xhs-note-extractor 0.1.5.dev1__py3-none-any.whl

xhs_note_extractor/DEVICE_RETRY_GUIDE.md

@@ -0,0 +1,98 @@
+# 小红书笔记提取器 - 设备重试机制使用指南
+
+## 功能概述
+
+小红书笔记提取器现在支持设备重试机制。当某个设备需要登录时，系统会自动尝试连接其他可用设备，直到找到无需登录的设备或所有设备都尝试过为止。
+
+## 使用方式
+
+### 1. 使用便捷函数（推荐）
+
+```python
+from xhs_note_extractor import extract_note_from_url
+
+# 直接提取笔记数据
+result = extract_note_from_url("https://www.xiaohongshu.com/explore/你的笔记ID")
+
+if result:
+    print("成功提取笔记数据")
+    print(f"作者: {result['author_name']}")
+    print(f"点赞数: {result['likes']}")
+    print(f"图片数: {len(result['image_urls'])}")
+else:
+    print("所有设备都需要登录，提取失败")
+```
+
+### 2. 使用类实例
+
+```python
+from xhs_note_extractor import XHSNoteExtractor
+
+# 创建提取器实例
+extractor = XHSNoteExtractor()
+
+# 显示可用设备
+print(f"可用设备: {extractor.available_devices}")
+
+# 提取笔记数据
+result = extractor.extract_note_data(url="https://www.xiaohongshu.com/explore/你的笔记ID")
+
+if result:
+    print("成功提取笔记数据")
+else:
+    print("所有设备都需要登录，提取失败")
+```
+
+### 3. 手动切换设备
+
+```python
+from xhs_note_extractor import XHSNoteExtractor
+
+extractor = XHSNoteExtractor()
+
+# 查看当前设备
+print(f"当前设备: {extractor.device.serial}")
+
+# 手动切换到下一个设备
+success = extractor.switch_to_next_device()
+if success:
+    print(f"已切换到设备: {extractor.device.serial}")
+```
+
+## 工作原理
+
+1. **设备发现**: 初始化时自动检测所有通过ADB连接的Android设备
+2. **登录检测**: 在提取笔记时检测是否需要登录
+3. **自动重试**: 如果需要登录，自动尝试下一个可用设备
+4. **循环尝试**: 依次尝试所有可用设备
+5. **结果返回**: 成功则返回数据，失败则返回None
+
+## 注意事项
+
+- 确保所有设备都已通过USB调试连接并授权
+- 设备需要安装小红书APP
+- 如果所有设备都需要登录，则返回None而不是抛出异常
+- 设备切换时会自动重启小红书APP
+
+## 测试脚本
+
+运行测试脚本验证设备重试功能：
+
+```bash
+python xhs_note_extractor/test_device_retry.py
+```
+
+## 故障排除
+
+1. **无法发现设备**：
+   - 检查USB连接
+   - 确保ADB调试已开启
+   - 运行 `adb devices` 验证设备连接
+
+2. **设备切换失败**：
+   - 检查设备是否仍然连接
+   - 确保小红书APP在设备上已安装
+
+3. **返回None**：
+   - 所有设备都需要登录
+   - 尝试手动登录某个设备后再试

xhs_note_extractor/__init__.py

@@ -0,0 +1,50 @@
+"""
+小红书笔记提取器包
+
+这是一个用于从小红书URL中提取笔记信息的Python包。
+支持URL解析、设备连接、页面跳转和笔记内容提取。
+
+主要功能：
+- URL解析和转换（支持标准格式和xhsdiscover协议格式）
+- 设备连接和自动化操作
+- 笔记内容提取（正文、图片、点赞数等）
+- 结构化数据返回
+
+示例:
+    >>> from xhs_note_extractor import XHSNoteExtractor
+    >>> extractor = XHSNoteExtractor()
+    >>> data = extractor.extract_note_data(url="https://www.xiaohongshu.com/explore/...")
+    >>> print(data['content'])
+"""
+
+__version__ = "1.0.0"
+__author__ = "JoyCode Agent"
+__email__ = "agent@joycode.com"
+
+from .extractor import XHSNoteExtractor
+from .utils import (
+    DeviceManager,
+    ElementFinder,
+    DataFormatter,
+    NetworkUtils,
+    FileManager,
+    XHSUtils,
+    connect_device,
+    format_like_count,
+    extract_image_urls_from_html,
+    fetch_html
+)
+
+__all__ = [
+    "XHSNoteExtractor",
+    "DeviceManager",
+    "ElementFinder",
+    "DataFormatter",
+    "NetworkUtils",
+    "FileManager",
+    "XHSUtils",
+    "connect_device",
+    "format_like_count",
+    "extract_image_urls_from_html",
+    "fetch_html",
+]

