Fit for MacOS Arm version

.temp_to_pub/EasySpider_MacOS_all_arch/Code/myChrome.py

@@ -12,6 +12,8 @@ from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
 from selenium.webdriver.support.ui import Select
 from selenium.webdriver import ActionChains
 from selenium.webdriver.common.by import By
+import sys
+
 desired_capabilities = DesiredCapabilities.CHROME
 desired_capabilities["pageLoadStrategy"] = "none"
 
@@ -89,9 +91,13 @@ class MyChrome(webdriver.Chrome):
         else:
             return super().find_elements(by=by, value=value)
 
-import sys
-if sys.platform != "darwin": # MacOS不支持Cloudflare
-    import undetected_chromedriver_ES as uc
+# MacOS不支持直接打包带Cloudflare的功能，如果要自己编译运行，可以把这个if去掉，然后配置好浏览器和driver路径
+if sys.platform != "darwin": 
+    ES = True
+    if ES: # 用自己写的ES版本
+        import undetected_chromedriver_ES as uc
+    else:
+        import undetected_chromedriver as uc
 
     class MyUCChrome(uc.Chrome):
 

.temp_to_pub/EasySpider_MacOS_all_arch/Code/utils.py

@@ -15,6 +15,7 @@ from urllib.parse import urlparse
 import pymysql
 from lxml import etree
 
+
 def is_valid_url(url):
     try:
         result = urlparse(url)
@@ -22,6 +23,7 @@ def is_valid_url(url):
     except ValueError:
         return False
 
+
 def lowercase_tags_in_xpath(xpath):
     return re.sub(r"([A-Z]+)(?=[\[\]//]|$)", lambda x: x.group(0).lower(), xpath)
 
@@ -30,10 +32,10 @@ def on_press_creator(press_time, event):
     def on_press(key):
         try:
             if key.char == 'p':
-                if press_time["is_pressed"] == False: # 没按下p键时，记录按下p键的时间
+                if press_time["is_pressed"] == False:  # 没按下p键时，记录按下p键的时间
                     press_time["duration"] = time.time()
                     press_time["is_pressed"] = True
-                else: # 按下p键时，判断按下p键的时间是否超过2.5秒
+                else:  # 按下p键时，判断按下p键的时间是否超过2.5秒
                     duration = time.time() - press_time["duration"]
                     if duration > 2:
                         if event._flag == False:
@@ -53,6 +55,7 @@ def on_press_creator(press_time, event):
             pass
     return on_press
 
+
 def on_release_creator(event, press_time):
     def on_release(key):
         try:
@@ -92,40 +95,45 @@ def on_release_creator(event, press_time):
 #         time.sleep(1)  # 每秒检查一次
 
 
-def download_image(url, save_directory):
+def download_image(browser, url, save_directory):
     # 定义浏览器头信息
     headers = {
         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
     }
     if is_valid_url(url):
-        # 发送 GET 请求获取图片数据
-        response = requests.get(url, headers=headers)
+        try:
+            # 发送 GET 请求获取图片数据
+            response = requests.get(url, headers=headers)
 
-        # 检查响应状态码是否为成功状态
-        if response.status_code == requests.codes.ok:
-            # 提取文件名
-            file_name = url.split('/')[-1].split("?")[0]
+            # 检查响应状态码是否为成功状态
+            if response.status_code == requests.codes.ok:
+                # 提取文件名
+                file_name = url.split('/')[-1].split("?")[0]
 
-            # 生成唯一的新文件名
-            new_file_name = file_name + '_' + \
-                str(uuid.uuid4()) + '_' + file_name
+                # 生成唯一的新文件名
+                new_file_name = file_name + '_' + \
+                    str(uuid.uuid4()) + '_' + file_name
 
-            # 构建保存路径
-            save_path = os.path.join(save_directory, new_file_name)
+                # 构建保存路径
+                save_path = os.path.join(save_directory, new_file_name)
 
-            # 保存图片到本地
-            with open(save_path, 'wb') as file:
-                file.write(response.content)
+                # 保存图片到本地
+                with open(save_path, 'wb') as file:
+                    file.write(response.content)
 
