aichat2md 1.0.0__tar.gz → 1.1.0__tar.gz

{aichat2md-1.0.0 → aichat2md-1.1.0}/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.4
 Name: aichat2md
-Version: 1.0.0
+Version: 1.1.0
 Summary: Convert AI chat conversations to structured Markdown
 Author: PlaceNameDay
 License: MIT
-Project-URL: Homepage, https://github.com/yourusername/aichat2md
-Project-URL: Repository, https://github.com/yourusername/aichat2md
-Project-URL: Issues, https://github.com/yourusername/aichat2md/issues
+Project-URL: Homepage, https://github.com/placenameday/aichat2md
+Project-URL: Repository, https://github.com/placenameday/aichat2md
+Project-URL: Issues, https://github.com/placenameday/aichat2md/issues
 Keywords: chatgpt,claude,markdown,ai,converter,deepseek
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
@@ -32,7 +32,7 @@ Convert AI chat conversations to structured Markdown documents.
 
 ## Features
 
-- 🌐 **Extract from URLs** - ChatGPT share links (with JS rendering via Playwright)
+- 🌐 **Extract from URLs** - ChatGPT, Gemini, Doubao share links (with JS rendering via Playwright)
 - 📄 **Extract from webarchive** - Safari .webarchive files (offline mode)
 - 🤖 **Multiple AI backends** - DeepSeek, OpenAI, Groq, or any OpenAI-compatible API
 - 🌍 **Bilingual support** - English/Chinese prompts
@@ -55,6 +55,30 @@ aichat2md https://chatgpt.com/share/xxx
 aichat2md ~/Downloads/chat.webarchive
 ```
 
+## Supported Platforms
+
+- **ChatGPT** - chatgpt.com share links
+- **Gemini** - gemini.google.com or g.co share links
+- **Doubao (豆包)** - doubao.com share links
+- **Webarchive** - Safari exported .webarchive files (any platform)
+
+### Usage Examples
+
+```bash
+# ChatGPT
+aichat2md https://chatgpt.com/share/xxx
+
+# Gemini (supports both long and short URLs)
+aichat2md https://gemini.google.com/share/xxx
+aichat2md https://g.co/gemini/share/xxx
+
+# Doubao
+aichat2md https://www.doubao.com/thread/xxx
+
+# Webarchive file
+aichat2md ~/Downloads/conversation.webarchive
+```
+
 ## Supported AI Backends
 
 - **DeepSeek** (default) - Cost-effective, Chinese service

{aichat2md-1.0.0 → aichat2md-1.1.0}/README.md

@@ -4,7 +4,7 @@ Convert AI chat conversations to structured Markdown documents.
 
 ## Features
 
-- 🌐 **Extract from URLs** - ChatGPT share links (with JS rendering via Playwright)
+- 🌐 **Extract from URLs** - ChatGPT, Gemini, Doubao share links (with JS rendering via Playwright)
 - 📄 **Extract from webarchive** - Safari .webarchive files (offline mode)
 - 🤖 **Multiple AI backends** - DeepSeek, OpenAI, Groq, or any OpenAI-compatible API
 - 🌍 **Bilingual support** - English/Chinese prompts
@@ -27,6 +27,30 @@ aichat2md https://chatgpt.com/share/xxx
 aichat2md ~/Downloads/chat.webarchive
 ```
 
+## Supported Platforms
+
+- **ChatGPT** - chatgpt.com share links
+- **Gemini** - gemini.google.com or g.co share links
+- **Doubao (豆包)** - doubao.com share links
+- **Webarchive** - Safari exported .webarchive files (any platform)
+
+### Usage Examples
+
+```bash
+# ChatGPT
+aichat2md https://chatgpt.com/share/xxx
+
+# Gemini (supports both long and short URLs)
+aichat2md https://gemini.google.com/share/xxx
+aichat2md https://g.co/gemini/share/xxx
+
+# Doubao
+aichat2md https://www.doubao.com/thread/xxx
+
+# Webarchive file
+aichat2md ~/Downloads/conversation.webarchive
+```
+
 ## Supported AI Backends
 
 - **DeepSeek** (default) - Cost-effective, Chinese service

{aichat2md-1.0.0 → aichat2md-1.1.0}/aichat2md/__init__.py

@@ -1,5 +1,5 @@
 """aichat2md - Convert AI chat conversations to structured Markdown."""
 