xhs_note_extractor/_version.py

@@ -0,0 +1,34 @@
+# file generated by setuptools-scm
+# don't change, don't track in version control
+
+__all__ = [
+    "__version__",
+    "__version_tuple__",
+    "version",
+    "version_tuple",
+    "__commit_id__",
+    "commit_id",
+]
+
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Tuple
+    from typing import Union
+
+    VERSION_TUPLE = Tuple[Union[int, str], ...]
+    COMMIT_ID = Union[str, None]
+else:
+    VERSION_TUPLE = object
+    COMMIT_ID = object
+
+version: str
+__version__: str
+__version_tuple__: VERSION_TUPLE
+version_tuple: VERSION_TUPLE
+commit_id: COMMIT_ID
+__commit_id__: COMMIT_ID
+
+__version__ = version = '0.1.dev2'
+__version_tuple__ = version_tuple = (0, 1, 'dev2')
+
+__commit_id__ = commit_id = 'g1aa72014c'

xhs_note_extractor/agent_login.py

@@ -0,0 +1,264 @@
+#!/usr/bin/env python3
+"""
+Phone Agent Usage Examples / Phone Agent 使用示例
+
+Demonstrates how to use Phone Agent for phone automation tasks via Python API.
+演示如何通过 Python API 使用 Phone Agent 进行手机自动化任务。
+"""
+import json
+from datetime import datetime
+
+from phone_agent import PhoneAgent
+from phone_agent.agent import AgentConfig
+from phone_agent.config import get_messages
+from phone_agent.model import ModelConfig
+
+from xhs_note_extractor.login_propmt import phone_agent_protocol_v3_t1, phone_agent_protocol_v3_t3
+from xhs_note_extractor.sms_verification import get_verification_code_sync
+
+def do_login(device_id:str, lang: str = "cn", phone_number:str = "19163152334"):
+    """Basic task example / 基础任务示例"""
+    # Configure model endpoint
+    model_config = ModelConfig(
+        model_name="ZhipuAI/AutoGLM-Phone-9B",
+        temperature=0.1,
+        api_key="ms-ed9ed848-d630-4192-a688-37ebbf985246",
+        base_url="https://api-inference.modelscope.cn/v1"
+    )
+
+    # Configure Agent behavior
+    agent_config = AgentConfig(
+        max_steps=50,
+        verbose=True,
+        lang=lang,
+        device_id=device_id,
+    )
+
+    # Create Agent
+    agent = PhoneAgent(
+        model_config=model_config,
+        agent_config=agent_config,
+    )
+    cur_date_time = datetime.now()
+    print(f'phone_number:{phone_number}')
+    # 从文件加载协议内容
+    prompt_task1 = phone_agent_protocol_v3_t1.format(phone_number)
+    result = agent.run(prompt_task1)
+    print(f"prompt_task1: {result}")
+    
+    # 解析JSON结果
+    try:
+        result_json = json.loads(result)
+        print(f"result_json: {result_json}")
+        # 检查任务1是否成功
+        if result_json.get("status") != "success":
+            print(f"验证码触发失败: {result_json.get('message')}")
+            return False
+    except json.JSONDecodeError:
+        print(f"result error: {result}")
+        # 如果不是JSON格式，尝试兼容旧格式
+        
+        # 检查是否包含图片验证码相关内容
+        image_captcha_keywords = ["图片验证码", "点击文字", "旋转图片", "滑块", "拼图", "拖拽", "文字验证"]
+        has_image_captcha = any(keyword in result for keyword in image_captcha_keywords)
+        
+        if has_image_captcha:
+            print("检测到图片验证码，验证码触发失败")
+            return False
+        
+        # 原始的旧格式检查逻辑
+        if (not "验证码已触发" in result and not "验证码已成功发送" in result and "任务已完成" not in result ) and ("图片验证码界面" in result):
+            print("验证码触发失败")
+            return False
+    # 3. 自定义重试参数
+    print(f"\n获取手机号 {phone_number} 的验证码（3次尝试，每次间隔3秒）...")
+    code = get_verification_code_sync(
+        phone_number,
+        send_time=cur_date_time,
+        max_retries=3,
+        retry_interval=3
+    )
+    print(f"手机号: {phone_number}, 验证码: {code}")
+    prompt_task3 = phone_agent_protocol_v3_t3.format(phone_number, code)
+    result = agent.run(prompt_task3)
+    print(f"prompt_task3: {result}")
+    
+    # 解析JSON结果
+    try:
+        result_json = json.loads(result)
+        # 检查任务3是否成功
+        return result_json.get("status") == "success"
+    except json.JSONDecodeError:
+        # 如果不是JSON格式，尝试兼容旧格式
+        return "登录成功" in result
+
+def example_with_callbacks(lang: str = "cn"):
+    """Task example with callbacks / 带回调的任务示例"""
+    msgs = get_messages(lang)
+
+    def my_confirmation(message: str) -> bool:
+        """Sensitive operation confirmation callback / 敏感操作确认回调"""
+        print(f"\n[{msgs['confirmation_required']}] {message}")
+        response = input(f"{msgs['continue_prompt']}: ")
+        return response.lower() in ("yes", "y", "是")
+
+    def my_takeover(message: str) -> None:
+        """Manual takeover callback / 人工接管回调"""
+        print(f"\n[{msgs['manual_operation_required']}] {message}")
+        print(msgs["manual_operation_hint"])
