1 line
90 KiB
JSON
1 line
90 KiB
JSON
{"repo": "beak2825/epstein-files-archive", "files": {"2fetcher.py": {"11fd63b69d8fe5cead76364a6c78bdcee214a842": {"t": 1785604116.9414802, "n": 15187, "h": "6811f4922090e336", "c": "import requests\nfrom bs4 import BeautifulSoup\nimport os\nfrom urllib.parse import urlparse, unquote\nfrom email.utils import parsedate_to_datetime\nimport re\nimport time\nfrom datetime import datetime, timedelta\n\n\nimport http.client\n\nhttp.client._MAXHEADERS = 1000\n# Define headers and cookies\nheaders = {\n \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/144.0.0.0 Safari/537.36\",\n \"Accept-Language\": \"en-US,en;q=0.9\",\n \"Accept-Encoding\": \"gzip, deflate, br\",\n \"Referer\": \"https://www.justice.gov/epstein/doj-disclosures\",\n \"Origin\": \"https://www.justice.gov\",\n \"Cookie\": \"justiceGovAgeVerified=true\"\n}\n\n# List of wanted headers for file metadata\nwanted_headers = [\n 'Date', 'Cache-Control', 'Content-Length', 'Etag', 'Expires', \n 'Last-Modified', 'Pragma', 'Server', 'Quic-Version', \n 'Content-Type', 'Alt-Svc', 'Accept-Ranges'\n]\n\n# Global counter for files processed\nfile_counter = 0\n\n# Function to update or append to HASHES.txt\ndef update_hashes_file(basename, last_mod, etag):\n hashes_file = 'HASHES.txt'\n lines = []\n updated = False\n \n if os.path.exists(hashes_file):\n with open(hashes_file, 'r', encoding='utf-8') as f:\n lines = f.readlines()\n \n pattern = re.compile(rf'^{re.escape(basename)}:\\s*(.*)$')\n for i, line in enumerate(lines):\n match = pattern.match(line.strip())\n if match:\n lines[i] = f\"{basename}: {last_mod}, {etag}\\n\"\n updated = True\n break\n \n if not updated:\n # Append to file\n with open(hashes_file, 'a', encoding='utf-8') as h:\n h.write(f\"{basename}: {last_mod}, {etag}\\n\")\n else:\n # Rewrite entire file with updated line\n with open(hashes_file, 'w', encoding='utf-8') as h:\n h.writelines(lines)\n\n# Function to get existing hash data from HASHES.txt\ndef get_hash_data(basename):\n \"\"\"Returns tuple (last_modified, etag) or (None, None) if not found\"\"\"\n hashes_file = 'HASHES.txt'\n if not os.path.exists(hashes_file):\n return None, None\n \n pattern = re.compile(rf'^{re.escape(basename)}:\\s*(.*)$')\n with open(hashes_file, 'r', encoding='utf-8') as f:\n for line in f:\n match = pattern.match(line.strip())\n if match:\n # Parse the data: \"Last-Modified, Etag\"\n data = match.group(1)\n parts = data.split(',', 1)\n if len(parts) == 2:\n return parts[0].strip(), parts[1].strip().strip('\"')\n return None, None\n\n# Function to save page link every 50 files\ndef save_page_link(dataset_num, page):\n with open('page_link.txt', 'w', encoding='utf-8') as f:\n f.write(f\"dataset={dataset_num}\\n\")\n f.write(f\"page={page}\\n\")\n\n# Function to load saved page link\ndef load_page_link():\n if not os.path.exists('page_link.txt'):\n return None, None\n \n try:\n with open('page_link.txt', 'r', encoding='utf-8') as f:\n lines = f.readlines()\n dataset = None\n page = None\n for line in lines:\n if line.startswith('dataset='):\n dataset = int(line.split('=')[1].strip())\n elif line.startswith('page='):\n page = int(line.split('=')[1].strip())\n return dataset, page\n except:\n return None, None\n\n# Function to check if error already exists in deleted.txt\ndef is_in_deleted_file(error_line):\n if not os.path.exists('deleted.txt'):\n return False\n \n with open('deleted.txt', 'r', encoding='utf-8') as f:\n for line in f:\n if line.strip() == error_line.strip():\n return True\n return False\n\n# Function to append to deleted.txt if not already present\ndef append_to_deleted(error_line):\n if not is_in_deleted_file(error_line):\n with open('deleted.txt', 'a', encoding='utf-8') as f:\n f.write(error_line + '\\n')\n\n# Function to check if file was processed and when\ndef check_file_processed(basename, dataset_num, reprocess_enabled):\n \"\"\"\n Returns tuple (processed, skip):\n - processed: True if file exists\n - skip: True if we should skip (exists and within 24h cooldown or reprocess disabled)\n \"\"\"\n txt_path = f\"EFTA/DataSet_{dataset_num}/{basename}.txt\"\n \n if not os.path.exists(txt_path):\n return False, False\n \n # File exists, check if reprocessing is enabled\n if not reprocess_enabled:\n