junshan-kit 2.2.3__py2.py3-none-any.whl → 2.2.5__py2.py3-none-any.whl

junshan_kit/DataProcessor.py

@@ -1,146 +1,68 @@
 """
 ----------------------------------------------------------------------
->>> Author       : Junshan Yin  
+>>> Author       : Junshan Yin
 >>> Last Updated : 2025-10-12
 ----------------------------------------------------------------------
 """
 
 import pandas as pd
-import os
-from sklearn.preprocessing import StandardScaler
-import junshan_kit.datahub
-import zipfile
-
-class CSVToPandasMeta:
-    def __init__(self):
-        self.data_downloader = junshan_kit.datahub.kaggle_data()
-        
-
-    def read_csv(self, data_name):
-        self.csv_path = f'exp_data/{data_name}/{data_name}.csv'
-        if not os.path.exists(self.csv_path):
-            self.data_downloader.download_data(f'{data_name}', f'exp_data/{data_name}')  
-
-    # ----------------- ccfd_kaggle ----------------------------------
-    def ccfd_kaggle(self, data_name = 'ccfd-kaggle', show_info = True):
-        # download data if not exist
-        self.read_csv(data_name)
-        
-        df = pd.read_csv(self.csv_path)
-        m_before, n_before = df.shape
-        df = df.dropna(axis=0, how='any')
-        m_after, n_after = df.shape
-        df['Class'] = df['Class'].replace(0, -1)
-
-        if show_info:
-            pos_count = (df['Class'] == 1).sum()
-            neg_count = (df['Class'] == -1).sum()
-            
-            print('\n' + '='*60)
-            print(f"{'CCFD-Kaggle Dataset Info':^60}")
-            print('='*60)
-            print(f"{'Original size:':<25} {m_before} rows x {n_before} cols")
-            print(f"{'Size after dropping NaNs:':<25} {m_after} rows x {n_after} cols")
-            print(f"{'Positive samples (+1):':<25} {pos_count}")
-            print(f"{'Negative samples (-1):':<25} {neg_count}")
-            print(f"{'Export size:':<25} {m_after} rows x {n_after} cols")
-            print('-'*60)
-            print(f"More details: https://www.jianguoyun.com/p/Dd1clVgQ4ZThCxiwzZQGIAA")
-            print('='*60 + '\n')
-
-        return df
-    
-    # ------------------------ 
-    def ghpdd_kaggle(self, data_name='ghpdd-kaggle', show_info=True):
-        # download data if not exist
-        self.read_csv(data_name)
-
-        # read csv
-        df = pd.read_csv(self.csv_path)
-        m_before, n_before = df.shape
-
-        # drop NaNs
-        df = df.dropna(axis=0, how='any')
-        m_after, n_after = df.shape
-
-        # drop unique identifier
-        if 'property_id' in df.columns:
-            df.drop(columns=['property_id'], inplace=True)
-
-        # Replace label 0 with -1
-        df['decision'] = df['decision'].replace(0, -1)
-
-        # Identify categorical and numerical columns
-        cat_cols = ['country', 'city', 'property_type', 'furnishing_status']
-        num_cols = [col for col in df.columns if col not in cat_cols + ['decision']]
-
-        # One-Hot encode categorical columns
-        df = pd.get_dummies(df, columns=cat_cols)
-
-        # Convert boolean columns to int
-        bool_cols = df.select_dtypes(include='bool').columns
-        for col in bool_cols:
-            df[col] = df[col].astype(int)
-
-        # Standardize numerical columns
-        scaler = StandardScaler()
-        df[num_cols] = scaler.fit_transform(df[num_cols])
-
-        # The size after export
-        m_export, n_export = df.shape
-
-        if show_info:
-            pos_count = (df['decision'] == 1).sum()
-            neg_count = (df['decision'] == -1).sum()
-            
-            print('\n' + '='*70)
-            print(f"{'GHPDD-Kaggle Dataset Info':^70}")
-            print('='*70)
-            print(f"{'Original size:':<35} {m_before} rows x {n_before} cols")
-            print(f"{'Size after dropping NaNs:':<35} {m_after} rows x {n_after} cols")
-            print(f"{'Positive samples (+1):':<35} {pos_count}")
-            print(f"{'Negative samples (-1):':<35} {neg_count}")
-            print(f"{'Export size (after encoding & scaling):':<35} {m_export} rows x {n_export} cols")
-            print('-'*70)
-            print(f"{'Note: categorical columns one-hot encoded, numerical standardized.'}")
-            print(f"More details: https://www.jianguoyun.com/p/DU6Lr9oQqdHDDRj5sI0GIAA")
-            print('='*70 + '\n')
-
-        return df
-
 