+        input(f"{msgs['press_enter_when_done']}: ")
+
+    # Create Agent with custom callbacks
+    agent_config = AgentConfig(lang=lang)
+    agent = PhoneAgent(
+        agent_config=agent_config,
+        confirmation_callback=my_confirmation,
+        takeover_callback=my_takeover,
+    )
+
+    # Execute task that may require confirmation
+    result = agent.run("打开淘宝搜索无线耳机并加入购物车")
+    print(f"{msgs['task_result']}: {result}")
+
+
+def example_step_by_step(lang: str = "cn"):
+    """Step-by-step execution example (for debugging) / 单步执行示例（用于调试）"""
+    msgs = get_messages(lang)
+
+    agent_config = AgentConfig(lang=lang)
+    agent = PhoneAgent(agent_config=agent_config)
+
+    # Initialize task
+    result = agent.step("打开美团搜索附近的火锅店")
+    print(f"{msgs['step']} 1: {result.action}")
+
+    # Continue if not finished
+    while not result.finished and agent.step_count < 10:
+        result = agent.step()
+        print(f"{msgs['step']} {agent.step_count}: {result.action}")
+        print(f"  {msgs['thinking']}: {result.thinking[:100]}...")
+
+    print(f"\n{msgs['final_result']}: {result.message}")
+
+
+def example_multiple_tasks(lang: str = "cn"):
+    """Batch task example / 批量任务示例"""
+    msgs = get_messages(lang)
+
+    agent_config = AgentConfig(lang=lang)
+    agent = PhoneAgent(agent_config=agent_config)
+
+    tasks = [
+        "打开高德地图查看实时路况",
+        "打开大众点评搜索附近的咖啡店",
+        "打开bilibili搜索Python教程",
+    ]
+
+    for task in tasks:
+        print(f"\n{'=' * 50}")
+        print(f"{msgs['task']}: {task}")
+        print("=" * 50)
+
+        result = agent.run(task)
+        print(f"{msgs['result']}: {result}")
+
+        # Reset Agent state
+        agent.reset()
+
+
+def example_remote_device(lang: str = "cn"):
+    """Remote device example / 远程设备示例"""
+    from phone_agent.adb import ADBConnection
+
+    msgs = get_messages(lang)
+
+    # Create connection manager
+    conn = ADBConnection()
+
+    # Connect to remote device
+    success, message = conn.connect("192.168.1.100:5555")
+    if not success:
+        print(f"{msgs['connection_failed']}: {message}")
+        return
+
+    print(f"{msgs['connection_successful']}: {message}")
+
+    # Create Agent with device specified
+    agent_config = AgentConfig(
+        device_id="192.168.1.100:5555",
+        verbose=True,
+        lang=lang,
+    )
+
+    agent = PhoneAgent(agent_config=agent_config)
+
+    # Execute task
+    result = agent.run("打开微信查看消息")
+    print(f"{msgs['task_result']}: {result}")
+
+    # Disconnect
+    conn.disconnect("192.168.1.100:5555")
+
+
+
+def check_adb_devices():
+    """Check if any ADB devices are connected / 检查是否有 ADB 设备连接"""
+    import subprocess
+    try:
+        result = subprocess.run(["adb", "devices"], capture_output=True, text=True)
+        lines = result.stdout.strip().split("\n")[1:] # Skip header
+        devices = [line for line in lines if line.strip()]
+        if not devices:
+            print("\nError: No Android devices connected via ADB.")
+            print("错误: 未通过 ADB 连接任何 Android 设备。")
+            print("Please connect a device or start an emulator.")
+            print("请连接设备或启动模拟器。")
+            return False
+        return True
+    except FileNotFoundError:
+        print("\nError: 'adb' command not found. Please install Android Platform Tools.")
+        print("错误: 未找到 'adb' 命令。请安装 Android Platform Tools。")
+        return False
+#
+# if __name__ == "__main__":
+#     if not check_adb_devices():
+#         exit(1)
+#
+#     import argparse
+#
+#     parser = argparse.ArgumentParser(description="Phone Agent Usage Examples")
+#     parser.add_argument(
+#         "--lang",
+#         type=str,
+#         default="cn",
+#         choices=["cn", "en"],
+#         help="Language for UI messages (cn=Chinese, en=English)",
+#     )
+#     args = parser.parse_args()
+#
+#     msgs = get_messages(args.lang)
+#
+#     print("Phone Agent Usage Examples")
+#     print("=" * 50)
+#
+#     # Run basic example
+#     print(f"\n1. Basic Task Example")
+#     print("-" * 30)
+#     do_login(args.lang)
+#
+#     # Uncomment to run other examples
+#     # print(f"\n2. Task Example with Callbacks")
+#     # print("-" * 30)
+#     # example_with_callbacks(args.lang)
+#
+#     # print(f"\n3. Step-by-step Example")
+#     # print("-" * 30)
+#     # example_step_by_step(args.lang)
+#
+#     # print(f"\n4. Batch Task Example")
+#     # print("-" * 30)
+#     # example_multiple_tasks(args.lang)
+#
+#     # print(f"\n5. Remote Device Example")
+#     # print("-" * 30)
+#     # example_remote_device(args.lang)