return True, True\n \n # Check the Date header to determine when it was last processed\n try:\n with open(txt_path, 'r', encoding='utf-8') as f:\n for line in f:\n if line.startswith('Date:'):\n date_str = line.split('Date:', 1)[1].strip()\n processed_date = parsedate_to_datetime(date_str)\n now = datetime.now(processed_date.tzinfo)\n time_diff = now - processed_date\n \n # If less than 24 hours, skip\n if time_diff < timedelta(hours=24):\n return True, True\n else:\n # More than 24 hours, allow reprocessing\n return True, False\n except:\n # If we can't read the date, allow reprocessing\n return True, False\n \n # No Date header found, allow reprocessing\n return True, False\n\n# Function to check if important data has changed\ndef has_data_changed(basename, new_last_mod, new_etag):\n \"\"\"Check if Etag or Last-Modified has changed\"\"\"\n old_last_mod, old_etag = get_hash_data(basename)\n \n if old_last_mod is None and old_etag is None:\n # No existing data\n return True\n \n # Compare Etag and Last-Modified\n if new_etag != old_etag or new_last_mod != old_last_mod:\n return True\n \n return False\n\n# Interactive start\nprint(\"Welcome to the Epstein Files Archiver.\")\nprint(\"Options:\")\nprint(\" 'normal' - Start from dataset 1, page 0\")\nprint(\" 'custom' - Specify dataset and page\")\nprint(\" 'resume' - Resume from saved page_link.txt\")\nchoice = input(\"Enter your choice: \").strip().lower()\n\n# Ask about reprocessing\nreprocess_input = input(\"Enable reprocessing after 24h cooldown? (yes/no, default: yes): \").strip().lower()\nreprocess_enabled = True if reprocess_input in ['', 'yes', 'y'] else False\n\nif reprocess_enabled:\n print(\"Reprocessing enabled: Files will be rechecked after 24 hours.\")\nelse:\n print(\"Reprocessing disabled: Already processed files will be skipped permanently.\")\n\nif choice == 'normal':\n dataset_num = 1\n start_page = 0\n print(\"Starting normal run from dataset 1, page 0.\")\nelif choice == 'custom':\n try:\n dataset_num = int(input(\"Enter starting dataset number: \"))\n start_page = int(input(\"Enter starting page number for that dataset: \"))\n print(f\"Starting from dataset {dataset_num}, page {start_page}.\")\n except ValueError:\n print(\"Invalid input. Starting normal run from dataset 1.\")\n dataset_num = 1\n start_page = 0\nelif choice == 'resume':\n dataset_num, start_page = load_page_link()\n if dataset_num is None or start_page is None:\n print(\"No saved progress found in page_link.txt. Starting from dataset 1, page 0.\")\n dataset_num = 1\n start_page = 0\n else:\n print(f\"Resuming from saved progress: dataset {dataset_num}, page {start_page}.\")\nelse:\n print(\"Invalid choice. Starting normal run from dataset 1.\")\n dataset_num = 1\n start_page = 0\n\nwhile True:\n base_url = f\"https://www.justice.gov/epstein/doj-disclosures/data-set-{dataset_num}-files\"\n \n # For the starting page if resuming\n page = start_page\n current_url = base_url if page == 0 else f\"{base_url}?page={page}\"\n \n # Fetch the first page (or resumed page)\n resp = requests.get(current_url, headers=headers, allow_redirects=False)\n \n if resp.status_code == 403:\n # Save the 403 response\n os.makedirs('unreleased-datasets', exist_ok=True)\n html_path = f\"unreleased-datasets/data-set-{dataset_num}-files.html\"\n txt_path = f\"unreleased-datasets/data-set-{dataset_num}-files.txt\"\n \n with open(html_path, 'w', encoding='utf-8') as f:\n f.write(resp.text)\n \n headers_txt = f\"Status-Code: {resp.status_code}\\n\"\n sorted_resp_headers = sorted(resp.headers.items(), key=lambda x: x[0])\n for k, v in sorted_resp_headers:\n headers_txt += f\"{k}: {v}\\n\"\n \n with open(txt_path, 'w', encoding='utf-8') as f:\n f.write(headers_txt)\n \n # Go to next dataset\n dataset_num += 1\n # Reset page to 0 for next dataset\n start_page = 0\n continue\n \n elif resp.status_code == 404:\n # Save the 404 response with fixed name as specified\n os.makedirs('unreleased-datasets', exist_ok=True)\n html_path = \"unreleased-datasets/404.html\"\n txt_path = \"unreleased-datasets/404.txt\"\n \n with open(html_path, 'w', encoding='utf-8') as f:\n f.write(resp.text)\n \n headers_txt = f\"Status-Code: {resp.status_code}\\n\"\n sorted_resp_headers = sorted(resp.headers.items(), key=lambda x: x[0])\n for k, v in sorted_resp_headers:\n headers_txt += f\"{k}: {v}\\n\"\n \n with open(txt_path, 'w', encoding='utf-8') as f:\n f.write(headers_txt)\n \n # Stop the script\n break\n \n elif resp.status_code != 200:\n # Unexpected status, log and stop\n print(f\"Unexpected status {resp.status_code} for {current_url}. Stopping.