New Download Location

ElectronJS/src/taskGrid/FlowChart.html

@@ -191,6 +191,8 @@
                     <input spellcheck=false onkeydown="inputDelete(event)" class="form-control" v-model.number="nowNode['parameters']['scrollCount']" type="number" required></input>
                     <label>Wait time after scrolling (in seconds):</label>
                     <input spellcheck=false onkeydown="inputDelete(event)" class="form-control" v-model.number="nowNode['parameters']['scrollWaitTime']" type="number" required></input>
+                    <label>Maximum file download wait time (in seconds):</label>
+                    <input spellcheck="false" onkeydown="inputDelete(event)" class="form-control" v-model.number="nowNode['parameters']['downloadWaitTime']" type="number" required></input>
                     <label>Way to handle pop-up windows after clicking:</label>
                     <p><select v-model='nowNode["parameters"]["alertHandleType"]' class="form-control">
                         <option :value = 0>No pop-up window</option>
@@ -718,6 +720,7 @@ If the expression returns a value greater than 0 or evaluates to True, the opera
                     <select id="dataWriteMode" name="dataWriteMode" class="form-control">
                         <option value="1">Append (If the file exists, append to it)</option>
                         <option value="2">Overwrite (If the file exists, overwrite it)</option>
+                        <option value=3>Rename on Write (renames file if it already exists)</option>
                     </select>
 <!--                    <label>Is it an extreme anti-scraping website like Cloudflare (<a href="https://www.bilibili.com/video/BV1Ph4y1E7R9/" target="_blank">Watch Tutorial</a>)?</label>-->
 <!--                    <select id="cloudflare" name="cloudflare" class="form-control">-->

ElectronJS/src/taskGrid/FlowChart_CN.html

@@ -191,6 +191,8 @@
                     <input spellcheck=false onkeydown="inputDelete(event)" class="form-control" v-model.number="nowNode['parameters']['scrollCount']" type="number" required></input>
                     <label>滚动后等待时间（秒）：</label>
                     <input spellcheck=false onkeydown="inputDelete(event)" class="form-control" v-model.number="nowNode['parameters']['scrollWaitTime']" type="number" required></input>
+                    <label>文件下载最长等待时间（秒）：</label>
+                    <input spellcheck=false onkeydown="inputDelete(event)" class="form-control" v-model.number="nowNode['parameters']['downloadWaitTime']" type="number" required></input>
                     <label>点击元素后如有弹窗出现，弹窗处理方式：</label>
                     <p><select v-model='nowNode["parameters"]["alertHandleType"]' class="form-control">
                         <option :value = 0>无弹窗</option>
@@ -718,6 +720,7 @@ print(emotlib.emoji()) # 使用其中的函数。
                     <select id="dataWriteMode" name="dataWriteMode" class="form-control">
                         <option value=1>追加写入（如果文件已存在则在原文件后面追加）</option>
                         <option value=2>覆盖写入（如果文件已存在则覆盖原文件）</option>
+                        <option value=3>重命名写入（如果文件已存在则重命名文件）</option>
                     </select>
 <!--                    <label>是否为Cloudflare等极端反爬网站（<a href="https://www.bilibili.com/video/BV1Ph4y1E7R9/" target="_blank">查看Cloudflare设计和执行教程</a>）：</label>-->
 <!--                    <select id="cloudflare" name="cloudflare" class="form-control">-->

ElectronJS/src/taskGrid/logic.js

@@ -282,6 +282,7 @@ function addParameters(t) {
         t["parameters"]["afterJS"] = ""; //执行后执行的js
         t["parameters"]["afterJSWaitTime"] = 0; //执行后js等待时间
         t["parameters"]["alertHandleType"] = 0; //弹窗处理类型，1代表确认，2代表取消
+        t["parameters"]["downloadWaitTime"] = 3600; //下载等待时间
     } else if (t.option == 3) { //提取数据
         t["parameters"]["clear"] = 0; //清空其他字段数据
         t["parameters"]["newLine"] = 1; //生成新行

ElectronJS/src/taskGrid/taskList.html

@@ -63,7 +63,7 @@
         <el-table
                 style="width: 100%"
                 :empty-text="LANG('No Task~暂无任务')"
-                :data="list.filter(data => !search || (data.name.toLowerCase().includes(search.toLowerCase())) || (data.url.toLowerCase().includes(search.toLowerCase())) || (data.links.includes(search.toLowerCase())) || (data.desc.includes(search.toLowerCase())))"
+                :data="list.filter(data => !search || (data.name.toLowerCase().includes(search.toLowerCase())) || (data.url.toLowerCase().includes(search.toLowerCase())) || (data.links.includes(search.toLowerCase())) || (data.desc.includes(search.toLowerCase())) || (data.id.toString().includes(search.toLowerCase())))"
                 :default-sort="{prop: 'mtime', order: 'descending'}"
         >
 