 
 class CSV_TO_Pandas:
     def __init__(self):
         pass
 
-    def unzip_file(self, zip_path: str, unzip_folder: str):
-        """
-        Args:
-            zip_path (str): Path to the ZIP file to extract.
-            dest_folder (str, optional): Folder to extract files into. 
-                If None, the function will create a folder with the same 
-                name as the ZIP file (without extension).
-
-        Examples:
-            >>> zip_path = "./downloads/data.zip"
-            >>> unzip_folder = "./exp_data/data"
-            >>> unzip_file(zip_path, unzip_folder)
+    def preprocess_dataset(
+        self,
+        csv_path,
+        drop_cols: list,
+        label_col: str,
+        label_map: dict,
+        print_info=False,
+    ):
         """
+        Preprocess a CSV dataset by performing data cleaning, label mapping, and feature encoding.
 
-        if unzip_folder is None:
-            unzip_folder = os.path.splitext(os.path.basename(zip_path))[0]
+        This function loads a dataset from a CSV file, removes specified non-feature columns,
+        drops rows with missing values, maps the target label to numerical values, and
+        one-hot encodes categorical features. Optionally, it can print dataset statistics
+        before and after preprocessing.
 
-        os.makedirs(unzip_folder, exist_ok=True)
-
-        with zipfile.ZipFile(zip_path, 'r') as zip_ref:
-            zip_ref.extractall(unzip_folder)
-
-        print(f"✅ Extracted '{zip_path}' to '{os.path.abspath(unzip_folder)}'")
-    
-    # -----------------------------------------------------
-
-    def clean_data(self, csv_path, drop_cols: list, label_col: str, label_map: dict,  print_info = False):
+        Args:
+            csv_path (str):
+                Path to the input CSV dataset.
+            drop_cols (list):
+                List of column names to drop from the dataset.
+            label_col (str):
+                Name of the target label column.
+            label_map (dict):
+                Mapping dictionary for label conversion (e.g., {"yes": 1, "no": -1}).
+            print_info (bool, optional):
+                Whether to print preprocessing information and dataset statistics.
+                Defaults to False.
+
+        Returns:
+            pandas.DataFrame:
+                The cleaned and preprocessed dataset ready for model input.
+
+        Steps:
+            1. Load the dataset from CSV.
+            2. Drop non-informative or irrelevant columns.
+            3. Remove rows with missing values.
+            4. Map label column to numerical values according to `label_map`.
+            5. One-hot encode categorical (non-label) text features.
+            6. Optionally print dataset information and summary statistics.
+
+        Example:
+            >>> label_map = {"positive": 1, "negative": -1}
+            >>> df = data_handler.preprocess_dataset(
+            ...     csv_path="data/raw.csv",
+            ...     drop_cols=["id", "timestamp"],
+            ...     label_col="sentiment",
+            ...     label_map=label_map,
+            ...     print_info=True
+            ... )
+        """
         # Step 0: Load the dataset
         df = pd.read_csv(csv_path)
 
@@ -151,15 +73,19 @@ class CSV_TO_Pandas:
         df = df.drop(columns=drop_cols)
 
         # Step 2: Remove rows with missing values
-        df = df.dropna(axis=0, how='any')
+        df = df.dropna(axis=0, how="any")
         m_encoded, n_encoded = df.shape
-        
-        # Step 3: Map target label to -1 and +1
+
+        # Step 3: Map target label (to -1 and +1)
         df[label_col] = df[label_col].map(label_map)
 
         # Step 4: Encode categorical features (exclude label column)
-        text_feature_cols = df.select_dtypes(include=['object', 'string', 'category']).columns
-        text_feature_cols = [col for col in text_feature_cols if col != label_col]  # ✅ exclude label
+        text_feature_cols = df.select_dtypes(
+            include=["object", "string", "category"]
+        ).columns
+        text_feature_cols = [
+            col for col in text_feature_cols if col != label_col
+        ]  # ✅ exclude label
 
         df = pd.get_dummies(df, columns=text_feature_cols, dtype=int)
         m_cleaned, n_cleaned = df.shape
@@ -170,23 +96,27 @@ class CSV_TO_Pandas:
             neg_count = (df[label_col] == -1).sum()
 
