aichat2md 1.0.1__tar.gz → 1.2.0__tar.gz

{aichat2md-1.0.1 → aichat2md-1.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aichat2md
-Version: 1.0.1
+Version: 1.2.0
 Summary: Convert AI chat conversations to structured Markdown
 Author: PlaceNameDay
 License: MIT
@@ -24,6 +24,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: playwright>=1.40.0
 Requires-Dist: requests>=2.31.0
+Requires-Dist: yaspin>=3.0.0
 Dynamic: license-file
 
 # aichat2md
@@ -32,7 +33,7 @@ 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 +56,30 @@ 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-1.0.1 → aichat2md-1.2.0}/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-1.0.1 → aichat2md-1.2.0}/aichat2md/__init__.py

@@ -1,5 +1,5 @@
 """aichat2md - Convert AI chat conversations to structured Markdown."""
 
-__version__ = "1.0.1"
+__version__ = "1.2.0"
 __author__ = "PlaceNameDay"
 __description__ = "Convert AI chat conversations to structured Markdown"

{aichat2md-1.0.1 → aichat2md-1.2.0}/aichat2md/cli.py

@@ -15,6 +15,9 @@ import sys
 from pathlib import Path
 from datetime import datetime
 from typing import Tuple
+import time
+
+from yaspin import yaspin
 
 from .config import setup_config, load_config
 from .extractors.playwright_extractor import extract_from_url
@@ -23,6 +26,17 @@ from .structurizer import structurize_content
 from . import __version__
 
 
+class TimedText:
+    """Dynamic text with elapsed time in seconds."""
+    def __init__(self, text: str):
+        self.text = text
+        self._start = time.time()
+
+    def __str__(self):
+        elapsed = int(time.time() - self._start)
+        return f"[{elapsed}s] {self.text}"
+
+
 def sanitize_filename(title: str, max_length: int = 50) -> str:
     """
     Sanitize title for use as filename.
@@ -87,15 +101,17 @@ def extract_content(input_path: str) -> Tuple[str, str]:
         Tuple of (extracted_text, source_identifier)
     """
     if input_path.startswith('http'):
-        print(f"📡 Extracting from URL: {input_path}")
-        text = extract_from_url(input_path)
+        with yaspin(text=TimedText(f"Extracting from URL (up to 60s): {input_path}")) as sp:
+            text = extract_from_url(input_path)
+            sp.ok(f"✓ Extracted {len(text)} characters")
         source = input_path
     else:
+        # Webarchive extraction is fast, no spinner needed
         print(f"📄 Extracting from webarchive: {input_path}")
         text = extract_from_webarchive(input_path)
+        print(f"✓ Extracted {len(text)} characters")
         source = Path(input_path).name
 
-    print(f"✓ Extracted {len(text)} characters")
     return text, source
 
 
@@ -221,8 +237,10 @@ Examples:
 
         # Structurize with AI
         provider = config.get("api_base_url", "API")
-        print(f"🤖 Structurizing with {provider}...")
-        markdown = structurize_content(raw_text, config, source)
+        estimated = min(60 + len(raw_text) // 100, 600)
+        with yaspin(text=TimedText(f"Structurizing {len(raw_text)} chars with {provider} (~{estimated}s)")) as sp:
+            markdown = structurize_content(raw_text, config, source)
+            sp.ok("✓ Structurized")
 
         # Determine output path
         output_path = determine_output_path(args.input, markdown, config, args.output)

aichat2md-1.2.0/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 = 60000) -> 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=60000)
+
+            # 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-1.0.1 → aichat2md-1.2.0}/aichat2md/structurizer.py

@@ -81,7 +81,9 @@ def structurize_content(
     }
 
     try:
-        response = requests.post(api_url, headers=headers, json=payload, timeout=60)
+        # Dynamic timeout based on content size: 60s base + 1s per 100 chars, max 600s
+        estimated_timeout = min(60 + len(raw_text) // 100, 600)
+        response = requests.post(api_url, headers=headers, json=payload, timeout=estimated_timeout)
         response.raise_for_status()
 
         result = response.json()

{aichat2md-1.0.1 → aichat2md-1.2.0}/aichat2md.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aichat2md
-Version: 1.0.1
+Version: 1.2.0
 Summary: Convert AI chat conversations to structured Markdown
 Author: PlaceNameDay
 License: MIT
@@ -24,6 +24,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: playwright>=1.40.0
 Requires-Dist: requests>=2.31.0
+Requires-Dist: yaspin>=3.0.0
 Dynamic: license-file
 
 # aichat2md
@@ -32,7 +33,7 @@ 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 +56,30 @@ 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-1.0.1 → aichat2md-1.2.0}/aichat2md.egg-info/requires.txt

@@ -1,2 +1,3 @@
 playwright>=1.40.0
 requests>=2.31.0
+yaspin>=3.0.0

{aichat2md-1.0.1 → aichat2md-1.2.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "aichat2md"
-version = "1.0.1"
+version = "1.2.0"
 description = "Convert AI chat conversations to structured Markdown"
 readme = "README.md"
 requires-python = ">=3.8"
@@ -28,6 +28,7 @@ classifiers = [
 dependencies = [
     "playwright>=1.40.0",
     "requests>=2.31.0",
+    "yaspin>=3.0.0",
 ]
 
 [project.scripts]

aichat2md-1.0.1/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])