Merge pull request #16 from roleecorn/dev

test version done

Author: roleecorn

logfile/.gitkeep

@@ -10,8 +10,9 @@
 import util
 import driver_control
 
-parser = argparse.ArgumentParser(description="這是一個簡單的範例 argparse 程式")
-parser.add_argument("--shop_name", help="提供一個名字作為參數", required=True)
+parser = argparse.ArgumentParser(description="自動飯用爬蟲程式")
+parser.add_argument("--shop_name", type=str, help="網站名稱", required=True)
+parser.add_argument("--test", action='store_true', help="測試選項，只進行一次運作")
 args = parser.parse_args()
 
 # 設定logging的配置
@@ -20,22 +21,38 @@
 myhome = Path.cwd()
 
 logging.basicConfig(
-    filename=myhome / 'logfile' / '{shop_name}.log',
+    filename=myhome / 'logfile' / f'{args.shop_name}.log',
     level=logging.INFO,
     format='%(asctime)s - %(levelname)s - %(message)s'
 )
 
-# 使用logging對象輸出日誌
-logging.info('This is a test message')
 
-a, b = util.read_csv(Path.cwd() / 'eddiebauer_test.csv')
 listsite, site_feature = util.read_csv(
-    (myhome / 'cite_file' / f'{args.shop_name}.csv').resolve())
+    (myhome / 'cite_file' / f'{args.shop_name}.csv'))
 with open('driver_path', 'r', encoding='big5') as f:
     tmp = f.read()
 driver = util.new_driver(myhome / tmp)
 with open('cite_fathers.json', 'r') as file:
     father: str = json.load(file)[args.shop_name]
+if args.test:
+    driver.get(url=listsite[0])
+    imgpath = util.check_imgpath(imgpath=myhome / args.shop_name,
+                                 imgfile=site_feature[0])
+    time.sleep(5)
+    driver_control.scroll_to_bottom_and_wait(driver=driver)
+    try:
+        parent_element = driver.find_element("class name", father)
+    except NoSuchElementException:
+        logging.error('element not find in parent_element')
+    try:
+        child_elements = parent_element.find_elements('xpath', "./*")
+    except NoSuchElementException:
+        logging.error('element not find in child_elements')
+    for element in child_elements:
+        tmp = util.capture(ele=element, path=imgpath)
+        print(tmp)
+    import sys
+    sys.exit()
 for i in len(listsite):
     driver.get(url=listsite[i])
     time.sleep(5)

main.py

@@ -1,4 +1,4 @@
 selenium
 webdriver-manager
-opencv-python
-pytesseract
+pytesseract
+Pillow

requirements.txt

@@ -13,11 +13,12 @@
 from .string_util import remove_non_alphanumeric, remove_non_number
 from .new_driver import new_driver
 from .check_imgpath import check_imgpath
-
+from .ele_capture import capture
 
 __all__ = ["read_csv",
            "new_driver",
            "remove_non_alphanumeric",
            "remove_non_number",
-           "check_imgpath"]
-__version__ = "0.1"
+           "check_imgpath",
+           "capture"]
+__version__ = "0.2"

util/__init__.py

@@ -1,6 +1,5 @@
 from selenium.webdriver.remote.webelement import WebElement
 from pathlib import Path
-from new_driver import new_driver
 import uuid
 
 
@@ -16,6 +15,7 @@ def capture(ele: WebElement, path: Path):
 
 if __name__ == "__main__":
     import time
+    from new_driver import new_driver
     myhome = Path.cwd().parent
     driver_path = myhome / '.wdm' / 'drivers' / 'chromedriver' / 'win32'
     driver_path = driver_path / '113.0.5672' / 'chromedriver.exe'