             # Step 6: Print dataset information
-            print('\n' + '='*80)
+            print("\n" + "=" * 80)
             print(f"{'Dataset Info':^70}")
-            print('='*80)
+            print("=" * 80)
             print(f"{'Original size:':<40} {m_original} rows x {n_original} cols")
-            print(f"{'Size after dropping NaN & non-feature cols:':<40} {m_cleaned} rows x {n_cleaned} cols")
+            print(
+                f"{'Size after dropping NaN & non-feature cols:':<40} {m_cleaned} rows x {n_cleaned} cols"
+            )
             print(f"{'Positive samples (+1):':<40} {pos_count}")
             print(f"{'Negative samples (-1):':<40} {neg_count}")
-            print(f"{'Size after one-hot encoding:':<40} {m_encoded} rows x {n_encoded} cols")
-            print('-'*80)
+            print(
+                f"{'Size after one-hot encoding:':<40} {m_encoded} rows x {n_encoded} cols"
+            )
+            print("-" * 80)
             print(f"Note:")
             print(f"{'Label column:':<40} {label_col}")
-            print(f"{'Dropped non-feature columns:':<40} {', '.join(drop_cols) if drop_cols else 'None'}")
-            print(f"{'text fetaure columns:':<40} {', '.join(list(text_feature_cols)) if list(text_feature_cols) else 'None'}")
-            print('='*80 + '\n')
+            print(
+                f"{'Dropped non-feature columns:':<40} {', '.join(drop_cols) if drop_cols else 'None'}"
+            )
+            print(
+                f"{'text fetaure columns:':<40} {', '.join(list(text_feature_cols)) if list(text_feature_cols) else 'None'}"
+            )
+            print("=" * 80 + "\n")
 
         return df
-
-        
-
-        

junshan_kit/DataSets.py

@@ -0,0 +1,3 @@
+
+
+

junshan_kit/kit.py

@@ -6,7 +6,12 @@
 """
 
 import zipfile
-import os
+import os, time
+
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
 
 def unzip_file(zip_path: str, unzip_folder: str):
     """
@@ -33,3 +38,205 @@ def unzip_file(zip_path: str, unzip_folder: str):
     print(f"✅ Extracted '{zip_path}' to '{os.path.abspath(unzip_folder)}'")
 
