#!/usr/bin/env python3 """ Extract Gemini chat 33edddd2e796d6a9 content Login as kinan@agileadapt.com and extract all conversation content """ import asyncio import time import os from playwright.async_api import async_playwright EMAIL = "kinan@agileadapt.com" PASSWORD = "Systema55" CHAT_URL = "https://gemini.google.com/app/33edddd2e796d6a9" OUTPUT_PATH = "/mnt/e/genesis-system/Conversations/gemini_chat_33edddd2e796d6a9_FULL.md" SCREENSHOT_DIR = "/mnt/e/genesis-system/hive/progress" async def extract_chat(): async with async_playwright() as p: browser = await p.chromium.launch( headless=True, args=['--no-sandbox', '--disable-setuid-sandbox', '--disable-dev-shm-usage'] ) context = await browser.new_context( viewport={"width": 1280, "height": 900}, user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36" ) page = await context.new_page() print("Step 1: Navigating to Google login...") await page.goto("https://accounts.google.com", wait_until='domcontentloaded', timeout=30000) await page.wait_for_timeout(2000) # Take screenshot of login page await page.screenshot(path=f"{SCREENSHOT_DIR}/gemini33edd_01_login.png") print(" Screenshot saved: gemini33edd_01_login.png") print("Step 2: Entering email...") try: await page.locator('input[type="email"]').fill(EMAIL) await page.wait_for_timeout(500) await page.keyboard.press("Enter") await page.wait_for_timeout(3000) except Exception as e: print(f" Email fill error: {e}") # Try alternate selector await page.fill('#identifierId', EMAIL) await page.wait_for_timeout(500) await page.click('#identifierNext') await page.wait_for_timeout(3000) await page.screenshot(path=f"{SCREENSHOT_DIR}/gemini33edd_02_after_email.png") print(" Screenshot saved: gemini33edd_02_after_email.png") print("Step 3: Entering password...") try: await page.locator('input[type="password"]').fill(PASSWORD) await page.wait_for_timeout(500) await page.keyboard.press("Enter") await page.wait_for_timeout(5000) except Exception as e: print(f" Password fill error: {e}") await page.screenshot(path=f"{SCREENSHOT_DIR}/gemini33edd_03_after_password.png") print(" Screenshot saved: gemini33edd_03_after_password.png") current_url = page.url print(f" Current URL after login: {current_url}") # Check if we need 2FA or other challenge page_content = await page.inner_text('body') if "2-Step" in page_content or "2FA" in page_content or "verification" in page_content.lower(): print(" WARNING: 2FA/verification required") print("Step 4: Navigating to Gemini chat...") await page.goto(CHAT_URL, wait_until='domcontentloaded', timeout=30000) await page.wait_for_timeout(5000) await page.screenshot(path=f"{SCREENSHOT_DIR}/gemini33edd_04_chat_page.png") print(" Screenshot saved: gemini33edd_04_chat_page.png") current_url = page.url print(f" Current URL: {current_url}") # Scroll to load all content print("Step 5: Scrolling to load all content...") for i in range(5): await page.evaluate("window.scrollTo(0, document.body.scrollHeight)") await page.wait_for_timeout(1000) await page.evaluate("window.scrollTo(0, 0)") await page.wait_for_timeout(500) # Final scroll to bottom await page.evaluate("window.scrollTo(0, document.body.scrollHeight)") await page.wait_for_timeout(2000) print("Step 6: Extracting page content...") full_text = await page.inner_text('body') page_title = await page.title() print(f" Page title: {page_title}") print(f" Full text length: {len(full_text)} chars") # Try to get structured messages print("Step 7: Trying to get structured message elements...") # Try various selectors for Gemini messages structured_content = [] selectors_to_try = [ 'model-response', 'user-query', '[data-message-author-role]', '.conversation-turn', 'message-content', '[class*="message"]', '[class*="turn"]', '[class*="response"]', '[class*="query"]', 'p', ] for selector in selectors_to_try[:6]: # Try first 6 try: elements = await page.locator(selector).all() if elements: print(f" Found {len(elements)} elements with selector: {selector}") texts = [] for el in elements: try: text = await el.inner_text() if text.strip() and len(text.strip()) > 10: texts.append(text.strip()) except: pass if texts: structured_content.append(f"\n## Selector: {selector}\n" + "\n---\n".join(texts[:50])) except Exception as e: print(f" Selector {selector} failed: {e}") # Get page HTML for further analysis page_html = await page.content() print(f" Page HTML length: {len(page_html)} chars") # Save screenshot of final state await page.screenshot(path=f"{SCREENSHOT_DIR}/gemini33edd_05_final.png", full_page=True) print(" Screenshot saved: gemini33edd_05_final.png") # Build output markdown output_content = f"""# Gemini Chat Extraction: 33edddd2e796d6a9 **Extracted**: 2026-02-20 **URL**: {CHAT_URL} **Page Title**: {page_title} **Final URL**: {current_url} **Total Body Text Length**: {len(full_text)} characters --- ## FULL BODY TEXT {full_text} --- ## STRUCTURED ELEMENTS {chr(10).join(structured_content) if structured_content else "No structured elements found with tested selectors"} """ # Save to file os.makedirs("/mnt/e/genesis-system/Conversations", exist_ok=True) with open(OUTPUT_PATH, 'w', encoding='utf-8') as f: f.write(output_content) print(f"\nStep 8: Content saved to {OUTPUT_PATH}") print(f" Output file size: {os.path.getsize(OUTPUT_PATH)} bytes") # Also save raw HTML for analysis html_path = OUTPUT_PATH.replace('.md', '_raw.html') with open(html_path, 'w', encoding='utf-8') as f: f.write(page_html) print(f" Raw HTML saved to {html_path}") await browser.close() return { 'full_text': full_text, 'page_title': page_title, 'current_url': current_url, 'text_length': len(full_text), 'structured_sections': len(structured_content) } if __name__ == "__main__": result = asyncio.run(extract_chat()) print(f"\n=== EXTRACTION COMPLETE ===") print(f"Text length: {result['text_length']}") print(f"Page title: {result['page_title']}") print(f"Final URL: {result['current_url']}") print(f"Structured sections found: {result['structured_sections']}")