xhs_note_extractor/cli.py

@@ -0,0 +1,98 @@
+#!/usr/bin/env python3
+"""
+Command Line Interface for XHS Note Extractor
+"""
+
+import argparse
+import sys
+from pathlib import Path
+
+from .extractor import XHSNoteExtractor
+from .utils import NetworkUtils
+
+
+def main():
+    """Main entry point for the CLI application."""
+    parser = argparse.ArgumentParser(
+        description="Extract Xiaohongshu (Little Red Book) note data from URLs"
+    )
+    parser.add_argument(
+        "url",
+        help="Xiaohongshu note URL to extract data from"
+    )
+    parser.add_argument(
+        "-o", "--output",
+        help="Output file path (default: stdout)"
+    )
+    parser.add_argument(
+        "-f", "--format",
+        choices=["json", "csv"],
+        default="json",
+        help="Output format (default: json)"
+    )
+    parser.add_argument(
+        "-v", "--verbose",
+        action="store_true",
+        help="Enable verbose output"
+    )
+    
+    args = parser.parse_args()
+    
+    # Validate URL
+    if not NetworkUtils.is_valid_xhs_url(args.url):
+        print(f"Error: Invalid Xiaohongshu URL: {args.url}", file=sys.stderr)
+        sys.exit(1)
+    
+    try:
+        if args.verbose:
+            print(f"Extracting data from: {args.url}")
+        
+        # Initialize extractor
+        extractor = XHSNoteExtractor()
+        
+        # Extract note data
+        note_data = extractor.extract_note(args.url)
+        
+        if not note_data:
+            print("Error: Failed to extract note data", file=sys.stderr)
+            sys.exit(1)
+        
+        # Format output
+        if args.format == "json":
+            import json
+            output = json.dumps(note_data, ensure_ascii=False, indent=2)
+        else:  # csv
+            import csv
+            from io import StringIO
+            
+            # Convert to CSV format (simplified)
+            output_buffer = StringIO()
+            writer = csv.writer(output_buffer)
+            
+            # Write headers
+            writer.writerow(["Field", "Value"])
+            
+            # Write data rows
+            for key, value in note_data.items():
+                if isinstance(value, (list, dict)):
+                    value = str(value)
+                writer.writerow([key, value])
+            
+            output = output_buffer.getvalue()
+        
+        # Output result
+        if args.output:
+            output_path = Path(args.output)
+            output_path.write_text(output, encoding='utf-8')
+            if args.verbose:
+                print(f"Output saved to: {output_path}")
+        else:
+            print(output)
+            
+    except Exception as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