 
+# =============================================================
+#                   JIANGUOYUN (NUTSTORE) CHROME VERSION
+# =============================================================
+
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+class JianguoyunDownloaderChrome:
+    """ Example:
+    >>> url = "https://www.jianguoyun.com/p/DdyHJxUQqdHDDRjvtI0GIAA"
+    >>> downloader = JianguoyunDownloaderChrome(url)
+    >>> downloader.run()
+    """
+    def __init__(self, url, download_path="./downloads"):
+        self.url = url
+        self.download_path = os.path.abspath(download_path)
+        os.makedirs(self.download_path, exist_ok=True)
+
+        self.chrome_options = ChromeOptions()
+        prefs = {
+            "download.default_directory": self.download_path,
+            "download.prompt_for_download": False,
+            "download.directory_upgrade": True,
+            "safebrowsing.enabled": True,
+            "profile.default_content_setting_values.automatic_downloads": 1,
+        }
+        self.chrome_options.add_experimental_option("prefs", prefs)
+        self.chrome_options.add_argument("--disable-gpu")
+        self.chrome_options.add_argument("--no-sandbox")
+        self.chrome_options.add_argument("--disable-dev-shm-usage")
+        self.chrome_options.add_argument("--enable-features=NetworkService,NetworkServiceInProcess")
+        # Uncomment for headless mode:
+        # self.chrome_options.add_argument("--headless")
+
+        self.driver = webdriver.Chrome(options=self.chrome_options)
+
+    def open_page(self):
+        print(f"🌐 Opening page: {self.url}")
+        self.driver.get(self.url)
+        print(f"✅ Page loaded: {self.driver.title}")
+
+    def click_download_button(self):
+        """Find and click the 'Download' button (supports English and Chinese)."""
+        print("🔍 Searching for the download button...")
+        wait = WebDriverWait(self.driver, 30)
+
+        try:
+            # Match both English 'Download' (case-insensitive) and Chinese '下载'
+            xpath = (
+                "//span[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
+                " | //button[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
+                " | //a[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
+                " | //span[contains(text(),'下载')]"
+                " | //button[contains(text(),'下载')]"
+                " | //a[contains(text(),'下载')]"
+            )
+
+            button = wait.until(EC.element_to_be_clickable((By.XPATH, xpath)))
+
+            # Click using JavaScript to avoid overlay or interaction issues
+            self.driver.execute_script("arguments[0].click();", button)
+            print(f"✅ Download button clicked. Files will be saved to: {self.download_path}")
+
+            # If the cloud service opens a new tab, switch to it
+            time.sleep(3)
+            if len(self.driver.window_handles) > 1:
+                self.driver.switch_to.window(self.driver.window_handles[-1])
+                print("📂 Switched to the new download tab.")
+
+        except Exception as e:
+            print("❌ Failed to find or click the download button:", e)
+            raise
+
+
+    def wait_for_downloads(self, timeout=3600):
+        print("⏳ Waiting for downloads to finish...")
+        start_time = time.time()
+        while time.time() - start_time < timeout:
+            downloading = [f for f in os.listdir(self.download_path) if f.endswith(".crdownload")]
+            if not downloading:
+                print("✅ Download completed!")
+                return
+            time.sleep(2)
+        print("⚠️ Timeout: download not completed within 1 hour")
+
+    def close(self):
+        self.driver.quit()
+        print("🚪 Browser closed.")
+
+    def run(self):
+        print('*' * 60)
+        try:
+            self.open_page()
+            self.click_download_button()
+            self.wait_for_downloads()
+        except Exception as e:
+            print("❌ Error:", e)
+        finally:
+            self.close()
+        print('*' * 60)
+
+
+# =============================================================
+#                   JIANGUOYUN (NUTSTORE) FIREFOX VERSION
+# =============================================================
+
+from selenium.webdriver.firefox.options import Options as FirefoxOptions
+from selenium.webdriver.firefox.service import Service
+
+class JianguoyunDownloaderFirefox:
+    """ Example:
+    >>> url = "https://www.jianguoyun.com/p/DdyHJxUQqdHDDRjvtI0GIAA"
+    >>> downloader = JianguoyunDownloaderFirefox(url)
+    >>> downloader.run()
+    """
+    def __init__(self, url, download_path="./downloads"):
+        self.url = url
+        self.download_path = os.path.abspath(download_path)
+        os.makedirs(self.download_path, exist_ok=True)
+
+        options = FirefoxOptions()
+        options.add_argument("--headless")
+        options.set_preference("browser.download.folderList", 2)
+        options.set_preference("browser.download.manager.showWhenStarting", False)
+        options.set_preference("browser.download.dir", self.download_path)
+        options.set_preference("browser.helperApps.neverAsk.saveToDisk",
+                            "application/zip,application/octet-stream,application/x-zip-compressed,multipart/x-zip")
+        options.set_preference("pdfjs.disabled", True)
+
+        service = Service("/snap/bin/geckodriver")
+        self.driver = webdriver.Firefox(service=service, options=options)
+
+    def open_page(self):
+        print(f"🌐 Opening page: {self.url}")
+        self.driver.get(self.url)
+        print(f"✅ Page loaded: {self.driver.title}")
+
+    def click_download_button(self):
+        """Find and click the 'Download' button (supports English and Chinese)."""
+        print("🔍 Searching for the download button...")
+        wait = WebDriverWait(self.driver, 30)
+
+        try:
+            # Match both English 'Download' (case-insensitive) and Chinese '下载'
+            xpath = (
+                "//span[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
+                " | //button[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
+                " | //a[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
+                " | //span[contains(text(),'下载')]"
+                " | //button[contains(text(),'下载')]"
+                " | //a[contains(text(),'下载')]"
+            )
+
+            button = wait.until(EC.element_to_be_clickable((By.XPATH, xpath)))
+
+            # Click using JavaScript to avoid overlay or interaction issues
+            self.driver.execute_script("arguments[0].click();", button)
+            print(f"✅ Download button clicked. Files will be saved to: {self.download_path}")
+
+            # If the cloud service opens a new tab, switch to it
+            time.sleep(3)
+            if len(self.driver.window_handles) > 1:
+                self.driver.switch_to.window(self.driver.window_handles[-1])
+                print("📂 Switched to the new download tab.")
+
+        except Exception as e:
+            print("❌ Failed to find or click the download button:", e)
+            raise
+
+    def wait_for_download(self, timeout=3600):
+        """Wait until all downloads are finished (auto-detects browser type)."""
+        print("⏳ Waiting for downloads to finish...")
+        start_time = time.time()
+
+        # Determine the temporary file extension based on the browser type
+        temp_ext = ".crdownload" if "chrome" in self.driver.capabilities["browserName"].lower() else ".part"
+
+        while time.time() - start_time < timeout:
+            downloading = [f for f in os.listdir(self.download_path) if f.endswith(temp_ext)]
+            if not downloading:
+                print("✅ Download completed!")
+                return True
+            time.sleep(2)
+
+
+    def close(self):
+        print("🛑 Closing browser...")
+        self.driver.quit()
+
+    def run(self):
+        print('*' * 60)
+        try:
+            self.open_page()
+            self.click_download_button()
+            self.wait_for_download(timeout=3600)
+        except Exception as e:
+            print("❌ Error:", e)
+        finally:
+            self.close()
+        print('*' * 60)
+
+
+
+