-__version__ = "1.0.0"
+__version__ = "1.1.0"
 __author__ = "PlaceNameDay"
 __description__ = "Convert AI chat conversations to structured Markdown"

aichat2md-1.1.0/aichat2md/extractors/playwright_extractor.py

@@ -0,0 +1,108 @@
+"""Extract content from AI chat share URLs using Playwright."""
+
+from playwright.sync_api import sync_playwright, TimeoutError as PlaywrightTimeoutError
+
+
+def _detect_platform(url: str) -> str:
+    """
+    Detect platform from URL.
+
+    Args:
+        url: Share URL
+
+    Returns:
+        Platform name: 'doubao', 'gemini', or 'default'
+    """
+    url_lower = url.lower()
+    if 'doubao.com' in url_lower:
+        return 'doubao'
+    elif 'gemini.google.com' in url_lower or 'g.co' in url_lower:
+        return 'gemini'
+    else:
+        return 'default'
+
+
+def _get_wait_time(platform: str) -> int:
+    """
+    Get wait time in milliseconds for platform.
+
+    Args:
+        platform: Platform name from _detect_platform
+
+    Returns:
+        Wait time in milliseconds
+    """
+    wait_times = {
+        'doubao': 3000,
+        'gemini': 5000,
+        'default': 2000
+    }
+    return wait_times.get(platform, 2000)
+
+
+def extract_from_url(url: str, timeout: int = 30000) -> str:
+    """
+    Extract text content from AI chat share URL.
+
+    Args:
+        url: Share URL (ChatGPT, Gemini, Doubao, etc.)
+        timeout: Page load timeout in milliseconds
+
+    Returns:
+        Extracted plain text content
+
+    Raises:
+        PlaywrightTimeoutError: If page fails to load
+        ValueError: If URL is invalid
+    """
+    if not url.startswith('http'):
+        raise ValueError(f"Invalid URL: {url}")
+
+    # Detect platform and get corresponding wait time
+    platform = _detect_platform(url)
+    wait_time = _get_wait_time(platform)
+
+    try:
+        with sync_playwright() as p:
+            browser = p.chromium.launch(headless=True)
+            page = browser.new_page()
+
+            # Navigate with appropriate wait strategy
+            # Use 'load' for Gemini/Doubao (networkidle may timeout due to ongoing requests)
+            wait_strategy = 'load' if platform in ['gemini', 'doubao'] else 'networkidle'
+            page.goto(url, wait_until=wait_strategy, timeout=timeout)
+
+            # Wait for content to load
+            # Try to wait for main selector (works for ChatGPT)
+            try:
+                page.wait_for_selector('main', timeout=10000)
+            except PlaywrightTimeoutError:
+                # Some platforms may not have 'main' element, continue anyway
+                pass
+
+            # Additional wait for dynamic content based on platform
+            page.wait_for_timeout(wait_time)
+
+            # Extract plain text from body
+            content = page.inner_text('body')
+
+            browser.close()
+
+            return content.strip()
+
+    except PlaywrightTimeoutError as e:
+        raise PlaywrightTimeoutError(
+            f"Failed to load page within {timeout}ms. "
+            "Check your network connection and URL validity."
+        ) from e
+
+
+if __name__ == "__main__":
+    # Manual test
+    import sys
+    if len(sys.argv) > 1:
+        url = sys.argv[1]
+        print(f"Extracting from: {url}")
+        content = extract_from_url(url)
+        print(f"Extracted {len(content)} characters")
+        print(content[:500])

