junshan-kit 2.1.7__py2.py3-none-any.whl → 2.1.9__py2.py3-none-any.whl

junshan_kit/DataProcessor.py

@@ -91,11 +91,11 @@ class CSVToPandas:
             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"{'Export size (after encoding & scaling):':<35} {m_export} rows x {n_export} 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.':^70}")
+            print(f"{'Note: categorical columns one-hot encoded, numerical standardized.'}")
             print(f"More details: https://www.jianguoyun.com/p/DU6Lr9oQqdHDDRj5sI0GIAA")
             print('='*70 + '\n')
 

junshan_kit/datahub.py

@@ -1,8 +1,13 @@
 import kagglehub
-import os
+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):
@@ -42,20 +47,93 @@ class kaggle_data:
     # 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)
 
-if __name__ == "__main__":
-    # Your code here
-    data = kaggle_data()
-    # Example usage
-    data.list_user_datasets()
-    data.download_data(data_name='letter-libsvm', copy_path='./exp_data/Letter')
 
-    """
-    import junshan_kit.datahub
-    data = junshan_kit.datahub.kaggle_data()
-    data.list_user_datasets()
-    data.read_data(data_name='letter-libsvm', copy_path='./exp_data/Letter')
-    """
 

junshan_kit/meta.py

@@ -0,0 +1,248 @@
+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:
+    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:
+    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):
+        print("⏳ Waiting for downloads to finish...")
+        start_time = time.time()
+        while time.time() - start_time < timeout:
+            files = os.listdir(self.download_path)
+            if any(not f.endswith(".part") for f in files):
+                print("✅ Download completed!")
+                return
+            time.sleep(5)
+        print("⚠️ Timeout: download not completed within 1 hour")
+
+    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)
+
+
+# =============================================================
+#                           MAIN
+# =============================================================
+
+# if __name__ == "__main__":
+#     url = "https://www.jianguoyun.com/p/DdyHJxUQqdHDDRjvtI0GIAA"
+
+#     use_chrome = True  # Set True to use Chrome, False for Firefox
+
+#     if use_chrome:
+#         downloader = JianguoyunDownloaderChrome(url)
+#     else:
+#         downloader = JianguoyunDownloaderFirefox(url)
+
+#     downloader.run()

junshan_kit/test.py

@@ -1,5 +1,3 @@
-import DataProcessor
+from datahub import JianguoDownloader
 
-
-data_loader = DataProcessor.CSVToPandas()
-data_loader.ghpdd_kaggle()
+data2 = JianguoDownloader('www.lka.com', './expspe')

junshan_kit-2.1.9.dist-info/METADATA

@@ -0,0 +1,11 @@
+Metadata-Version: 2.4
+Name: junshan_kit
+Version: 2.1.9
+Summary: This is an optimization tool.
+Author-email: Junshan Yin <junshanyin@163.com>
+Requires-Dist: kaggle==1.7.4.5
+Requires-Dist: kagglehub==0.3.13
+Requires-Dist: numpy==2.2.6
+Requires-Dist: pandas==2.3.3
+Requires-Dist: scikit-learn==1.7.1
+Requires-Dist: selenium==4.36.0

junshan_kit-2.1.9.dist-info/RECORD

@@ -0,0 +1,8 @@
+junshan_kit/DataProcessor.py,sha256=AW_1jROexC3s41-RgzqzYVwPI0sOf3tzjiph4qa_Vcw,3882
+junshan_kit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+junshan_kit/datahub.py,sha256=I34e26psFS8WK4X6SNucKPLtdBm0Ujzqa0VDIRACah4,5163
+junshan_kit/meta.py,sha256=wzctYAckD3Gex1MMK5J6diV5z66E_rDUb814NzBQ5VY,9816
+junshan_kit/test.py,sha256=uSckjcr_Wgj__YPTwD6x0GY8Hfn5GBEXIpRf9vIYBbU,91
+junshan_kit-2.1.9.dist-info/METADATA,sha256=AjGMtbds79-V-BRJoU-vx0_PYNy9tJ380zOKlI8bOPs,329
+junshan_kit-2.1.9.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
+junshan_kit-2.1.9.dist-info/RECORD,,

junshan_kit-2.1.7.dist-info/METADATA

@@ -1,31 +0,0 @@
-Metadata-Version: 2.4
-Name: junshan_kit
-Version: 2.1.7
-Summary: This is an optimization tool.
-Author-email: Junshan Yin <junshanyin@163.com>
-Requires-Dist: kaggle==1.7.4.5
-Requires-Dist: kagglehub==0.3.13
-Requires-Dist: numpy==2.2.6
-Requires-Dist: pandas==2.3.3
-Requires-Dist: scikit-learn==1.7.1
-Description-Content-Type: text/markdown
-
-- For class kaggle_data in datahub
-  - We need to set API of kaggle.
-
-```python
-import junshan_kit.datahub
-data = junshan_kit.datahub.kaggle_data()
-data.list_user_datasets()
-data.read_data(data_name='letter-libsvm', copy_path='./exp_data/Letter')
-```
-
-
-
-
-
-
-
-
-
-

junshan_kit-2.1.7.dist-info/RECORD

@@ -1,7 +0,0 @@
-junshan_kit/DataProcessor.py,sha256=rp_w325h8EvKcLMSa12w5B-UA8G75O1qP0ogE6GDSE0,3886
-junshan_kit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-junshan_kit/datahub.py,sha256=BWcG_TPW1xf_y_GzxRXanuOAB01WugBiO5r53EDbr8s,1815
-junshan_kit/test.py,sha256=jyZQPgX40HlLM23vGMbuZFwFBk7YiFqzzh9xuOTzbw8,91
-junshan_kit-2.1.7.dist-info/METADATA,sha256=ePQG7bT7y7yVU7iSI3CxnfNacwJLyAlSB7nEmAG3_NM,599
-junshan_kit-2.1.7.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
-junshan_kit-2.1.7.dist-info/RECORD,,