\")\n break\n \n # Now enter the page loop, starting from the fetched page\n while True:\n # Parse the current page\n soup = BeautifulSoup(resp.text, 'html.parser')\n \n # Find all file links in views-field-title\n file_links = []\n for field in soup.find_all('div', class_='views-field views-field-title'):\n a = field.find('a')\n if a and 'href' in a.attrs:\n link = a['href']\n full_link = 'https://www.justice.gov' + link if link.startswith('/') else link\n file_links.append(full_link)\n \n # Track how many files were actually processed on this page\n files_processed_on_page = 0\n \n # Process each file link\n for link in file_links:\n # Extract basename first to check if already processed\n path = urlparse(link).path\n basename = unquote(path.split('/')[-1])\n \n # Check if file was already processed\n processed, skip = check_file_processed(basename, dataset_num, reprocess_enabled)\n \n if skip:\n print(f\"Skipping {basename} (already processed within 24h or reprocess disabled)\")\n continue\n \n # Use HEAD to get headers without downloading body\n file_resp = requests.head(link, headers=headers, allow_redirects=False)\n \n if 300 <= file_resp.status_code < 400:\n # Redirect detected: pause and log\n print(f\"Redirect detected for {link} (status: {file_resp.status_code})\")\n with open('redirects.log', 'a', encoding='utf-8') as f:\n f.write(f\"URL: {link}\\n\")\n f.write(f\"Status: {file_resp.status_code}\\n\")\n f.write(f\"Location: {file_resp.headers.get('Location', 'N/A')}\\n\")\n f.write(f\"Request Headers: {file_resp.request.headers}\\n\\n\")\n input(\"Press Enter to continue...\")\n continue # Skip saving headers for redirects\n \n if file_resp.status_code != 200:\n # Log to deleted.txt with duplicate checking\n error_line = f\"Failed to fetch headers for {link}: {file_resp.status_code}\"\n print(error_line)\n append_to_deleted(error_line)\n continue\n \n # Extract metadata\n last_mod = file_resp.headers.get('Last-Modified')\n etag = file_resp.headers.get('Etag', 'N/A').strip('\"')\n \n # If file was processed before, check if data changed\n if processed:\n if not has_data_changed(basename, last_mod, etag):\n print(f\"Skipping {basename} (no changes in Etag or Last-Modified)\")\n continue\n else:\n print(f\"Reprocessing {basename} (data changed)\")\n \n # Create directory\n dir_path = f\"EFTA/DataSet_{dataset_num}\"\n os.makedirs(dir_path, exist_ok=True)\n \n # Path for txt file\n txt_path = os.path.join(dir_path, f\"{basename}.txt\")\n \n # Collect and sort wanted headers (only if present)\n present_headers = {k: file_resp.headers[k] for k in wanted_headers if k in file_resp.headers}\n sorted_headers = sorted(present_headers.items(), key=lambda x: x[0])\n \n # Write to txt\n with open(txt_path, 'w', encoding='utf-8') as f:\n f.write(f\"Status-Code: {file_resp.status_code}\\n\")\n for k, v in sorted_headers:\n f.write(f\"{k}: {v}\\n\")\n \n # Set file modified time based on Last-Modified (GMT to timestamp)\n if last_mod:\n dt = parsedate_to_datetime(last_mod)\n timestamp = dt.timestamp()\n os.utime(txt_path, (timestamp, timestamp)) # Sets mtime to GMT equivalent; system will display in EST\n \n # Update HASHES.txt (will update if exists, else append)\n update_hashes_file(basename, last_mod, f'\"{etag}\"')\n \n # Increment counters\n file_counter += 1\n files_processed_on_page += 1\n \n # Save page link every 50 files\n if file_counter % 50 == 0:\n save_page_link(dataset_num, page)\n print(f\"Progress saved: {file_counter} files processed (Dataset {dataset_num}, Page {page})\")\n \n # Check if we processed any files on this page\n if files_processed_on_page == 0:\n print(f\"No new files to process on page {page}, moving to next page.