{junshan_kit-2.2.3.dist-info → junshan_kit-2.2.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: junshan_kit
-Version: 2.2.3
+Version: 2.2.5
 Summary: This is an optimization tool.
 Author-email: Junshan Yin <junshanyin@163.com>
 Requires-Dist: kaggle==1.7.4.5

junshan_kit-2.2.5.dist-info/RECORD

@@ -0,0 +1,7 @@
+junshan_kit/DataProcessor.py,sha256=eryVmS5BFZj8wjDN2QWVHqkbFgFuWU0HXV9s6TGf9QM,4442
+junshan_kit/DataSets.py,sha256=ajz1GSNU9xYVrFEDSz6Xwg7amWQ_yvW75tQa1ZvRIWc,3
+junshan_kit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+junshan_kit/kit.py,sha256=FaQT0H7FLKUuTNgU0zfU7Qn3MsjeW6C_rsrB_UOEVJ4,9571
+junshan_kit-2.2.5.dist-info/METADATA,sha256=6eUE_T57eUMtYiE958tpJp7glbX2qXyMObOhW_n0INo,329
+junshan_kit-2.2.5.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
+junshan_kit-2.2.5.dist-info/RECORD,,

junshan_kit/datahub.py

@@ -1,146 +0,0 @@
-"""
-----------------------------------------------------------------------
->>> Author       : Junshan Yin  
->>> Last Updated : 2025-10-12
-----------------------------------------------------------------------
-"""
-
-import kagglehub
-import os, time
-import warnings
-import shutil
-from kaggle.api.kaggle_api_extended import KaggleApi
-from selenium import webdriver
-from selenium.webdriver.common.by import By
-from selenium.webdriver.chrome.options import Options
-from selenium.webdriver.support.ui import WebDriverWait
-from selenium.webdriver.support import expected_conditions as EC
-
-class kaggle_data:
-    def list_datasets(self):
-        api = KaggleApi()
-        api.authenticate()
-        datasets = api.dataset_list(user='junshan888')
-        print('Available datasets:')
-        print('*' * 60)
-        if datasets is not None:
-            for ds in datasets:
-                if ds is not None:
-                    print(ds.title)
-        print('*' * 60)
-    
-    def list_user_datasets(self):
-        warnings.warn(
-            "list_user_datasets() is deprecated. Use list_datasets() instead.",
-            DeprecationWarning,
-            stacklevel=2
-        )
-        return self.list_datasets()
-    
-        # example:  list_user_datasets()
-
-    #---------------------------------------------------------------
-    def download_data(self, data_name = 'letter-libsvm', copy_path = None):
-        path = kagglehub.dataset_download(f'junshan888/{data_name}')
-        # print("Downloaded to:", path)
-        if copy_path is not None:
-            # Create target directory if it doesn't exist
-            os.makedirs(copy_path, exist_ok=True)
-            # Copy dataset to target directory
-            shutil.copytree(path, copy_path, dirs_exist_ok=True)
-
-            print(f"✅ Dataset has been copied to: {copy_path}")
-
-    # example: read_data(copy_path='./exp_data')
-
-
-class JianguoDownloaderChrome:
-    def __init__(self, url: str, download_path: str = "./downloads"):
-        self.url = url
-        self.download_path = os.path.abspath(download_path)
-        os.makedirs(self.download_path, exist_ok=True)
-
-        # Configure Chrome options
-        self.chrome_options = Options()
-        prefs = {
-            "download.default_directory": self.download_path,
-            "download.prompt_for_download": False,
-            "download.directory_upgrade": True,
-            "safebrowsing.enabled": True,
-            "profile.default_content_setting_values.automatic_downloads": 1,
-        }
-        self.chrome_options.add_experimental_option("prefs", prefs)
-
-        # Optional stability flags
-        self.chrome_options.add_argument("--disable-gpu")
-        self.chrome_options.add_argument("--no-sandbox")
-        self.chrome_options.add_argument("--disable-dev-shm-usage")
-        self.chrome_options.add_argument("--enable-features=NetworkService,NetworkServiceInProcess")
-
-        # Start Chrome
-        self.driver = webdriver.Chrome(options=self.chrome_options)
-
-    def open_page(self):
-        """Open the Jianguoyun share page."""
-        print(f"🌐 Opening link: {self.url}")
-        self.driver.get(self.url)
-
-    def click_download_button(self):
-        """Find and click the download button."""
-        print("🔍 Looking for the download button...")
-        wait = WebDriverWait(self.driver, 30)
-        span = wait.until(
-            EC.presence_of_element_located((By.XPATH, "//span[contains(text(),'下载')]"))
-        )
-        parent = span.find_element(By.XPATH, "./..")
-        self.driver.execute_script("arguments[0].click();", parent)
-        print(f"✅ Download button clicked. Files will be saved to: {self.download_path}")
-
-        # If Jianguoyun opens a new tab, switch to it
-        time.sleep(3)
-        if len(self.driver.window_handles) > 1:
-            self.driver.switch_to.window(self.driver.window_handles[-1])
-            print("📂 Switched to download tab.")
-
-    def wait_for_downloads(self, timeout=30000):
-        """Wait until all downloads are finished."""
-        print("⏳ Waiting for downloads to finish...")
-        start_time = time.time()
-        while True:
-            downloading = [f for f in os.listdir(self.download_path) if f.endswith(".crdownload")]
-            if not downloading:
-                print("✅ Download completed!")
-                return True
-            if time.time() - start_time > timeout:
-                print("⏰ Timeout: downloads may not have finished.")
-                return False
-            time.sleep(2)
-
-    def get_latest_file(self):
-        """Return the most recently downloaded file (if any)."""
-        files = [os.path.join(self.download_path, f) for f in os.listdir(self.download_path)]
-        return max(files, key=os.path.getctime) if files else None
-
-    def close(self):
-        """Close the browser."""
-        self.driver.quit()
-        print("🚪 Browser closed.")
-
-    def run(self):
-        """Run the complete download process."""
-        print('*'*50)
-        try:
-            self.open_page()
-            self.click_download_button()
-            self.wait_for_downloads()
-            latest = self.get_latest_file()
-            if latest:
-                print(f"📄 Latest downloaded file: {latest}")
-        except Exception as e:
-            print("❌ Error occurred:", e)
-        finally:
-            self.close()
-        print('*'*50)
-
-
-