ElectronJS/tasks/228.json

@@ -1 +1 @@
-{"id":228,"name":"[2312.02977] Exploring the nonclassical dynamics of the \"classical'' Schrödinger equation","url":"https://arxiv.org/abs/2312.02977","links":"https://arxiv.org/abs/2312.02977","create_time":"12/7/2023, 2:44:58 AM","update_time":"12/7/2023, 2:56:47 AM","version":"0.6.0","saveThreshold":10,"quitWaitTime":60,"environment":1,"maximizeWindow":0,"maxViewLength":15,"recordLog":1,"outputFormat":"xlsx","saveName":"current_time","inputExcel":"","startFromExit":0,"pauseKey":"p","containJudge":false,"desc":"https://arxiv.org/abs/2312.02977","inputParameters":[{"id":0,"name":"urlList_0","nodeId":1,"nodeName":"打开网页","value":"https://arxiv.org/abs/2312.02977","desc":"要采集的网址列表，多行以\\n分开","type":"text","exampleValue":"https://arxiv.org/abs/2312.02977"}],"outputParameters":[],"graph":[{"index":0,"id":0,"parentId":0,"type":-1,"option":0,"title":"root","sequence":[1,2],"parameters":{"history":1,"tabIndex":0,"useLoop":false,"xpath":"","iframe":false,"wait":0,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0},"isInLoop":false},{"id":1,"index":1,"parentId":0,"type":0,"option":1,"title":"打开网页","sequence":[],"isInLoop":false,"position":0,"parameters":{"useLoop":false,"xpath":"","wait":0,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0,"url":"https://arxiv.org/abs/2312.02977","links":"https://arxiv.org/abs/2312.02977","maxWaitTime":10,"scrollType":0,"scrollCount":1,"scrollWaitTime":1,"cookies":""}},{"id":2,"index":2,"parentId":0,"type":0,"option":2,"title":"点击Download PDF","sequence":[],"isInLoop":false,"position":1,"parameters":{"history":4,"tabIndex":-1,"useLoop":false,"xpath":"//*[contains(@class, \"download-pdf\")]","iframe":false,"wait":2,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0,"scrollType":0,"scrollCount":1,"scrollWaitTime":1,"clickWay":0,"maxWaitTime":10,"params":[],"alertHandleType":0,"allXPaths":["/html/body/div[2]/main[1]/div[1]/div[1]/div[2]/div[1]/ul[1]/li[1]/a[1]","//a[contains(., 'Download P')]","//A[@class='abs-button download-pdf']","/html/body/div[last()-3]/main/div/div/div[last()-2]/div[last()-5]/ul/li[last()-2]/a"]}}]}
+{"id":228,"name":"[2312.02977] Exploring the nonclassical dynamics of the \"classical'' Schrödinger equation","url":"https://arxiv.org/abs/2312.02977","links":"https://arxiv.org/abs/2312.02977","create_time":"12/7/2023, 2:44:58 AM","update_time":"2023-12-28 14:20:46","version":"0.6.0","saveThreshold":10,"quitWaitTime":60,"environment":1,"maximizeWindow":0,"maxViewLength":15,"recordLog":1,"outputFormat":"xlsx","saveName":"TTT","dataWriteMode":3,"inputExcel":"","startFromExit":0,"pauseKey":"p","containJudge":false,"browser":"chrome","removeDuplicate":0,"desc":"https://arxiv.org/abs/2312.02977","inputParameters":[{"id":0,"name":"urlList_0","nodeId":1,"nodeName":"打开网页","value":"https://arxiv.org/abs/2312.02977","desc":"要采集的网址列表，多行以\\n分开","type":"text","exampleValue":"https://arxiv.org/abs/2312.02977"}],"outputParameters":[],"graph":[{"index":0,"id":0,"parentId":0,"type":-1,"option":0,"title":"root","sequence":[1,2,3],"parameters":{"history":1,"tabIndex":0,"useLoop":false,"xpath":"","iframe":false,"wait":0,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0},"isInLoop":false},{"id":1,"index":1,"parentId":0,"type":0,"option":1,"title":"打开网页","sequence":[],"isInLoop":false,"position":0,"parameters":{"useLoop":false,"xpath":"","wait":0,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0,"url":"https://arxiv.org/abs/2312.02977","links":"https://arxiv.org/abs/2312.02977","maxWaitTime":10,"scrollType":0,"scrollCount":1,"scrollWaitTime":1,"cookies":""}},{"id":2,"index":2,"parentId":0,"type":0,"option":2,"title":"点击Download PDF","sequence":[],"isInLoop":false,"position":1,"parameters":{"history":4,"tabIndex":-1,"useLoop":false,"xpath":"//*[contains(@class, \"download-pdf\")]","iframe":false,"wait":2,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0,"scrollType":0,"scrollCount":1,"scrollWaitTime":1,"clickWay":0,"maxWaitTime":10,"params":[],"alertHandleType":0,"allXPaths":["/html/body/div[2]/main[1]/div[1]/div[1]/div[2]/div[1]/ul[1]/li[1]/a[1]","//a[contains(., 'Download P')]","//A[@class='abs-button download-pdf']","/html/body/div[last()-3]/main/div/div/div[last()-2]/div[last()-5]/ul/li[last()-2]/a"]}},{"id":3,"index":3,"parentId":0,"type":0,"option":2,"title":"点击Download PDF","sequence":[],"isInLoop":false,"position":2,"parameters":{"history":4,"tabIndex":-1,"useLoop":false,"xpath":"//*[contains(@class, \"download-pdf\")]","iframe":false,"wait":2,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0,"scrollType":0,"scrollCount":1,"scrollWaitTime":1,"clickWay":0,"maxWaitTime":10,"params":[],"alertHandleType":0,"allXPaths":["/html/body/div[2]/main[1]/div[1]/div[1]/div[2]/div[1]/ul[1]/li[1]/a[1]","//a[contains(., 'Download P')]","//A[@class='abs-button download-pdf']","/html/body/div[last()-3]/main/div/div/div[last()-2]/div[last()-5]/ul/li[last()-2]/a"]}}]}