\")\n \n # Check for next page\n next_link = soup.find('a', class_='usa-pagination__next-page')\n if not next_link:\n break\n \n # Fetch next page\n page += 1\n next_url = f\"{base_url}?page={page}\"\n resp = requests.get(next_url, headers=headers, allow_redirects=False)\n if resp.status_code != 200:\n print(f\"Failed to fetch page {page} for dataset {dataset_num}: {resp.status_code}\")\n break\n \n # If we completed the dataset (or broke due to page fail), move to next\n dataset_num += 1\n # Reset page to 0 for next dataset\n start_page = 0\n page = 0\n\nprint(\"Script completed.\")\n"}}, "check_and_fix_hashes.py": {"4d7a6fdc66cdf86acc74a083325afb73f2a1ba63": {"t": 1785604118.1204748, "n": 3249, "h": "dc6f3d69c3df7d44", "c": "#!/usr/bin/env python3\n\"\"\"\nScript to check HASHES.txt for duplicate lines and out-of-order entries,\nthen create a sorted and deduplicated version as HASHES2.txt\n\nStrictly extracts ONLY the 8-digit number after EFTA (anywhere in the line)\nand ignores everything else (path, extension, colon, headers, etc.).\nSorting is purely numerical on that number, least to greatest.\nNon-matching lines (no EFTA########) go to the end, in original order.\n\"\"\"\n\nimport re\nfrom collections import Counter\n\ndef extract_number(line):\n \"\"\"Extract ONLY the numeric portion after EFTA######## — ignore path/extension/everything else\"\"\"\n match = re.search(r'EFTA(\\d{8})', line)\n if match:\n return int(match.group(1))\n return None\n\ndef main():\n input_file = 'HASHES.txt'\n output_file = 'HASHES2.txt'\n \n print(\"Reading HASHES.txt...\")\n \n with open(input_file, 'r', encoding='utf-8') as f:\n lines = [line.rstrip('\\n\\r') for line in f]\n \n print(f\"Total lines read: {len(lines)}\")\n \n # Duplicate check\n print(\"\\n=== CHECKING FOR DUPLICATE LINES ===\")\n line_counts = Counter(lines)\n duplicates = {line: count for line, count in line_counts.items() if count > 1}\n if duplicates:\n print(f\"Found {len(duplicates)} duplicate lines (showing first 10):\")\n for line, count in sorted(duplicates.items())[:10]:\n print(f\" ({count}x) {line[:80]}...\")\n else:\n print(\"No duplicates found.\")\n \n # Order check\n print(\"\\n=== CHECKING NUMERIC ORDER ===\")\n prev_num = None\n first_out_of_order = None\n out_of_order_count = 0\n for i, line in enumerate(lines, 1):\n num = extract_number(line)\n if num is None:\n print(f\"Warning: Line {i} has no EFTA number: {line[:80]}\")\n continue\n if prev_num is not None and num < prev_num:\n out_of_order_count += 1\n if first_out_of_order is None:\n first_out_of_order = i\n print(f\"First out-of-order at line {i}:\")\n print(f\" Prev: EFTA{prev_num:08d}\")\n print(f\" Curr: EFTA{num:08d}\")\n prev_num = num\n print(f\"Out-of-order entries: {out_of_order_count}\")\n \n # Deduplicate + sort by number only\n print(\"\\n=== CREATING SORTED HASHES2.txt ===\")\n seen = set()\n unique_lines = [line for line in lines if not (line in seen or seen.add(line))]\n \n def sort_key(line):\n num = extract_number(line)\n return num if num is not None else float('inf') # non-EFTA lines go to end\n \n sorted_lines = sorted(unique_lines, key=sort_key)\n \n with open(output_file, 'w', encoding='utf-8') as f:\n for line in sorted_lines:\n f.write(line + '\\n')\n \n print(f\"Created {output_file} → {len(sorted_lines)} entries (removed {len(lines)-len(unique_lines)} dups)\")\n \n print(\"\\n=== FIRST 10 LINES OF HASHES2.txt ===\")\n for i, line in enumerate(sorted_lines[:10], 1):\n print(f\"{i:3d}: {line[:80]}\")\n \n print(\"\\n=== SUMMARY ===\")\n print(f\"Original: {len(lines)} lines\")\n print(f\"Unique: {len(unique_lines)}\")\n print(f\"Out-of-order: {out_of_order_count}\")\n print(f\"Sorted file: {output_file}\")\n\nif __name__ == '__main__':\n main()"}}, "multimedia-search-a.json": {"7057688cc295701ec558ed598e04c6ee6d87a674": {"t": 1785604120.01066, "n": 23968, "h": "f95fa2aed134945e", "c": "{\"hits\":{\"total\":{\"value\":598217,\"relation\":\"gte\"},\"max_score\":1.8429456,\"hits\":[{\"_source\":{\"documentId\":\"9915a2e2\",\"chunkIndex\":0,\"totalChunks\":1,\"charStart\":0,\"charEnd\":1864,\"chunkSize\":1864,\"isChunked\":false,\"startPage\":1,\"endPage\":1,\"ORIGIN_FILE_NAME\":\"EFTA01372849.pdf\",\"ORIGIN_FILE_URI\":\"https:\\/\\/www.justice.gov\\/epstein\\/files\\/DataSet 10\\/EFTA01372849.pdf\",\"bucket\":\"amazon-s3x-sync\",\"key\":\"DataSet 