junshan_kit/meta.py

@@ -1,256 +0,0 @@
-"""
-----------------------------------------------------------------------
->>> Author       : Junshan Yin  
->>> Last Updated : 2025-10-12
-----------------------------------------------------------------------
-"""
-
-import os
-import time
-import shutil
-import warnings
-import kagglehub
-from kaggle.api.kaggle_api_extended import KaggleApi
-
-from selenium import webdriver
-from selenium.webdriver.common.by import By
-from selenium.webdriver.support.ui import WebDriverWait
-from selenium.webdriver.support import expected_conditions as EC
-
-
-# =============================================================
-#                   KAGGLE DATA MANAGEMENT
-# =============================================================
-
-class KaggleData:
-    def list_datasets(self):
-        """
-        List available datasets from a specific user.
-        """
-        api = KaggleApi()
-        api.authenticate()
-        datasets = api.dataset_list(user='junshan888')
-        print('Available datasets:')
-        print('*' * 60)
-        if datasets:
-            for ds in datasets:
-                print(ds.title) # type: ignore
-        print('*' * 60)
-
-    def list_user_datasets(self):
-        warnings.warn(
-            "list_user_datasets() is deprecated. Use list_datasets() instead.",
-            DeprecationWarning,
-            stacklevel=2
-        )
-        return self.list_datasets()
-
-    def download_data(self, data_name='letter-libsvm', copy_path=None):
-        """Download a Kaggle dataset and optionally copy it to a target folder."""
-        path = kagglehub.dataset_download(f'junshan888/{data_name}')
-        if copy_path:
-            os.makedirs(copy_path, exist_ok=True)
-            shutil.copytree(path, copy_path, dirs_exist_ok=True)
-            print(f"✅ Dataset copied to: {copy_path}")
-
-
-# =============================================================
-#                   JIANGUOYUN (NUTSTORE) CHROME VERSION
-# =============================================================
-
-from selenium.webdriver.chrome.options import Options as ChromeOptions
-
-class JianguoyunDownloaderChrome:
-    """ Example:
-    >>> url = "https://www.jianguoyun.com/p/DdyHJxUQqdHDDRjvtI0GIAA"
-    >>> downloader = JianguoyunDownloaderChrome(url)
-    >>> downloader.run()
-    """
-    def __init__(self, url, download_path="./downloads"):
-        self.url = url
-        self.download_path = os.path.abspath(download_path)
-        os.makedirs(self.download_path, exist_ok=True)
-
-        self.chrome_options = ChromeOptions()
-        prefs = {
-            "download.default_directory": self.download_path,
-            "download.prompt_for_download": False,
-            "download.directory_upgrade": True,
-            "safebrowsing.enabled": True,
-            "profile.default_content_setting_values.automatic_downloads": 1,
-        }
-        self.chrome_options.add_experimental_option("prefs", prefs)
-        self.chrome_options.add_argument("--disable-gpu")
-        self.chrome_options.add_argument("--no-sandbox")
-        self.chrome_options.add_argument("--disable-dev-shm-usage")
-        self.chrome_options.add_argument("--enable-features=NetworkService,NetworkServiceInProcess")
-        # Uncomment for headless mode:
-        # self.chrome_options.add_argument("--headless")
-
-        self.driver = webdriver.Chrome(options=self.chrome_options)
-
-    def open_page(self):
-        print(f"🌐 Opening page: {self.url}")
-        self.driver.get(self.url)
-        print(f"✅ Page loaded: {self.driver.title}")
-
-    def click_download_button(self):
-        """Find and click the 'Download' button (supports English and Chinese)."""
-        print("🔍 Searching for the download button...")
-        wait = WebDriverWait(self.driver, 30)
-
-        try:
-            # Match both English 'Download' (case-insensitive) and Chinese '下载'
-            xpath = (
-                "//span[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
-                " | //button[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
-                " | //a[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
-                " | //span[contains(text(),'下载')]"
-                " | //button[contains(text(),'下载')]"
-                " | //a[contains(text(),'下载')]"
-            )
-
-            button = wait.until(EC.element_to_be_clickable((By.XPATH, xpath)))
-
-            # Click using JavaScript to avoid overlay or interaction issues
-            self.driver.execute_script("arguments[0].click();", button)
-            print(f"✅ Download button clicked. Files will be saved to: {self.download_path}")
-
-            # If the cloud service opens a new tab, switch to it
-            time.sleep(3)
-            if len(self.driver.window_handles) > 1:
-                self.driver.switch_to.window(self.driver.window_handles[-1])
-                print("📂 Switched to the new download tab.")
-
-        except Exception as e:
-            print("❌ Failed to find or click the download button:", e)