ElectronJS/tasks/311.json

@@ -0,0 +1 @@
+{"id":311,"name":"重命名测试","url":"https://www.jd.com","links":"https://www.jd.com","create_time":"2023-12-28 14:05:20","update_time":"2023-12-28 14:05:43","version":"0.6.0","saveThreshold":10,"quitWaitTime":60,"environment":0,"maximizeWindow":0,"maxViewLength":15,"recordLog":1,"outputFormat":"xlsx","saveName":"TTT","dataWriteMode":3,"inputExcel":"","startFromExit":0,"pauseKey":"p","containJudge":false,"browser":"chrome","removeDuplicate":0,"desc":"https://www.jd.com","inputParameters":[{"id":0,"name":"urlList_0","nodeId":1,"nodeName":"打开网页","value":"https://www.jd.com","desc":"要采集的网址列表，多行以\\n分开","type":"text","exampleValue":"https://www.jd.com"}],"outputParameters":[{"id":0,"name":"参数1_链接文本","desc":"","type":"text","recordASField":1,"exampleValue":"手机"},{"id":1,"name":"参数2_链接地址","desc":"","type":"text","recordASField":1,"exampleValue":"https://shouji.jd.com/"}],"graph":[{"index":0,"id":0,"parentId":0,"type":-1,"option":0,"title":"root","sequence":[1,2],"parameters":{"history":1,"tabIndex":0,"useLoop":false,"xpath":"","iframe":false,"wait":0,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0},"isInLoop":false},{"id":1,"index":1,"parentId":0,"type":0,"option":1,"title":"打开网页","sequence":[],"isInLoop":false,"position":0,"parameters":{"useLoop":false,"xpath":"","wait":0,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0,"url":"https://www.jd.com","links":"https://www.jd.com","maxWaitTime":10,"scrollType":0,"scrollCount":1,"scrollWaitTime":1,"cookies":""}},{"id":2,"index":2,"parentId":0,"type":1,"option":8,"title":"循环采集数据","sequence":[3],"isInLoop":false,"position":1,"parameters":{"history":4,"tabIndex":-1,"useLoop":false,"xpath":"/html/body/div[5]/div[1]/div[1]/div[1]/div[1]/div[1]/div[1]/div[1]/div[1]/div/a","iframe":false,"wait":0,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0,"scrollType":0,"scrollCount":1,"scrollWaitTime":1,"loopType":1,"pathList":"","code":"","waitTime":0,"exitCount":0,"exitElement":"//body","historyWait":2,"breakMode":0,"breakCode":"","breakCodeWaitTime":0,"skipCount":0,"allXPaths":["/html/body/div[5]/div[1]/div[1]/div[1]/div[1]/div[1]/div[1]/div[1]/div[1]/div[1]/a[1]","//a[contains(., '手机')]","/html/body/div[last()-5]/div/div[last()-4]/div/div[last()-2]/div/div/div/div[last()-1]/div[last()-12]/a[last()-1]"]}},{"id":3,"index":3,"parentId":2,"type":0,"option":3,"title":"提取数据","sequence":[],"isInLoop":true,"position":0,"parameters":{"history":4,"tabIndex":-1,"useLoop":false,"xpath":"","iframe":false,"wait":0,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0,"clear":0,"newLine":1,"params":[{"nodeType":1,"contentType":0,"relative":true,"name":"参数1_链接文本","desc":"","extractType":0,"relativeXPath":"","allXPaths":"","exampleValues":[{"num":0,"value":"手机"}],"unique_index":"zvn77ulso2lqoswqo4","iframe":false,"default":"","paraType":"text","recordASField":1,"beforeJS":"","beforeJSWaitTime":0,"JS":"","JSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"downloadPic":0,"splitLine":0},{"nodeType":2,"contentType":0,"relative":true,"name":"参数2_链接地址","desc":"","relativeXPath":"","allXPaths":"","exampleValues":[{"num":0,"value":"https://shouji.jd.com/"}],"unique_index":"zvn77ulso2lqoswqo4","iframe":false,"default":"","paraType":"text","recordASField":1,"beforeJS":"","beforeJSWaitTime":0,"JS":"","JSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"downloadPic":0,"splitLine":0}]}}]}