10\\/EFTA01372849.pdf\",\"contentType\":\"application\\/pdf\",\"fileSize\":103607,\"totalWords\":322,\"totalCharacters\":1864,\"processedAt\":\"2026-01-30T12:46:04Z\",\"indexedAt\":\"2026-01-30T12:46:04Z\",\"source\":\"document-indexing-pipeline\"},\"fields\":{\"ORIGIN_FILE_NAME\":[\"EFTA01372849.pdf\"]},\"highlight\":{\"content\":[\"\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nNo exceptions noted\\n5\\nMediaNews Group, Inc\\nD1506955\\n10\\/20\\/2015\\nLow\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nNo exceptions\",\"\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nNo exceptions noted\\n9\\nFederative Republic of Brazil\\nM1503287 70470\\n12\\/3\\/2015\\nHigh\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\",\"\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nNo exceptions noted.\\n10\\nFrontline Ltd\\nD1511018\\n12\\/8\\/2015\\nHigh\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nNo exceptions\"]}},{\"_source\":{\"documentId\":\"03ba6f4a\",\"chunkIndex\":0,\"totalChunks\":1,\"charStart\":0,\"charEnd\":3298,\"chunkSize\":3298,\"isChunked\":false,\"startPage\":1,\"endPage\":9,\"ORIGIN_FILE_NAME\":\"EFTA00110660.pdf\",\"ORIGIN_FILE_URI\":\"https:\\/\\/www.justice.gov\\/epstein\\/files\\/DataSet 9\\/EFTA00110660.pdf\",\"bucket\":\"amazon-s3x-sync\",\"key\":\"DataSet 9\\/EFTA00110660.pdf\",\"contentType\":\"application\\/pdf\",\"fileSize\":1505647,\"totalWords\":616,\"totalCharacters\":3298,\"processedAt\":\"2026-01-30T16:22:49Z\",\"indexedAt\":\"2026-01-30T16:22:50Z\",\"source\":\"document-indexing-pipeline\"},\"fields\":{\"ORIGIN_FILE_NAME\":[\"EFTA00110660.pdf\"]},\"highlight\":{\"content\":[\"Date\\nContraband\\n5\\/28\\/19\\nNA\\n5\\/28\\/19\\nn\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n5\\/28\\/19\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n5\\/29\\/19\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n5\\/29\\/19\\nn\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n5\\/31\\/19\\nn\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6\\/03\\/19\\nn\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6\\/03\\/19\\nn\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6\\/03\\/19\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6\\/03\\/19\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6\\/03\\/19\\nn\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6\\/63\",\"\\/19\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\n6\\/03\\/19\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6\\/04\\/19\\nn\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6\\/09\\/19\\nn\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6\\/07\\/19\\nn\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6\\/07\\/19\\nn\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6\\/04\\/19\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6 10-9019\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6-10-20\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6\\/10\\/19\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6\\/10\\/19\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6\\/10\\/19\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6\\/10\\/19\\nN\",\"\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n,S\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n)\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nw\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nEFTA001106\\n\\nDabe\\nName C\\nReg #\"]}},{\"_source\":{\"documentId\":\"1d556cec\",\"chunkIndex\":0,\"totalChunks\":1,\"charStart\":0,\"charEnd\":10048,\"chunkSize\":10048,\"isChunked\":false,\"startPage\":1,\"endPage\":9,\"ORIGIN_FILE_NAME\":\"EFTA00694739.pdf\",\"ORIGIN_FILE_URI\":\"https:\\/\\/www.justice.gov\\/epstein\\/files\\/DataSet 9\\/EFTA00694739.pdf\",\"bucket\":\"amazon-s3x-sync\",\"key\":\"DataSet 