=7'
        price_url = price_url1 + str(book_con) + price_url2



        if num == 0:
            sale_num_404 = sale_num_404 + 1
        else:
            sale_num_404 = 0

        #小谷吖数据
        if num >= mix_number:
            f = open("销量达标.csv", 'a')
            f.write(price_url)
            f.write(',')
            f.write(book_con)
            f.write(',')
            f.write(str(book_sale_price))
            f.write(',')
            f.write(str(num))
            f.write('\n')

        else:
            return False
    else:
        return False


def open_page():
    '''
    启动浏览器的基础工作，登录
    :return:
    '''
    browser = open_chrome()
    #browser = webdriver.Chrome()
    try:
        browser.get("https://www.kongfz.com/")
        time.sleep(5)
        action = ActionChains(browser)
        logon = browser.find_elements_by_class_name("item-info")[0]
        action.move_to_element(logon).perform()
        time.sleep(2)

        browser.find_element_by_class_name("login-btn").click()
        time.sleep(3)
        browser.switch_to.frame(browser.find_element_by_id("iframe_login"))
        time.sleep(1)

        global name_index

        if name_index == len(name_msg)-1:
            name_index = 0
        browser.find_element_by_id("username").send_keys(name_msg[0][0])
        time.sleep(0.5)
        browser.find_element_by_id("password").send_keys(name_msg[0][1])
        name_index = name_index + 1
        time.sleep(1)
        browser.find_element_by_class_name("autoLogin").click()
        time.sleep(1)
        browser.find_element_by_class_name("login_submit").click()
        time.sleep(2)
        browser.switch_to.default_content()
    except:
        print("")
    time.sleep(10)
    return browser


def get_shop_isbn(url,url_shop_id):

    '''
    获取店铺isbn
    :param url:
    :param url_shop_id:
    :return:
    '''

    ret = requests.get(url, headers=headers)
    ret.encoding = ret.apparent_encoding
    soup = BeautifulSoup(ret.text, 'html.parser')
    book_names = soup.findAll(name='a',attrs={"class":"row-name"})  #获取书名
    book_content = []
    book_url = 'https://book.kongfz.com/'
    for i in book_names:
        itemid = i['href'].replace(book_url+url_shop_id, '').replace('/', '')
        isbn = soup.find(name='div',attrs={"itemid":itemid})['isbn']
        # price =  soup.find(name='div',attrs={"itemid":itemid})['price']
        # price = price[price.find("￥")+1:]
        # price = price[:price.find("\n")]
        book_content.append(isbn)
    return book_content




def get_isbn_url(browser,sale_url):
    '''
    获取指定isbn的已售链接
    :return:
    '''
    shop_list = []
    browser.get(sale_url)
    element = WebDriverWait(browser, 10).until(
        EC.presence_of_element_located((By.CLASS_NAME, 'item-link'))
    )
    a = browser.find_elements_by_class_name("item-link")
    s = 0
    for i in a:
        if "https://book.kongfz.com/0/" in i.get_attribute("href"):
            print(i.get_attribute("href"))
            shop_list.append(i.get_attribute("href"))
            s = s + 1
        if s == 50:
            break
    return shop_list



def get_sale_shop_url(url):
    """
    根据已售数据获取店铺id
    :param url:
    :return:
    """
    shop_id = ""
    ret = requests.get(url,headers = headers)
    ret.encoding = ret.apparent_encoding
    soup = BeautifulSoup(ret.text, 'html.parser')
    book_head = soup.find(name='head')  # 获取书名
    book_metas = book_head.findAll(name='meta')
    book_meta = book_metas[1].findAll(name='meta')
    for i in book_meta:
        i = str(i)
        if "url=https://shop.kongfz.com/" in i:
            i = i[i.index("url=https://shop.kongfz.com/")+28:]
            i = i[:i.index("/")]
            shop_id = i
            break
    return shop_id
            # print(i)



def get_shop_msg(browser,url):
    '''
    获取店铺信息
    :param browser:
    :param url:
    :return:
    '''
    browser.get(url)
    element = WebDriverWait(browser, 10).until(
        EC.presence_of_element_located((By.CLASS_NAME, 'sale-count'))
    )

    sale_num = browser.find_element_by_class_name("sale-count").text
    sale_num = sale_num.replace("(","")
    sale_num = sale_num.replace(")","")
    sale_num = sale_num.replace("笔","")
    print(sale_num)

    url1 = url + "/all/"
    browser.get(url1)
    element = WebDriverWait(browser, 10).until(
        EC.presence_of_element_located((By.CLASS_NAME, 'crumbs-nav-start'))
    )
    tag = browser.find_elements_by_class_name("crumbs-nav-start")[-1].text
    shop_num = tag.replace("条结果","").replace(" ","")
    print(shop_num)
    print("\n")