-            print("图片已成功下载到:", save_path)
-            print("The image has been successfully downloaded to:", save_path)
-        else:
-            print("下载图片失败，请检查此图片链接是否有效:", url)
-            print(
-                "Failed to download image, please check if this image link is valid:", url)
+                browser.print_and_log("图片已成功下载到:", save_path)
+                browser.print_and_log(
+                    "The image has been successfully downloaded to:", save_path)
+            else:
+                browser.print_and_log("下载图片失败，请检查此图片链接是否有效:", url)
+                browser.print_and_log(
+                    "Failed to download image, please check if this image link is valid:", url)
+        except Exception as e:
+            browser.print_and_log("下载图片失败|Error downloading image: ", e)
     else:
-        print("下载图片失败，请检查此图片链接是否有效:", url)
-        print("Failed to download image, please check if this image link is valid:", url)
+        browser.print_and_log("下载图片失败，请检查此图片链接是否有效:", url)
+        browser.print_and_log(
+            "Failed to download image, please check if this image link is valid:", url)
 
 
 def get_output_code(output):
@@ -141,9 +149,10 @@ def get_output_code(output):
 # 判断字段是否为空
 
 
-def isnull(s):
+def isnotnull(s):
     return len(s) != 0
 
+
 def new_line(outputParameters, maxViewLength, record):
     line = []
     i = 0
@@ -155,6 +164,7 @@ def new_line(outputParameters, maxViewLength, record):
     print("")
     return line
 
+
 def write_to_csv(file_name, data, record):
     with open(file_name, 'a', encoding='utf-8-sig', newline="") as f:
         f_csv = csv.writer(f)
@@ -167,6 +177,61 @@ def write_to_csv(file_name, data, record):
         f.close()
 
 
+def eval_repl(matchobj):
+     print(matchobj.group(1))
+     return str(eval(matchobj.group(1), globals(), locals()))
+
+
+
+def replace_field_values(orginal_text, outputParameters, browser=None):
+    pattern = r'Field\["([^"]+)"\]'
+    try:
+        replaced_text = re.sub(
+            pattern, lambda match: outputParameters.get(match.group(1), ''), orginal_text)
+        if replaced_text.find("EVAL") != -1: # 如果返回值中包含EVAL
+            replaced_text = replaced_text.replace("self.", "browser.")
+            replaced_text = re.sub(r'EVAL\("(.*?)"\)', lambda match: str(eval(match.group(1))), replaced_text)
+    except:
+        replaced_text = orginal_text
+    return replaced_text
+
+
+def write_to_json(file_name, data, types, record, keys):
+    keys = list(keys)
+    # Prepare empty list for data
+    data_to_write = []
+    # Tranform data and append to list
+    for line in data:
+        to_write = {}
+        for i in range(len(line)):
+            if types[i] == "int" or types[i] == "bigInt":
+                try:
+                    line[i] = int(line[i])
+                except:
+                    line[i] = 0
+            elif types[i] == "double":
+                try:
+                    line[i] = float(line[i])
+                except:
+                    line[i] = 0.0
+            if record[i]:
+                to_write.update({keys[i]: line[i]})
+        data_to_write.append(to_write)
+
+    try:
+        # read data from JSON
+        with open(file_name, 'r', encoding='utf-8') as f:
+            json_data = json.load(f)
+    except:
+        json_data = []
+
+    json_data.extend(data_to_write)
+
+    # write data to JSON
+    with open(file_name, 'w', encoding='utf-8') as f:
+        json.dump(json_data, f, ensure_ascii=False)
+
+
 def write_to_excel(file_name, data, types, record):
     first = False
     if os.path.exists(file_name):
@@ -180,7 +245,7 @@ def write_to_excel(file_name, data, types, record):
         first = True
     # 追加数据到工作表
     for line in data:
-        if not first: # 如果不是第一行，需要转换数据类型
+        if not first:  # 如果不是第一行，需要转换数据类型
             for i in range(len(line)):
                 if types[i] == "int" or types[i] == "bigInt":
                     try:
@@ -203,9 +268,6 @@ def write_to_excel(file_name, data, types, record):
     wb.save(file_name)
 