ExecuteStage/.vscode/launch.json

@@ -12,7 +12,7 @@
             "justMyCode": false,
             //  "args": ["--ids", "[7]", "--read_type", "remote", "--headless", "0"]
             // "args": ["--ids", "[9]", "--read_type", "remote", "--headless", "0", "--saved_file_name", "YOUTUBE"]
-            "args": ["--ids", "[63]", "--headless", "0", "--user_data", "0", "--keyboard", "0",
+            "args": ["--ids", "[67]", "--headless", "0", "--user_data", "0", "--keyboard", "0",
         "--read_type", "remote"]
             // "args": "--ids '[97]' --user_data 1 --server_address http://localhost:8074 --config_folder '/Users/naibo/Documents/EasySpider/ElectronJS/' --headless 0 --read_type remote --config_file_name config.json --saved_file_name"
         }

ExecuteStage/easyspider_executestage.py

@@ -112,9 +112,10 @@ class BrowserThread(Thread):
         self.print_and_log("Save Name for task ID", id, "is:", self.saveName)
         if not os.path.exists("Data/Task_" + str(id)):
             os.mkdir("Data/Task_" + str(id))
-        if not os.path.exists("Data/Task_" + str(id) + "/" + self.saveName):
-            os.mkdir("Data/Task_" + str(id) + "/" +
-                     self.saveName)  # 创建保存文件夹用来保存截图
+        self.downloadFolder = "Data/Task_" + str(id) + "/" + self.saveName
+        if not os.path.exists(self.downloadFolder):
+            os.mkdir(self.downloadFolder)  # 创建保存文件夹用来保存截图和文件
+        self.existing_files = sorted([os.path.join(self.downloadFolder, file) for file in os.listdir(self.downloadFolder)], key=os.path.getmtime)
         self.getDataStep = 0
         self.startSteps = 0
         try:
@@ -144,7 +145,7 @@ class BrowserThread(Thread):
             'source': js})  # TMALL 反扒
         WebDriverWait(self.browser, 10)
         self.browser.command_executor._commands["send_command"] = ("POST", '/session/$sessionId/chromium/send_command')
-        path = os.path.join(os.path.abspath("./"), "Data", "Task_" + str(self.id))
+        path = os.path.join(os.path.abspath("./"), "Data", "Task_" + str(self.id), self.saveName)
         self.paramss = {'cmd': 'Page.setDownloadBehavior', 'params': {'behavior': 'allow', 'downloadPath': path}}
 