-            raise
-
-
-    def wait_for_downloads(self, timeout=3600):
-        print("⏳ Waiting for downloads to finish...")
-        start_time = time.time()
-        while time.time() - start_time < timeout:
-            downloading = [f for f in os.listdir(self.download_path) if f.endswith(".crdownload")]
-            if not downloading:
-                print("✅ Download completed!")
-                return
-            time.sleep(2)
-        print("⚠️ Timeout: download not completed within 1 hour")
-
-    def close(self):
-        self.driver.quit()
-        print("🚪 Browser closed.")
-
-    def run(self):
-        print('*' * 60)
-        try:
-            self.open_page()
-            self.click_download_button()
-            self.wait_for_downloads()
-        except Exception as e:
-            print("❌ Error:", e)
-        finally:
-            self.close()
-        print('*' * 60)
-
-
-# =============================================================
-#                   JIANGUOYUN (NUTSTORE) FIREFOX VERSION
-# =============================================================
-
-from selenium.webdriver.firefox.options import Options as FirefoxOptions
-from selenium.webdriver.firefox.service import Service
-
-class JianguoyunDownloaderFirefox:
-    """ Example:
-    >>> url = "https://www.jianguoyun.com/p/DdyHJxUQqdHDDRjvtI0GIAA"
-    >>> downloader = JianguoyunDownloaderFirefox(url)
-    >>> downloader.run()
-    """
-    def __init__(self, url, download_path="./downloads"):
-        self.url = url
-        self.download_path = os.path.abspath(download_path)
-        os.makedirs(self.download_path, exist_ok=True)
-
-        options = FirefoxOptions()
-        options.add_argument("--headless")
-        options.set_preference("browser.download.folderList", 2)
-        options.set_preference("browser.download.manager.showWhenStarting", False)
-        options.set_preference("browser.download.dir", self.download_path)
-        options.set_preference("browser.helperApps.neverAsk.saveToDisk",
-                            "application/zip,application/octet-stream,application/x-zip-compressed,multipart/x-zip")
-        options.set_preference("pdfjs.disabled", True)
-
-        service = Service("/snap/bin/geckodriver")
-        self.driver = webdriver.Firefox(service=service, options=options)
-
-    def open_page(self):
-        print(f"🌐 Opening page: {self.url}")
-        self.driver.get(self.url)
-        print(f"✅ Page loaded: {self.driver.title}")
-
-    def click_download_button(self):
-        """Find and click the 'Download' button (supports English and Chinese)."""
-        print("🔍 Searching for the download button...")
-        wait = WebDriverWait(self.driver, 30)
-
-        try:
-            # Match both English 'Download' (case-insensitive) and Chinese '下载'
-            xpath = (
-                "//span[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
-                " | //button[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
-                " | //a[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
-                " | //span[contains(text(),'下载')]"
-                " | //button[contains(text(),'下载')]"
-                " | //a[contains(text(),'下载')]"
-            )
-
-            button = wait.until(EC.element_to_be_clickable((By.XPATH, xpath)))
-
-            # Click using JavaScript to avoid overlay or interaction issues
-            self.driver.execute_script("arguments[0].click();", button)
-            print(f"✅ Download button clicked. Files will be saved to: {self.download_path}")
-
-            # If the cloud service opens a new tab, switch to it
-            time.sleep(3)
-            if len(self.driver.window_handles) > 1:
-                self.driver.switch_to.window(self.driver.window_handles[-1])
-                print("📂 Switched to the new download tab.")
-
-        except Exception as e:
-            print("❌ Failed to find or click the download button:", e)
-            raise
-
-    def wait_for_download(self, timeout=3600):
-        """Wait until all downloads are finished (auto-detects browser type)."""
-        print("⏳ Waiting for downloads to finish...")
-        start_time = time.time()
-
-        # Determine the temporary file extension based on the browser type
-        temp_ext = ".crdownload" if "chrome" in self.driver.capabilities["browserName"].lower() else ".part"
-
-        while time.time() - start_time < timeout:
-            downloading = [f for f in os.listdir(self.download_path) if f.endswith(temp_ext)]
-            if not downloading:
-                print("✅ Download completed!")
-                return True
-            time.sleep(2)
-
-
-    def close(self):
-        print("🛑 Closing browser...")
-        self.driver.quit()
-
-    def run(self):
-        print('*' * 60)
-        try:
-            self.open_page()
-            self.click_download_button()
-            self.wait_for_download(timeout=3600)
-        except Exception as e:
-            print("❌ Error:", e)
-        finally:
-            self.close()
-        print('*' * 60)
-