xhs_note_extractor/date_desc_utils.py

@@ -0,0 +1,80 @@
+import re
+from datetime import datetime, timedelta
+
+def parse_time_to_timestamp_ms(time_str: str, now: datetime | None = None) -> int:
+    if now is None:
+        now = datetime.now()
+
+    time_str = time_str.strip()
+    # Remove common prefixes
+    for prefix in ["编辑于", "发布于"]:
+        if time_str.startswith(prefix):
+            time_str = time_str[len(prefix):].strip()
+    
+    # Remove location suffix (e.g., "昨天 15:09重庆" -> "昨天 15:09")
+    # Match common Chinese city/province names at the end
+    import re as re_module
+    time_str = re_module.sub(r'[\u4e00-\u9fa5]{2,4}$', '', time_str).strip()
+
+    # 刚刚
+    if time_str == "刚刚":
+        dt = now
+
+    # X分钟前
+    elif match := re.match(r"(\d+)分钟前", time_str):
+        dt = now - timedelta(minutes=int(match.group(1)))
+
+    # X小时前
+    elif match := re.match(r"(\d+)小时前", time_str):
+        dt = now - timedelta(hours=int(match.group(1)))
+
+    # X天前
+    elif match := re.match(r"(\d+)天前", time_str):
+        dt = now - timedelta(days=int(match.group(1)))
+
+    # 今天 HH:mm
+    elif match := re.match(r"今天\s*(\d{1,2}:\d{2})", time_str):
+        dt = datetime.strptime(
+            f"{now.date()} {match.group(1)}",
+            "%Y-%m-%d %H:%M"
+        )
+
+    # 昨天 HH:mm
+    elif match := re.match(r"昨天\s*(\d{1,2}:\d{2})", time_str):
+        dt = datetime.strptime(
+            f"{(now - timedelta(days=1)).date()} {match.group(1)}",
+            "%Y-%m-%d %H:%M"
+        )
+
+    # 前天 HH:mm
+    elif match := re.match(r"前天\s*(\d{1,2}:\d{2})", time_str):
+        dt = datetime.strptime(
+            f"{(now - timedelta(days=2)).date()} {match.group(1)}",
+            "%Y-%m-%d %H:%M"
+        )
+
+    # YYYY-MM-DD HH:mm
+    elif re.match(r"\d{4}-\d{2}-\d{2}\s+\d{1,2}:\d{2}", time_str):
+        dt = datetime.strptime(time_str, "%Y-%m-%d %H:%M")
+
+    # YYYY-MM-DD
+    elif re.match(r"\d{4}-\d{2}-\d{2}", time_str):
+        dt = datetime.strptime(time_str, "%Y-%m-%d")
+
+    # ✅ 新增：MM-DD（默认当前年份）
+    elif match := re.match(r"(\d{2})-(\d{2})", time_str):
+        year = now.year
+        month, day = map(int, match.groups())
+        dt = datetime(year, month, day)
+
+    # HH:mm（默认当天）
+    elif re.match(r"\d{1,2}:\d{2}", time_str):
+        dt = datetime.strptime(
+            f"{now.date()} {time_str}",
+            "%Y-%m-%d %H:%M"
+        )
+
+    else:
+        raise ValueError(f"无法解析的时间格式: {time_str}")
+
+    return int(dt.timestamp() * 1000)