         self.browser.execute("send_command", self.paramss)  # 下载地址改变
@@ -187,12 +188,19 @@ class BrowserThread(Thread):
             self.links = list(filter(isnotnull, service["url"]))  # 要执行的link
         self.OUTPUT = []  # 采集的数据
         try:
-            self.dataWriteMode = service["dataWriteMode"] # 数据写入模式，1为追加，2为覆盖
+            self.dataWriteMode = service["dataWriteMode"] # 数据写入模式，1为追加，2为覆盖，3为重命名文件
         except:
             self.dataWriteMode = 1
         if self.outputFormat == "csv" or self.outputFormat == "txt" or self.outputFormat == "xlsx" or self.outputFormat == "json":
-            if self.dataWriteMode == 2 and os.path.exists("Data/Task_" + str(self.id) + "/" + self.saveName + '.' + self.outputFormat):
-                os.remove("Data/Task_" + str(self.id) + "/" + self.saveName + '.' + self.outputFormat)
+            if os.path.exists("Data/Task_" + str(self.id) + "/" + self.saveName + '.' + self.outputFormat):
+                if self.dataWriteMode == 2:
+                    os.remove("Data/Task_" + str(self.id) + "/" + self.saveName + '.' + self.outputFormat)
+                elif self.dataWriteMode == 3:
+                    i = 2
+                    while os.path.exists("Data/Task_" + str(self.id) + "/" + self.saveName + '_' + str(i) + '.' + self.outputFormat):
+                        i = i + 1
+                    self.saveName = self.saveName + '_' + str(i)
+                    self.print_and_log("文件已存在，已重命名为", self.saveName)
         self.writeMode = 1  # 写入模式，0为新建，1为追加
         if self.outputFormat == "csv" or self.outputFormat == "txt" or self.outputFormat == "xlsx":
             if not os.path.exists("Data/Task_" + str(self.id) + "/" + self.saveName + '.' + self.outputFormat):
@@ -521,7 +529,7 @@ class BrowserThread(Thread):
                                "/", len(self.links))
             self.executeNode(0)
             self.urlId = self.urlId + 1
-        files = os.listdir("Data/Task_" + str(self.id) + "/" + self.saveName)
+        # files = os.listdir("Data/Task_" + str(self.id) + "/" + self.saveName)
         # 如果目录为空，则删除该目录
         # if not files:
         #     os.rmdir("Data/Task_" + str(self.id) + "/" + self.saveName)
@@ -1799,6 +1807,11 @@ class BrowserThread(Thread):
                 self.print_and_log("History Length Error")
                 self.history["index"] = 0
         self.scrollDown(param)  # 根据参数配置向下滚动
+
+        # 处理文件变化，新下载
+        files = os.listdir(self.downloadFolder)
+        latest_file = files[-1]
+        self.existing_files = files
         # rt.end()
 
     def get_content(self, p, element):
@@ -2372,8 +2385,8 @@ if __name__ == '__main__':
             cloudflare = 0
         if cloudflare == 0:
             options.add_argument('log-level=3')  # 隐藏日志
-            path = os.path.join(os.path.abspath("./"), "Data", "Task_" + str(id))
-            print("Data path:", path)
+            path = os.path.join(os.path.abspath("./"), "Data", "Task_" + str(id), "files")
+            print("文件下载路径|File Download path:", path)
             options.add_experimental_option("prefs", {
                 # 设置文件下载路径
                 "download.default_directory": path,

ExecuteStage/utils.py

@@ -61,6 +61,40 @@ def send_email(config):
             pass
 
 
+def wait_for_download_complete(download_dir, timeout=3600):
+    """等待下载完成，直到没有.crdownload文件为止，或者超时"""
+    while True:
+        time.sleep(1)  # 每一秒检查一次
+        timeout -= 1
+        is_downloading = False
+        for fname in os.listdir(download_dir):
+            if fname.endswith('.crdownload'):
+                is_downloading = True
+                break
+        # 如果没有下载或超时，则退出
+        if not is_downloading or timeout <= 0:
+            break
+        elif timeout % 10 == 0:
+            print(f"下载文件中，请等待...|Downloading in progress, please wait... {timeout} seconds left")
+            print("可以在点击元素选项中设置下载超时时间。|You can set the download timeout in the 'Click Element' option.")
+    if is_downloading:
+        print("下载可能未完成，但已经超时。|Download may not be completed, but it has timed out.")
+    else:
+        print("下载完成。|Download completed.")
+
+def rename_downloaded_file(download_dir):
+    """重命名下载文件，假设是最新下载的文件"""
+    files = os.listdir(download_dir)
+    paths = [os.path.join(download_dir, basename) for basename in files]
+    latest_file = max(paths, key=os.path.getmtime, default=None)
+
+    if latest_file is not None and not latest_file.endswith('.crdownload'):
+        new_name = latest_file.split('/')[-1] + '_' + str(uuid.uuid4()) + '_' + latest_file.split('/')[-1]
+        new_path = os.path.join(download_dir, new_name)
+        os.rename(latest_file, new_path)
+        print(f"文件已重命名为: {new_path}")
+        print(f"File has been renamed to: {new_path}")
+
 def is_valid_url(url):
     try:
         result = urlparse(url)