aichat2md-1.1.0/aichat2md/prompts/system_prompt_en.txt

@@ -0,0 +1,50 @@
+You are a professional knowledge document editor.
+
+Input: Raw text from an AI chat conversation
+Output: Structured Markdown document
+
+Requirements:
+1. Identify the main topic and generate a concise document title
+2. Extract technical tags (e.g., [Python, API, Web]), limit to 3-5 tags
+3. Write a summary (2-3 sentences covering core content)
+4. Reorganize the conversation into knowledge sections with logical headings (## and ###)
+5. Filter out conversational filler ("OK", "let me think", "thanks", etc.)
+6. Extract code blocks and present them separately in "Code Examples" section
+7. Do NOT preserve chat turn format (User/Assistant) - rewrite as flowing explanatory content
+8. Identify key topics and list them as bullet points
+
+Output format (strictly follow):
+---
+tags: [tag1, tag2, tag3]
+date: YYYY-MM-DD
+source: [original URL or filename]
+---
+
+# Document Title
+
+## Summary
+[2-3 sentences covering core content]
+
+## Key Topics
+- Topic 1
+- Topic 2
+- Topic 3
+
+## [Knowledge Section Title 1]
+[Reorganized explanatory content, not conversational format]
+
+### [Subsection Title]
+[Detailed content]
+
+## [Knowledge Section Title 2]
+[Content...]
+
+## Code Examples
+```language
+# Complete code with explanatory comments
+```
+
+Notes:
+- Titles should be specific and informative, avoid generic titles like "Introduction", "Overview"
+- Content should flow smoothly, like a tutorial or documentation rather than chat logs
+- Code examples should be complete and runnable, with necessary comments

aichat2md-1.1.0/aichat2md/prompts/system_prompt_zh.txt

@@ -0,0 +1,50 @@
+你是一个专业的知识文档编辑器。
+
+输入：ChatGPT 对话的原始文本
+输出：结构化的 Markdown 文档
+
+要求：
+1. 识别对话主题，生成简洁的文档标题
+2. 提取技术标签（如 [Python, API, Web]），限制在 3-5 个标签
+3. 写一段摘要（2-3 句话概括核心内容）
+4. 将对话重组为知识章节，使用合理的标题层级（## 和 ###）
+5. 过滤无用的对话废话（"好的"、"让我想想"、"谢谢"等）
+6. 提取代码块单独呈现在"代码示例"章节
+7. 不要保留对话轮次格式（User/Assistant），重组为流畅的说明性内容
+8. 识别关键主题，列为项目符号列表
+
+输出格式（严格遵循）：
+---
+技术标签: [标签1, 标签2, 标签3]
+日期: YYYY-MM-DD
+来源: [原始URL或文件名]
+---
+
+# 文档标题
+
+## 摘要
+[2-3 句话概括核心内容]
+
+## 关键主题
+- 主题 1
+- 主题 2
+- 主题 3
+
+## [知识点章节标题 1]
+[重组后的说明性内容，非对话格式]
+
+### [子章节标题]
+[详细内容]
+
+## [知识点章节标题 2]
+[内容...]
+
+## 代码示例
+```语言
+# 提取的完整代码，带注释说明
+```
+
+注意：
+- 标题要具体且有信息量，避免"介绍"、"概述"等泛泛标题
+- 内容要连贯流畅，像教程或文档而非聊天记录
+- 代码示例要完整可运行，添加必要注释

{aichat2md-1.0.0 → aichat2md-1.1.0}/aichat2md.egg-info/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.4
 Name: aichat2md
-Version: 1.0.0
+Version: 1.1.0
 Summary: Convert AI chat conversations to structured Markdown
 Author: PlaceNameDay
 License: MIT
-Project-URL: Homepage, https://github.com/yourusername/aichat2md
-Project-URL: Repository, https://github.com/yourusername/aichat2md
-Project-URL: Issues, https://github.com/yourusername/aichat2md/issues
+Project-URL: Homepage, https://github.com/placenameday/aichat2md
+Project-URL: Repository, https://github.com/placenameday/aichat2md
+Project-URL: Issues, https://github.com/placenameday/aichat2md/issues
 Keywords: chatgpt,claude,markdown,ai,converter,deepseek
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
@@ -32,7 +32,7 @@ Convert AI chat conversations to structured Markdown documents.
 