    return sale_num,shop_num

# date_6 = int(get_bak_data(get_now_date(),6))


if __name__ == "__main__":
    #更新数据
    browser = open_page()
    shop_data = read_scv(shop_path)
    shop_new_data = []
    isbn_index = 0
    current_timestamp1 = int(time.time())
    for shop in shop_data:
        for i in range(1,6):
            try:
                isbns = get_shop_isbn(shop_url_comb(shop[0],i),shop[0])
                isbn_index = 0
            except:
                isbn_index = isbn_index + 1
            if isbn_index >2:
                isbn_index = 0
                print("重新打开网页避免网页崩溃。")
                # browser.quit()
                time.sleep(5)
                # browser = open_page()
            print(isbns)
            for isbn in isbns:
                time.sleep(3)
                sale_lists = []
                if isbn == "":
                    continue
                sale_url = "https://search.kongfz.com/product/?dataType=1&keyword=" + str(
                    isbn) + "&sortType=10&page=1&actionPath=sortType"
                try:
                    sale_lists = get_isbn_url(browser, sale_url)
                    isbn_index = 0
                except:
                    isbn_index = isbn_index + 1
                if isbn_index > 2:
                    isbn_index = 0
                    print("重新打开网页避免网页崩溃。")
                    # browser.quit()
                    time.sleep(5)
                    # browser = open_page()
                # print(sale_lists)
                shop_ids = []

                if sale_lists == []:
                    continue

                for shop_list in sale_lists:
                    try:
                        shop_id = get_sale_shop_url(shop_list)
                    except:
                        continue
                    print(shop_id)
                    url = "http://shop.kongfz.com/" + str(shop_id)
                    try:
                        sale_num, shop_num = get_shop_msg(browser, url)
                    except:
                        continue

                    if int(shop_num) >=100 and int(shop_num) <=shop_book_num:
                        print(shop_new_data)
                        if int(sale_num)/int(shop_num) >= shop_sale_num:
                            f = open("test.txt","a")
                            f.write(str(shop_id))
                            f.write('\n')
                            f.close()
                            shop_new_data= [[shop_id, str(int(get_bak_data(get_now_date(),6))), '8'],]

                            shiyong_shop_data = []

                            for shop in shop_new_data:
                                next = 0
                                s = 0
                                while 1:
                                    s = s + 1
                                    if s > 20:
                                        break
                                    try:
                                        contents = get_book_name_isbn(shop_url_comb(str(shop[0]), s), str(shop[0]))
                                        write_content_to_txt(contents, str(shop[0]))
                                        print(shop[0], '第' + str(s) + '页数据已采集完成')
                                    except:
                                        print("next")
                                        next = next + 1
                                        contents = [0, 0]
                                        # time.sleep(0.5)
                                    if next > 10:
                                        next = 0
                                        break
                                    if int(contents[1]) <= int(shop[1]):
                                        break
                                shiyong_shop_data.append([shop[0], get_now_date(), shop[2]])

                                try:
                                    book_isbns = read_scv(str(shop[0]) + '.csv')
                                    rm_shop_csv(shop[0] + '.csv')
                                except:
                                    book_isbns = []
                                # 读完一条数据直接删除加写入

                                data = deal_shop_id(shiyong_shop_data, shop_data)
                                print(data)
                                f = open(shop_path, "w")
                                f.close()
                                write_new_csv(shop_path, data)
                                shiyong_shop_data = []

                                sousuo_flag = 0
                                sleep_time = 0
                                index_sousuo = 0

                                for book_isbn in book_isbns:
                                    # current_timestamp2 = int(time.time())
                                    # if current_timestamp2 - current_timestamp1 >= 3600:
                                    #     current_timestamp1 = current_timestamp2

                                    time.sleep(random.randint(4, 6))



                                    if index_404 > 10:
                                        # time.sleep(60)
                                        index_404 = 0
                                        sale_num_404 = 0
                                        index_sousuo = 0
                                        time.sleep(600)
                                        browser.quit()
                                        time.sleep(6)
                                        browser = open_page()

                                    if sale_num_404 > 10:
                                        # time.sleep(60)
                                        index_404 = 0
                                        sale_num_404 = 0
                                        index_sousuo = 0
                                        time.sleep(600)
                                        browser.quit()
                                        time.sleep(6)
                                        browser = open_page()

                                    sousuo_flag = sousuo_flag + 1
                                    print("isbn" + book_isbn[0])
                                    if len(book_isbn[0]) != 13:
                                        continue
                                    try:
                                        result = get_book_content(book_isbn[0], browser)
                                        index_sousuo = index_sousuo + 1
                                        if index_sousuo %100 == 0:
                                            time.sleep(random.randint(60, 120))
                                        f = open("sousuo.txt","a",encoding="utf-8")
                                        f.write(str(datetime.now()) +": " + str(index_sousuo))
                                        f.write("\n")
                                        f.close()

                                        print("采集数量："+ str(index_sousuo))
                                        if result == "forbidden":
                                            print("重新打开网页避免网页崩溃。")
                                            # browser.quit()
                                            time.sleep(30)
                                            # browser = open_page()

                                        # sleep_time = sleep_time + 1
                                    except:
                                        print("重新打开网页避免网页崩溃。")
                                        # browser.quit()
                                        # time.sleep(30)
                                        # browser = open_page()

                                        continue
                                    # print ("多抓鱼对比通过数量:"+str(duozhuayu_flag),"通过isbn搜索数量："+str(isbn_num))

                                    # if sousuo_flag % 100 == 0:
                                    #     print("重新打开网页避免网页崩溃。")
                                    #     browser.quit()
                                    #     time.sleep(120)
                                    #     browser = open_page()