9\\/EFTA00694739.pdf\",\"contentType\":\"application\\/pdf\",\"fileSize\":681317,\"totalWords\":2150,\"totalCharacters\":10048,\"processedAt\":\"2026-01-30T17:47:48Z\",\"indexedAt\":\"2026-01-30T17:47:48Z\",\"source\":\"document-indexing-pipeline\"},\"fields\":{\"ORIGIN_FILE_NAME\":[\"EFTA00694739.pdf\"]},\"highlight\":{\"content\":[\"\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nX\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nOA\\nG\\nmo\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nL\\nKd\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n7\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n7\\n7\\nfo\\u0027\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\ndo\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nUA\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nEA\\nZ\\u2088\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nYd\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nXd\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nWd\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n7\\nV\\u03b4\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nUd\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nTo\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nRo\\u0027\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nPo\\u0027\\nOd\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nNo\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nMd\\u0027\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n1\\nLo\\u0022\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nKd\",\"11\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nO19X\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nO19X\\n(8\\n1\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nOI\\nyo\\u0027\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n3A@\\nXo\\nW\\nWo\\n7\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nZ\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nZ\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nL\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nV\\nLA\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nL\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nL\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\no\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nto\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\ndo\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nP\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nDA\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\n0*\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n?\\n10\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n8A\\n4?\",\"d\\u0027\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n7\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n9d\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n78\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nhA\\n7\\n58\\n30\\u0022\\nOA\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nP\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nP\\n,8\\u0022\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nP\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nP\\n7\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n4\\n%3\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\ng\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n11\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n1\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nO{T:2A;-\\n7\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nt4@\\n98\\u0022\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n4@\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nZ\\nLA\\n10\\u0022\\n1\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\"]}},{\"_source\":{\"documentId\":\"ebb63214\",\"chunkIndex\":2,\"totalChunks\":5,\"charStart\":13419,\"charEnd\":19845,\"chunkSize\":6426,\"isChunked\":true,\"startPage\":7,\"endPage\":12,\"ORIGIN_FILE_NAME\":\"EFTA00288287.pdf\",\"ORIGIN_FILE_URI\":\"https:\\/\\/www.justice.gov\\/epstein\\/files\\/DataSet 9\\/EFTA00288287.pdf\",\"bucket\":\"amazon-s3x-sync\",\"key\":\"DataSet 9\\/EFTA00288287.pdf\",\"contentType\":\"application\\/pdf\",\"fileSize\":781081,\"totalWords\":5148,\"totalCharacters\":28625,\"processedAt\":\"2026-01-30T16:49:25Z\",\"indexedAt\":\"2026-01-30T16:49:26Z\",\"source\":\"document-indexing-pipeline\"},\"fields\":{\"ORIGIN_FILE_NAME\":[\"EFTA00288287.pdf\"]},\"highlight\":{\"content\":[\"DAI GR Equity\\n6,695\\n13,908\\n#N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n38.51\\n1.25%\\nDBK GR Equity\\n-\\n677\\n#N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n0.00\\n1.24%\\nDD US Equity\\n2,864\\n12,908\\n#N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n35.71\\n0.62%\\nDDAIF US Equity\",\"3,978\\n8,377\\n#N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n31.90\\n1.49%\\nDE US