QingLong/AI/T3_TextSummarize.py

# -*- coding: utf-8 -*-
from pathlib import Path
from typing import Optional, Tuple
from openai import OpenAI, APIError, APITimeoutError
import time
import httpx


class ContentAnalyzer:
    """课程内容分析器（长超时版）"""

    def __init__(
            self,
            api_key: str = "sk-01d13a39e09844038322108ecdbd1bbc",
            base_url: str = "https://dashscope.aliyuncs.com/compatible-mode/v1",
            model: str = "deepseek-r1",
            max_retries: int = 10,
            initial_timeout: int = 300  # 初始超时改为300秒
    ):
        self._show_progress("🔧", "初始化分析器...", level=0)
        self.client = OpenAI(api_key=api_key, base_url=base_url)
        self.model = model
        self.max_retries = max_retries
        self.initial_timeout = initial_timeout
        self._check_network()
        self._show_progress("✅", "分析器准备就绪", level=0)

    def _show_progress(self, emoji: str, message: str, level: int = 1):
        indent = "  " * level
        timestamp = time.strftime("%H:%M:%S")
        print(f"{indent}{emoji} [{timestamp}] {message}")

    def _check_network(self):
        try:
            with httpx.Client(timeout=30) as client:  # 网络检查超时延长到30秒
                client.get("https://dashscope.aliyuncs.com")
            self._show_progress("🌐", "网络连接正常", level=1)
        except Exception as e:
            self._show_progress("❌", f"网络异常: {str(e)}", level=1)
            raise

    def analyze_content(
            self,
            content: str,
            prompt_template: str = "帮我梳理：这节课分了几个部分，每部分的名称和开始的时间是多少：{}"
    ) -> Tuple[bool, str]:
        for attempt in range(self.max_retries + 1):
            try:
                # 动态计算超时时间：60s, 65s, 70s...
                current_timeout = self.initial_timeout + attempt * 5
                self._show_progress("⏱️", f"尝试 {attempt + 1}/{self.max_retries} (超时: {current_timeout}s)")

                full_prompt = prompt_template.format(content)
                completion = self.client.chat.completions.create(
                    model=self.model,
                    messages=[{'role': 'user', 'content': full_prompt}],
                    timeout=current_timeout
                )

                if not completion.choices:
                    self._show_progress("⚠️", "API返回空响应", level=2)
                    return False, "API响应中未包含有效结果"

                self._show_progress("✅", "请求成功", level=2)
                return True, completion.choices[0].message.content

            except APITimeoutError:
                if attempt < self.max_retries:
                    delay = 2 ** attempt
                    self._show_progress("⏳", f"{delay}s后重试...", level=2)
                    time.sleep(delay)
                else:
                    self._show_progress("❌", "超过最大重试次数", level=2)
                    return False, f"API请求超时，已重试{self.max_retries}次"

            except APIError as e:
                self._show_progress("🚨", f"API错误: {str(e)}", level=2)
                return False, f"API调用失败: {str(e)}"

            except Exception as e:
                self._show_progress("💥", f"意外错误: {str(e)}", level=2)
                return False, f"未处理的异常: {str(e)}"

        return False, "未知错误"

    def analyze_file(
            self,
            file_path: Path,
            output_path: Optional[Path] = None,
            encoding: str = 'utf-8'
    ) -> Tuple[bool, str]:
        """处理文件全流程"""
        try:
            self._show_progress("📂", f"开始处理文件: {file_path}", level=0)

            # 检查文件
            self._show_progress("🔍", "验证文件...", level=1)
            if not file_path.exists():
                self._show_progress("❌", "文件不存在", level=2)
                return False, f"文件不存在: {file_path}"
            if file_path.stat().st_size > 10 * 1024 * 1024:  # 10MB警告
                self._show_progress("⚠️", "注意：大文件可能影响处理速度", level=2)

            # 读取内容
            self._show_progress("📖", "读取文件内容...", level=1)
            try:
                content = file_path.read_text(encoding=encoding)
            except UnicodeDecodeError:
                self._show_progress("🔠", "解码失败，尝试GBK编码...", level=2)
                content = file_path.read_text(encoding='gbk')

            # 分析内容
            self._show_progress("🧠", "开始分析...", level=1)
            success, result = self.analyze_content(content)

            if not success:
                return False, result

            # 保存结果
            if output_path:
                self._show_progress("💾", f"保存到: {output_path}", level=1)
                try:
                    output_path.parent.mkdir(parents=True, exist_ok=True)
                    output_path.write_text(result, encoding=encoding)
                    self._show_progress("✅", "保存成功", level=2)
                except Exception as e:
                    self._show_progress("❌", f"保存失败: {str(e)}", level=2)
                    return False, f"结果保存失败: {str(e)}"

            self._show_progress("🎉", "处理完成！", level=0)
            return True, result

        except Exception as e:
            self._show_progress("💣", f"严重错误: {str(e)}", level=1)
            return False, f"文件处理失败: {str(e)}"


def analyzer_action(input_file,output_file):
    print("\n" + "=" * 50)
    print("  🚀 长春云校视频课程智能打标记系统  ".center(50, "✨"))
    print("=" * 50)

    analyzer = ContentAnalyzer(initial_timeout=300)  # 显式设置初始超时
    success, result = analyzer.analyze_file(input_file, output_file)

    print("\n" + "=" * 50)
    if success:
        print("✅ 分析成功！结果如下：\n")
        print(result)
    else:
        print(f"❌ 分析失败：{result}")
    print("=" * 50)