Feature/driver

.gitignore

@@ -11,4 +11,5 @@ test.ipynb
 
 driver/.DS_Store
 
-interface
+interface
+config\chromedriver.exes

Driver.py

@@ -1,5 +1,6 @@
 from selenium import webdriver
 from selenium.webdriver.chrome.options import Options
+from selenium.common.exceptions import SessionNotCreatedException
 from Resolvers import PathResolver
 from platform import system
 
@@ -51,10 +52,11 @@ def __init__(
             executable_path=self.driver_directory,
             options=chrome_options
         )
-
+        
         driver.set_window_size(1440, 900)
         self._driver = driver
 
     def driver(self):
         return self._driver
 
+

GoogleTrend.py

@@ -3,6 +3,7 @@
 from platform import system
 
 from selenium import webdriver
+from selenium.common.exceptions import NoSuchElementException
 # from selenium.webdriver.chrome.options import Options
 # from selenium.webdriver.common.by import By
 import pandas as pd
@@ -97,6 +98,8 @@ def _download(self, failed:int=0):
             print('Done (成功)')
 
             return True
+        except NoSuchElementException:
+            return self.no_error()
         except:
             s = randint(2, 5)
             print(f'Failed (失敗) ··· 休眠約 {s}s 後喚醒')

Stock.py

@@ -28,15 +28,15 @@ def scrapping_per_week(self):
                 print(f'\n正在抓取 {self.origin_q} {self.key} {cy}年 週資料···')
                 url = f'{self.url}?date={cy}-01-01%20{cy}-12-31&q={self.q}{geo_query}{cat_query}'
                 self._toPage(url)
-                if self.no_error():
-                    self._download()
+                # if self.no_error():
+                self._download()
 
             elif sequence_type == 'cross-year':
                 print(f'\n正在抓取 {self.origin_q} {self.key} {cy}年 跨 {cy+1}年 週資料···')
                 url = f'{self.url}?date={cy}-07-01%20{cy+1}-6-30&q={self.q}{geo_query}{cat_query}'
                 self._toPage(url)
-                if self.no_error():
-                    self._download()
+                # if self.no_error():
+                self._download()
             cy += 1
 
     def merge_per_week(self):
@@ -105,8 +105,8 @@ def _0_or_1(i: int):
                 url += f'date={cy}-{iTs(sm)}-01%20{cy}-{iTs(sm+5)}-3{_0_or_1(sm+5)}&q={self.q}{geo_query}{cat_query}'
                 sm += 6
                 self._toPage(url)
-                if self.no_error():
-                    self._download()
+                if not self._download():
+                    continue
                 sleep(rd_ms())
             cy += 1
             sm = 1
@@ -163,8 +163,7 @@ def scrapping_per_month(self):
         print(f'\n正在抓取 {self.origin_q} {self.key} {2004}年 跨 {current_year}年 月資料···')
         url = f'{self.url}?date={start_date}%20{current_date}&q={self.q}{geo_query}{cat_query}'
         self._toPage(url)
-        if self.no_error():
-            self._download()
+        self._download()
 
     def merge_per_month(self):
         print(f'\n正在合併月資料 ···')
@@ -207,7 +206,7 @@ def has_set_ticker_detail(self) -> (bool):
                     if text == self.origin_q:
                         key = splited_elements
             print(key)
-            sleep(1)
+            sleep(0.5)
 
             if key:
                 if self.origin_q == key[1]:

Updater.py

@@ -1,12 +1,30 @@
+from selenium import webdriver
 from Resolvers import PathResolver
 from Driver import Driver
+from time import sleep
+from selenium.common.exceptions import NoSuchElementException
 
 class DriverUpdater:
     def __init__(self):
         self._get_driver()
 