junshan_kit/test.py

@@ -1,8 +0,0 @@
-from DataProcessor import CSV_TO_Pandas
-
-
-data_ = CSV_TO_Pandas()
-
-
-
-data_.clean_data('data_csv/Electric Vehicle Population Data/Electric_Vehicle_Population_Data.csv', [], [], {})

junshan_kit-2.2.3.dist-info/RECORD

@@ -1,9 +0,0 @@
-junshan_kit/DataProcessor.py,sha256=rDL3NLD-WlT3x6x74XkB_542_sk3BrnIk5p4rYlVn5o,7212
-junshan_kit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-junshan_kit/datahub.py,sha256=_Q_3AlZ8vk1Ma6h9I44SxWBA8w9m1CQNvYztMcsxzUo,5377
-junshan_kit/kit.py,sha256=h4Q_87hEJbXH4A9ryaGMu_nle5RlM8OR_PaW_hWCVBY,1040
-junshan_kit/meta.py,sha256=SiY9P93aABrksNE6G3ft5gzcuP2cUgc4Vx6LH7ZFmzg,10113
-junshan_kit/test.py,sha256=FgzG4oG7kkq6rWasxdBSY1qx_B0navRI5Ei-wJ1Dvo0,180
-junshan_kit-2.2.3.dist-info/METADATA,sha256=h4_Z0LMIigJgrkt2hD5TcYJwOCkArMRySh-OopgZ9Xo,329
-junshan_kit-2.2.3.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
-junshan_kit-2.2.3.dist-info/RECORD,,