Equity\\n750\\n8,537\\n#N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n12.37\\n0.71%\\nDELL US Equity\\n#N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nDG FP Equity\\n4,505\\n10,090\\n#N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n67.84\\n0.66%\\nDGE\",\"#N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n0.00\\n0.86%\\nDNB NO Equity\\n70\\n1,168\\n#N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6.71\\n0.89%\\nDOW US Equity\\n2,306\\n7,396\\n#N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n33.34\\n0.94%\\nDPW GR Equity\\n161\\n660\\n#N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n16.87\\n1.45%\"]}},{\"_source\":{\"documentId\":\"061fb160\",\"chunkIndex\":1,\"totalChunks\":11,\"charStart\":7000,\"charEnd\":14866,\"chunkSize\":7866,\"isChunked\":true,\"startPage\":3,\"endPage\":9,\"ORIGIN_FILE_NAME\":\"EFTA01084848.pdf\",\"ORIGIN_FILE_URI\":\"https:\\/\\/www.justice.gov\\/epstein\\/files\\/DataSet 9\\/EFTA01084848.pdf\",\"bucket\":\"amazon-s3x-sync\",\"key\":\"DataSet 9\\/EFTA01084848.pdf\",\"contentType\":\"application\\/pdf\",\"fileSize\":5710835,\"totalWords\":11289,\"totalCharacters\":71598,\"processedAt\":\"2026-01-30T18:48:08Z\",\"indexedAt\":\"2026-01-30T18:48:09Z\",\"source\":\"document-indexing-pipeline\"},\"fields\":{\"ORIGIN_FILE_NAME\":[\"EFTA01084848.pdf\"]},\"highlight\":{\"content\":[\"1\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nSN\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E-1248\\n1660:00\\nHours\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nDesc\\nBLADE, MAIN ROTOR\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nATA\\n62-10-00 MAIN BLADES\\n0\\nCycles\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nPosition\\nORANGE\\n0\\nLandings\\nn\",\"n\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nPosition #1\\nr\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nLandings\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nCondition NEW\\nMCN\\n6220-1060\\nMain Rotor Blade Pin.\",\"62-20-00 MAIN HEADS\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nCycles\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nPosition #1\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nLandings\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nn\\/\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nCondition NEW\\nMCN\\n6220-1100\\nMain Rotor Adapter.\"]}},{\"_source\":{\"documentId\":\"01e2cd19\",\"chunkIndex\":26,\"totalChunks\":30,\"charStart\":179751,\"charEnd\":186938,\"chunkSize\":7187,\"isChunked\":true,\"startPage\":77,\"endPage\":81,\"ORIGIN_FILE_NAME\":\"EFTA00802185.pdf\",\"ORIGIN_FILE_URI\":\"https:\\/\\/www.justice.gov\\/epstein\\/files\\/DataSet 9\\/EFTA00802185.pdf\",\"bucket\":\"amazon-s3x-sync\",\"key\":\"DataSet 9\\/EFTA00802185.pdf\",\"contentType\":\"application\\/pdf\",\"fileSize\":7494150,\"totalWords\":33268,\"totalCharacters\":206093,\"processedAt\":\"2026-01-30T18:05:32Z\",\"indexedAt\":\"2026-01-30T18:05:37Z\",\"source\":\"document-indexing-pipeline\"},\"fields\":{\"ORIGIN_FILE_NAME\":[\"EFTA00802185.pdf\"]},\"highlight\":{\"content\":[\"N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nAlteration\\n12\\/18\\/1996\\nIAW KC Aviation Dwg # GIV-25-05-200\\nModified Cabin Headliner per KC Aviation\\nDwg # GIV-25-50-213,\",\"N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nAlteration\\n03\\/25\\/1995\\nReroute\\n62\\nYes\\nN88GA\\nPerformed ASC 230, Stabilizers, Vertical\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\",\"the NLG Assembly, performed\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nRepair\\n08\\/12\\/1993\\nremoval of Bearing GB14G-10.\"]}},{\"_source\":{\"documentId\":\"89c9b81e\",\"chunkIndex\":3,\"totalChunks\":6,\"charStart\":21000,\"charEnd\":28079,\"chunkSize\":7079,\"isChunked\":true,\"startPage\":10,\"endPage\":14,\"ORIGIN_FILE_NAME\":\"EFTA01193391.pdf\",\"ORIGIN_FILE_URI\":\"https:\\/\\/www.justice.gov\\/epstein\\/files\\/DataSet 9\\/EFTA01193391.pdf\",\"bucket\":\"amazon-s3x-sync\",\"key\":\"DataSet 9\\/EFTA01193391.pdf\",\"contentType\":\"application\\/pdf\",\"fileSize\":668433,\"totalWords\":5847,\"totalCharacters\":39431,\"processedAt\":\"2026-01-30T19:01:11Z\",\"indexedAt\":\"2026-01-30T19:01:12Z\",\"source\":\"document-indexing-pipeline\"},\"fields\":{\"ORIGIN_FILE_NAME\":[\"EFTA01193391.pdf\"]},\"highlight\":{\"content\":[\"Leon