 ## Features
 
-- 🌐 **Extract from URLs** - ChatGPT share links (with JS rendering via Playwright)
+- 🌐 **Extract from URLs** - ChatGPT, Gemini, Doubao share links (with JS rendering via Playwright)
 - 📄 **Extract from webarchive** - Safari .webarchive files (offline mode)
 - 🤖 **Multiple AI backends** - DeepSeek, OpenAI, Groq, or any OpenAI-compatible API
 - 🌍 **Bilingual support** - English/Chinese prompts
@@ -55,6 +55,30 @@ aichat2md https://chatgpt.com/share/xxx
 aichat2md ~/Downloads/chat.webarchive
 ```
 
+## Supported Platforms
+
+- **ChatGPT** - chatgpt.com share links
+- **Gemini** - gemini.google.com or g.co share links
+- **Doubao (豆包)** - doubao.com share links
+- **Webarchive** - Safari exported .webarchive files (any platform)
+
+### Usage Examples
+
+```bash
+# ChatGPT
+aichat2md https://chatgpt.com/share/xxx
+
+# Gemini (supports both long and short URLs)
+aichat2md https://gemini.google.com/share/xxx
+aichat2md https://g.co/gemini/share/xxx
+
+# Doubao
+aichat2md https://www.doubao.com/thread/xxx
+
+# Webarchive file
+aichat2md ~/Downloads/conversation.webarchive
+```
+
 ## Supported AI Backends
 
 - **DeepSeek** (default) - Cost-effective, Chinese service

{aichat2md-1.0.0 → aichat2md-1.1.0}/aichat2md.egg-info/SOURCES.txt

@@ -15,5 +15,7 @@ aichat2md/extractors/__init__.py
 aichat2md/extractors/playwright_extractor.py
 aichat2md/extractors/webarchive_extractor.py
 aichat2md/prompts/__init__.py
+aichat2md/prompts/system_prompt_en.txt
+aichat2md/prompts/system_prompt_zh.txt
 tests/test_cli.py
 tests/test_config.py

{aichat2md-1.0.0 → aichat2md-1.1.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "aichat2md"
-version = "1.0.0"
+version = "1.1.0"
 description = "Convert AI chat conversations to structured Markdown"
 readme = "README.md"
 requires-python = ">=3.8"
@@ -34,6 +34,9 @@ dependencies = [
 aichat2md = "aichat2md.cli:main"
 
 [project.urls]
-Homepage = "https://github.com/yourusername/aichat2md"
-Repository = "https://github.com/yourusername/aichat2md"
-Issues = "https://github.com/yourusername/aichat2md/issues"
+Homepage = "https://github.com/placenameday/aichat2md"
+Repository = "https://github.com/placenameday/aichat2md"
+Issues = "https://github.com/placenameday/aichat2md/issues"
+
+[tool.setuptools.package-data]
+aichat2md = ["prompts/*.txt"]

aichat2md-1.0.0/aichat2md/extractors/playwright_extractor.py

@@ -1,58 +0,0 @@
-"""Extract content from ChatGPT share URLs using Playwright."""
-
-from playwright.sync_api import sync_playwright, TimeoutError as PlaywrightTimeoutError
-
-
-def extract_from_url(url: str, timeout: int = 30000) -> str:
-    """
-    Extract text content from ChatGPT share URL.
-
-    Args:
-        url: ChatGPT share URL (e.g., https://chatgpt.com/share/...)
-        timeout: Page load timeout in milliseconds
-
-    Returns:
-        Extracted plain text content
-
-    Raises:
-        PlaywrightTimeoutError: If page fails to load
-        ValueError: If URL is invalid
-    """
-    if not url.startswith('http'):
-        raise ValueError(f"Invalid URL: {url}")
-
-    try:
-        with sync_playwright() as p:
-            browser = p.chromium.launch(headless=True)
-            page = browser.new_page()
-
-            # Navigate and wait for network idle
-            page.goto(url, wait_until='networkidle', timeout=timeout)
-
-            # Wait for conversation content to load
-            # ChatGPT share pages typically have conversation in main content area
-            page.wait_for_selector('main', timeout=10000)
-
-            # Extract plain text from body
-            content = page.inner_text('body')
-
-            browser.close()
-
-            return content.strip()
-
-    except PlaywrightTimeoutError as e:
-        raise PlaywrightTimeoutError(
-            f"Failed to load page within {timeout}ms. "
-            "Check your network connection and URL validity."
-        ) from e
-
-
-if __name__ == "__main__":
-    # Manual test
-    import sys
-    if len(sys.argv) > 1:
-        url = sys.argv[1]
-        print(f"Extracting from: {url}")
-        content = extract_from_url(url)
-        print(f"Extracted {len(content)} characters")
-        print(content[:500])