 
-
-
-
 class Time:
     def __init__(self, type1=""):
         self.t = int(round(time.time() * 1000))
@@ -223,28 +285,34 @@ class myMySQL:
             if sys.platform == "darwin":
                 if config_file.find("./") >= 0:
                     config_file = config_file.replace("./", "")
-                config_file = os.path.expanduser("~/Library/Application Support/EasySpider/" + config_file)
+                config_file = os.path.expanduser(
+                    "~/Library/Application Support/EasySpider/" + config_file)
             print("MySQL config file path: ", config_file)
             with open(config_file, 'r') as f:
                 config = json.load(f)
-                host = config["host"]
-                port = config["port"]
-                user = config["username"]
-                passwd = config["password"]
-                db = config["database"]
+                self.host = config["host"]
+                self.port = config["port"]
+                self.user = config["username"]
+                self.passwd = config["password"]
+                self.db = config["database"]
         except Exception as e:
-            print("读取配置文件失败，请检查配置文件："+config_file+"是否存在。")
-            print("Failed to read configuration file, please check if the configuration file: "+config_file+" exists.")
+            print("读取配置文件失败，请检查配置文件："+config_file+"是否存在，或配置信息是否有误。")
+            print("Failed to read configuration file, please check if the configuration file: " +
+                  config_file+" exists, or if the configuration information is incorrect.")
             print(e)
+        self.connect()
+        
+    def connect(self):
         try:
             self.conn = pymysql.connect(
-            host=host, port=port, user=user, passwd=passwd, db=db)
+                host=self.host, port=self.port, user=self.user, passwd=self.passwd, db=self.db)
             print("成功连接到数据库。")
             print("Successfully connected to the database.")
         except:
             print("连接数据库失败，请检查配置文件是否正确。")
-            print("Failed to connect to the database, please check if the configuration file is correct.")
-    
+            print(
+                "Failed to connect to the database, please check if the configuration file is correct.")
+
     def create_table(self, table_name, parameters):
         self.table_name = table_name
         self.field_sql = "("
@@ -253,7 +321,8 @@ class myMySQL:
         cursor.execute("SHOW TABLES LIKE '%s'" % table_name)
         result = cursor.fetchone()
 
-        sql = "CREATE TABLE " + table_name + " (_id INT AUTO_INCREMENT PRIMARY KEY, "
+        sql = "CREATE TABLE " + table_name + \
+            " (_id INT AUTO_INCREMENT PRIMARY KEY, "
         for item in parameters:
             if item["recordASField"]:
                 name = item['name']
@@ -309,25 +378,32 @@ class myMySQL:
                         line[i] = 0.0
                 elif types[i] == "datetime":
                     try:
-                        line[i] = datetime.datetime.strptime(line[i], '%Y-%m-%d %H:%M:%S')
+                        line[i] = datetime.datetime.strptime(
+                            line[i], '%Y-%m-%d %H:%M:%S')
                     except:
-                        line[i] = datetime.datetime.strptime("1970-01-01 00:00:00", '%Y-%m-%d %H:%M:%S')
+                        line[i] = datetime.datetime.strptime(
+                            "1970-01-01 00:00:00", '%Y-%m-%d %H:%M:%S')
                 elif types[i] == "date":
                     try:
-                        line[i] = datetime.datetime.strptime(line[i], '%Y-%m-%d')
+                        line[i] = datetime.datetime.strptime(
+                            line[i], '%Y-%m-%d')
                     except:
-                        line[i] = datetime.datetime.strptime("1970-01-01", '%Y-%m-%d')
+                        line[i] = datetime.datetime.strptime(
+                            "1970-01-01", '%Y-%m-%d')
                 elif types[i] == "time":
                     try:
-                        line[i] = datetime.datetime.strptime(line[i], '%H:%M:%S')
+                        line[i] = datetime.datetime.strptime(
+                            line[i], '%H:%M:%S')
                     except:
-                        line[i] = datetime.datetime.strptime("00:00:00", '%H:%M:%S')
+                        line[i] = datetime.datetime.strptime(
+                            "00:00:00", '%H:%M:%S')
             to_write = []
             for i in range(len(line)):
                 if record[i]:
                     to_write.append(line[i])
             # 构造插入数据的 SQL 语句
-            sql = f"INSERT INTO "+ self.table_name +" "+self.field_sql+" VALUES ("
+            sql = f"INSERT INTO " + self.table_name + \
+                " "+self.field_sql+" VALUES ("
             for item in to_write:
                 sql += "%s, "
             # 移除最后的逗号并添加闭合的括号
@@ -335,20 +411,28 @@ class myMySQL:
             # 执行 SQL 语句
             try:
                 cursor.execute(sql, to_write)
+            except pymysql.OperationalError as e:
+                print("Error:", e)
+                print("Try to reconnect to the database...")
+                self.connect()
+                cursor = self.conn.cursor() # 重新创建游标对象
+                cursor.execute(sql, to_write) # 重新执行SQL语句
+                # self.write_to_mysql(OUTPUT, record, types)
             except Exception as e:
                 print("Error:", e)
                 print("Error SQL:", sql, to_write)
                 print("插入数据库错误，请查看以上的错误提示，然后检查数据的类型是否正确，是否文本过长（超过一万的文本类型要设置为大文本）。")
                 print("Inserting database error, please check the above error, and then check whether the data type is correct, whether the text is too long (text type over 10,000 should be set to large text).")
                 print("重新执行任务时，请删除数据库中的数据表" + self.table_name + "，然后再次运行程序。")
-                print("When re-executing the task, please delete the data table " + self.table_name + " in the database, and then run the program again.")
+                print("When re-executing the task, please delete the data table " +
+                      self.table_name + " in the database, and then run the program again.")
 
