yield

import json
import os, sys
import random
import pandas as pd
import time
import urllib3
from pyvirtualdisplay import Display

urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
ABS_PATH = os.path.abspath(os.path.join(os.path.abspath(__file__), ".."))
sys.path.append(ABS_PATH)
TEST_PATH = os.path.join(ABS_PATH, 'test')
chrome_driver_path = os.getenv('executable_path')

from core.library.utils import LogManager
from core.library.common.storage_manager.blob import AzureBlob
from core.library.modules.requester import Requester
from core.library.utils import utils

CONTAINER_NAME = "regulation"

# -*- coding: utf-8 -*-
import sys, os
import re
import random
import time

import undetected_chromedriver as uc
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import Select
from bs4 import BeautifulSoup

ABS_PATH = os.path.abspath(os.path.join(os.path.abspath(__file__), "..", ".."))
DATASET_PATH = os.path.abspath(os.path.join(os.path.abspath(__file__), ".."))
sys.path.append(ABS_PATH)
sys.path.append(DATASET_PATH)
chrome_driver_path = os.getenv('executable_path')

from core.library.utils import LogManager, utils
from helper_class import *


class INTERFACING():

    def __init__(self):
        self.driver_initialized = False
        self.driver = ''
        self.MAX_TRIALS = 2
        self.chrome_version = utils.get_google_chrome_version()

    def make_soup(self):
        return BeautifulSoup(self.driver.page_source, 'lxml')  # etree.HTML()

    def current_url(self):
        return self.driver.current_url

    def get_driver(self):

        uc.TARGET_VERSION = utils.get_google_chrome_version()
        chrome_options = uc.ChromeOptions()
        # chrome_options.add_argument("--headless")
        chrome_options.add_argument("--window-size=1920.,1080")
        chrome_options.add_argument("--disable-extensions")
        chrome_options.add_argument("--disable-dev-shm-usage")
        chrome_options.add_argument("--disable-popup-blocking")
        chrome_options.add_argument("--profile-directory=Default")
        chrome_options.add_argument("--ignore-certificate-errors")
        chrome_options.add_argument("--disable-plugins-discovery")
        chrome_options.add_argument("--incognito")
        chrome_options.add_argument("--no-first-run")
        chrome_options.add_argument("--no-service-autorun")
        chrome_options.add_argument("--no-default-browser-check")
        chrome_options.add_argument("--password-store=basic")
        chrome_options.add_argument("--no-sandbox")
        chrome_options.add_argument('--disable-application-cache')
        chrome_options.add_argument('--disable-gpu')
        chrome_options.add_argument("--disable-setuid-sandbox")
        chrome_options.add_argument(
            "user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36"
        )
        self.driver = uc.Chrome(options=chrome_options, version_main=utils.get_google_chrome_version(),
                                driver_executable_path=chrome_driver_path)
        time.sleep(10)
        self.driver_initialized = True

    def close_driver(self):
        self.driver.quit()

    def get_selenium_response(self, url):
        soup_list=[]
        if not self.driver_initialized:
            self.get_driver()
        else:
            pass
        self.driver.get(url)
        time.sleep(3)
        # 找到下拉框元素
        select_ele = Select(self.driver.find_element_by_xpath("//*[@id='example_length']/label/select"))

        # 选择 100 条/页
        select_ele.select_by_value("100")
        time.sleep(5)
        soup = self.make_soup()
        soup_list.append(soup)
        num = 1
        while num < 107:
            try:
                next_page = self.driver.find_element_by_xpath('//*[@id="example_next"]/a')
                next_page.click()
                time.sleep(3)
                num += 1
                soup = self.make_soup()
                soup_list.append(soup)
            except:
                print('已到达最后一页，共爬取{}页'.format(num))
                break

    def get_page_source(self):
        return self.driver.page_source

    def clicking(self, xpath):
        elem = self.driver.find_element(By.XPATH, xpath)
        elem.click()
        time.sleep(random.randint(2, 3))

    def entering_values(self, xpath, value):
        elem = self.driver.find_element(By.XPATH, xpath)
        elem.clear()
        elem.send_keys(value)
        time.sleep(random.randint(2, 4))

    def send_keys(self, xpath):
        elem = self.driver.find_element(By.XPATH, xpath).send_keys(Keys.RETURN)

    def going_back(self):
        self.driver.execute_script("window.history.go(-1)")
        time.sleep(1)

    def refresh_page(self):
        self.driver.refresh()

    def close_handle(self):
        self.driver.close()

    def get_current_handle(self):
        return self.driver.current_window_handle

    def get_all_handles(self):
        return self.driver.window_handles

    def swtich_to_window(self, handle):
        self.driver.switch_to.window(handle)


class IndiaRegistrationRequester(Requester):
    def request(self):
        # with Display(visible=False, size=(1920, 1080)) as display:
        self.news_request(self.url)

    def news_request(self, url):
        """
        获取新闻更新页面及其对应详情页面中的所有数据
        url: 新闻更新页面url
        x_path: 翻页的xpath路径
        return: 返回更新页所有数据
        """
        soup_list = self.get_response(url)
        print(soup_list)
        self.content = pd.DataFrame()


    def get_response(self, link):
        soup_list = INTERFACING().get_selenium_response(link)
        return soup_list