# coding=utf-8

import os

import re

from selenium import webdriver

# from pyvirtualdisplay import Display

from selenium.webdriver.chrome.options import Options

from datetime import datetime,timedelta

import time

from pyquery import PyQuery as pq

import re

import datetime

class consumer:

    def __init__(self):

        #通过配置文件获取IEDriverServer.exe路径

        # IEDriverServer ='C:\Program Files\Internet Explorer\IEDriverServer.exe'

        # self.driver = webdriver.Ie(IEDriverServer)

        # self.driver.maximize_window()

        # self.driver = webdriver.PhantomJS(service_args=['--load-images=false'])

        # self.driver = driver = webdriver.Chrome()

        chrome_options = Options()

        chrome_options.add_argument('--headless')

        chrome_options.add_argument('--no-sandbox')

        chrome_options.add_argument('--disable-dev-shm-usage')

        chrome_options.add_argument('--disable-gpu')

        self.driver = webdriver.Chrome(chrome_options=chrome_options)

        # options = webdriver.FirefoxOptions()

        # # options.set_headless()

        # options.add_argument('--headless')

        # options.add_argument('--disable-gpu')

        # self.driver = webdriver.Firefox(firefox_options=options)

        # self.driver.set_page_load_timeout(10)

        # self.driver.maximize_window()

        # display = Display(visible=0, size=(800, 600))

        # display.start()

        # self.driver = webdriver.Firefox()

        # self.driver.maximize_window()

    def WriteLog(self, message,date):

        dir = os.path.join(os.getcwd(), 'consumer1')

        if not os.path.exists(dir):

            os.mkdir(dir)

        fileName = os.path.join(dir, date  +   '.txt')

        with open(fileName, 'a') as f:

            f.write(message)

    # http://search.cctv.com/search.php?qtext=消费主张&type=video

    def CatchData(self,url='http://search.cctv.com/search.php?qtext=%E6%B6%88%E8%B4%B9%E4%B8%BB%E5%BC%A0&type=video'):

        error = ''

        try:

            self.driver.get(url)

            selenium_html = self.driver.execute_script("return document.documentElement.outerHTML")

            doc = pq(selenium_html)

            message = '{0},{1}'.format( '标题', '时间')

            filename = datetime.datetime.now().strftime('%Y-%m-%d')

            self.WriteLog(message, filename)

            pages = doc("div[class='page']").find("a")

            # 2018-06-05 00:12:21

            pattern = re.compile("\d{4}-\d{2}-\d{2}\s\d{2}:\d{2}:\d{2}")

            for index in range(1,6):

                url = "get_data('{0}', '消费主张', 'relevance', 'video', '-1', '1', '', '20', '1')".format(index)

                self.driver.execute_script(url)

                selenium_html = self.driver.execute_script("return document.documentElement.outerHTML")

                doc = pq(selenium_html)

                print(index)

                try:

                    Elements = doc("div[class='jvedio']").find("a")

                    for sub in Elements.items():

                        title = sub.attr('title')

                        print(title)

                        ts = pattern.findall(title)

                        strtime = ''

                        if ts and len(ts) == 1:

                            strtime = ts[0]

                        if strtime:

                            index1 = title.index(strtime)

                            title = str(title[0:index1]).replace("•","")

                        title = '\n{0},{1}'.format(title, strtime)

                        self.WriteLog(title, filename)

                except Exception as e:

                    print("OS error: {0}".format(e))

        except Exception as e1:

            error = "ex"

# python "C:\Program Files (x86)\JetBrains\PyCharm 2016.2.3\helpers\pydev\setup_cython.py" build_ext --inplace

obj = consumer()

obj.CatchData()

# obj.CatchContent('')

# obj.export('')