         # 提交到数据库执行
         self.conn.commit()
 
         # 关闭游标和连接
         cursor.close()
-    
+
     def close(self):
         self.conn.close()
         print("成功关闭数据库。")

.temp_to_pub/EasySpider_MacOS_all_arch/First time open please see this.txt

@@ -2,4 +2,14 @@ Due to the complex security settings of MacOS, the issue of being unable to open
 
 https://github.com/NaiboWang/EasySpider/wiki/MacOS-Guide
 
+For the Arm version, if it shows "the package is damaged", you need to use the following command to modify the package attributes:
+
+xattr -cr Your EasySpider.app file path
+ 
+For example:
+
+xattr -cr /Users/username/Downloads/EasySpider_MacOS_all_arch/EasySpider.app
+ 
+Then try to open it again.
+
 File access permissions must be granted, microphone permissions are not necessary at all, and the author is not sure why microphone permissions are being requested, so they can be declined.

.temp_to_pub/EasySpider_MacOS_all_arch/第一次打开请看这个.txt

@@ -1,3 +1,13 @@
 由于MacOS复杂的安全性设置，初次打开软件会显示未验证开发者从而不允许打开的问题，请参考以下视频来查看MacOS版本如何打开软件和执行任务：https://www.bilibili.com/video/BV1WL411h71r
 
+对于Arm版本，如果显示“包已损坏”，则需要使用下面的命令修改包属性：
+
+xattr -cr 你的EasySpider.app文件路径
+
+如：
+
+Xattr -cr /Users/用户名/Downloads/EasySpider_MacOS_all_arch/EasySpider.app
+
+然后再次尝试打开。
+
 文件访问权限必须给，麦克风权限完全用不到，作者也不清楚为什么会需要麦克风，因此可以拒绝。

ElectronJS/package_macos.sh

@@ -7,8 +7,8 @@ cd ../../ElectronJS
 rm -rf out
 rm -r ../.temp_to_pub/EasySpider_MacOS_all_arch/EasySpider.app
 npm run make
-unzip out/make/zip/darwin/x64/EasySpider-darwin-x64* -d ../.temp_to_pub/EasySpider_MacOS_all_arch/
-# mv out/EasySpider-darwin-x64/EasySpider.app ../.temp_to_pub/EasySpider_MacOS_all_arch/
+unzip out/make/zip/darwin/*64/EasySpider-darwin* -d ../.temp_to_pub/EasySpider_MacOS_all_arch/
+# mv out/EasySpider-darwin-*64/EasySpider.app ../.temp_to_pub/EasySpider_MacOS_all_arch/
 rm ../.temp_to_pub/EasySpider_MacOS_all_arch/EasySpider.app/Contents/Resources/app/VS_BuildTools.exe
 rm -r ../.temp_to_pub/EasySpider_MacOS_all_arch/EasySpider.app/Contents/Resources/app/chrome_win64
 rm -r ../.temp_to_pub/EasySpider_MacOS_all_arch/EasySpider.app/Contents/Resources/app/chromedrivers

ExecuteStage/easyspider_executestage.py

@@ -1761,8 +1761,8 @@ class BrowserThread(Thread):
 
 
 if __name__ == '__main__':
-    # from multiprocessing import freeze_support
-    # freeze_support() # 防止无限死循环多开
+    from multiprocessing import freeze_support
+    freeze_support() # 防止无限死循环多开
     
     # 如果需要调试程序，请在命令行参数中加入--keyboard 0 来禁用键盘监听以提升调试速度
     # If you need to debug the program, please add --keyboard 0 in the command line parameters to disable keyboard listening to improve debugging speed

ExecuteStage/requirements.txt

@@ -1,7 +1,7 @@
 commandline_config==2.2.3
 requests==2.31.0
 selenium==4.5.0
-pyinstaller==5.9.0
+pyinstaller==5.13.2
 Pillow==9.4.0
 openpyxl==3.1.2
 pymysql==1.1.0

Extension/manifest_v3/src/content-scripts/config.json

@@ -1 +1 @@
-{"language":"en"}
+{"language":"zh"}