-    def _get_driver(self):
+    def _get_driver(self) -> (webdriver.chrome.webdriver.WebDriver):
         download_pr = PathResolver(['download'], mkdir=True)
-        self.driver = Driver(
-            download_directory=download_pr.path()
-        )
+        self.updater = Driver(
+            download_directory=download_pr.path(),
+            headless=False
+        ).driver()
+
+    def to_page(self, url:str):
+        self.updater.get(url=url)
+        sleep(1)
+
+    def check_version(self):
+        try:
+            judgment = self.updater.find_element_by_css_selector(
+            "#content-base > section.section-block.section-block-main-extra > div > div.content-block-main > div.judgment.judgment-bad")
+            print(judgment.text)
+        except NoSuchElementException:
+            self.updater.close();
+            print('Done!')
+

cli.py

@@ -7,7 +7,7 @@
 from Resolvers import PathResolver
 from pandas import read_csv
 from selenium.common.exceptions import SessionNotCreatedException
-# from Driver import DriverUpdater
+from Updater import DriverUpdater
 
 class SVI_CLI:
     def __init__(self, config):
@@ -211,18 +211,22 @@ def google_trend_cli(self):
 
 
     def taiwan_stock_cli(self):
-        # try:
-        while True:
-            if not self.google_trend_cli():
-                break
-        # except SessionNotCreatedException:
-            # print('ChromeDriver 版本過期，請更新版本。')
-            # updater = DriverUpdater()
+        try:
+            while True:
+                if not self.google_trend_cli():
+                    break
+        except SessionNotCreatedException:
+            print('\n[ChromeDriver]: ChromeDriver版本過期，請更新版本。\n')
+            print('[Info]: \"Ctrl + 滑鼠左鍵\" 點擊以下網址，查看版本資訊')
+            print('https://www.whatismybrowser.com/detect/what-version-of-chrome-do-i-have\n')
+            print('[Info]: \"Ctrl + 滑鼠左鍵\" 點擊以下網址，下載最新版本的 chromedriver')
+            print('https://chromedriver.chromium.org/downloads\n')
+            input('輸入 Enter 結束')
             # handle driver updating...
-        # except:
-            # print('\n中斷爬蟲中')
-            # dot(1)
-            # self.save()
+        except:
+            print('\n中斷爬蟲中')
+            dot(1)
+            self.save()
 
         print('\n----- 系統將在 2 秒後自動關閉視窗，或是手動點擊右上角離開視窗 ··· -----')
         sleep(1)

config/config.json

@@ -1 +1 @@
-{"geo":{"0":"TW"},"txt":{"0":true},"cat":{"0":true},"day":{"0":true},"week":{"0":true},"month":{"0":true},"cross_year":{"0":true},"all_year_range":{"0":false},"prevent_spamming":{"0":true},"table.columns_name":{"0":["ticker","company","date","Raw_SVI","Adj_raw_SVI","median","Adjust_SVI"]},"median_range.week":{"0":8},"median_range.month":{"0":8}}
+{"geo":{"0":"TW"},"txt":{"0":true},"cat":{"0":true},"day":{"0":false},"week":{"0":true},"month":{"0":false},"cross_year":{"0":true},"all_year_range":{"0":false},"prevent_spamming":{"0":true},"table.columns_name":{"0":["ticker","company","date","Raw_SVI","Adj_raw_SVI","median","Adjust_SVI"]},"median_range.week":{"0":8},"median_range.month":{"0":8}}

main.py

@@ -2,6 +2,8 @@
 from config import tw_stock_config
 from datetime import datetime
 from utils import dot
+from Updater import DriverUpdater
+from selenium.common.exceptions import SessionNotCreatedException
 
 
 def main():
@@ -12,6 +14,13 @@ def main():
     print('\n----- 若要背景執行大量資料爬蟲，請將系統 *螢幕保護 或 *休眠關閉，否則可能造成資訊中斷而損失資料 -----')
     dot(.5)
 
+    try:
+        updater = DriverUpdater()
+        updater.to_page(url="https://www.whatismybrowser.com/detect/what-version-of-chrome-do-i-have")
+        updater.check_version()
+    except SessionNotCreatedException:
+        print('session created failed~')
+
     config = tw_stock_config()
 
     svi = SVI_CLI(config=config)