Black\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n250,000.00\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n107 Portfolio LP\\nLimited Partner\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nVarious\\nVarious\\nLeon Black\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n0.00\\n46.82%\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nHamlet Holdings LLC\\nMember\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nVarious\",\"Limited Partner\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nVarious\\nVarious\\nLeon Black\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n8,274.00\\n1.64%\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nAIF IILP\\nLimited Partner\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nVarious\\nVarious\\nLeon Black\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n0.00\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nApollo Real\",\"8.67%\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nAIF II LP\\nLimited Partner\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nVarious\\nVarious\\nLDB 2011 LLC\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n0.00\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nPAM Centre L.P.\"]}},{\"_source\":{\"documentId\":\"f6b48e6f\",\"chunkIndex\":0,\"totalChunks\":1,\"charStart\":0,\"charEnd\":5801,\"chunkSize\":5801,\"isChunked\":false,\"startPage\":1,\"endPage\":172,\"ORIGIN_FILE_NAME\":\"EFTA01343500.pdf\",\"ORIGIN_FILE_URI\":\"https:\\/\\/www.justice.gov\\/epstein\\/files\\/DataSet 10\\/EFTA01343500.pdf\",\"bucket\":\"amazon-s3x-sync\",\"key\":\"DataSet 10\\/EFTA01343500.pdf\",\"contentType\":\"application\\/pdf\",\"fileSize\":2098296,\"totalWords\":689,\"totalCharacters\":5801,\"processedAt\":\"2026-01-30T12:38:15Z\",\"indexedAt\":\"2026-01-30T12:38:15Z\",\"source\":\"document-indexing-pipeline\"},\"fields\":{\"ORIGIN_FILE_NAME\":[\"EFTA01343500.pdf\"]},\"highlight\":{\"content\":[\"\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\n\\nEFTA01343699\\n00BBB\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\n\\nEFTA01343700\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\n\\nEFTA01343701\\n0\\n\\n^@^@^@^@^@^@^@^@^@^@^@^@^@^@1\\nEFTA01343702\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\n\\n^@^@^@^@^@^@^@^@^@^@^@^@^@^@1\\nEFTA01343703\\n@\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\",\"EFTA01343759\\n(9)\\n@\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\n\\nEFTA01343760\\n@\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\n\\nEFTA01343761\\n0\\n0\\n@)\\n\\nhe^@^@^@^@^@^@\\nEFTA01343762\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\n\\nEFTA01343763\\n^@^@^@^@\\n@\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\n@\\n\\nEFTA01343764\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\n\\nEFTA01343765\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\",\"(9)\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\n@\\n\\nEFTA01343793\\nhe^@^@^@^@^@^@^\\n\\n@\\nEFTA01343794\\n@\\n\\nEFTA01343795\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\n\\nEFTA01343796\\n\\u003Cem\\u003Ea\\u003C\\/em\\u003E\\nine^@^@^@^@^@^\\n\\nEFTA01343797\\n@\\n@\\n(\\u003Cem\\u003Ea\\u003C\\/em\\u003E)\\n(\\u003Cem\\u003Ea\\u003C\\/em\\u003E)\\n@\\n\\nEFTA01343798\\n(\\u003Cem\\u003Ea\\u003C\\/em\\u003E)\"]}},{\"_source\":{\"documentId\":\"861c634d\",\"chunkIndex\":0,\"totalChunks\":1,\"charStart\":0,\"charEnd\":1011,\"chunkSize\":1011,\"isChunked\":false,\"startPage\":1,\"endPage\":55,\"ORIGIN_FILE_NAME\":\"EFTA00251213.pdf\",\"ORIGIN_FILE_URI\":\"https:\\/\\/www.justice.gov\\/epstein\\/files\\/DataSet 9\\/EFTA00251213.pdf\",\"bucket\":\"amazon-s3x-sync\",\"key\":\"DataSet 9\\/EFTA00251213.pdf\",\"contentType\":\"application\\/pdf\",\"fileSize\":46534417,\"totalWords\":309,\"totalCharacters\":1011,\"processedAt\":\"2026-01-30T16:47:07Z\",\"indexedAt\":\"2026-01-30T16:47:08Z\",\"source\":\"document-indexing-pipeline\"},\"fields\":{\"ORIGIN_FILE_NAME\":[\"EFTA00251213.pdf\"]},\"highlight\":{\"content\":[\"Visits\\n\\nEFTA00251214\\n\\n-\\nBEE\\n\\n$\\n\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nSOUTH\\n\\u2449\\n11\\n\\nCOLL\\nS\\n\\nCOLLECTE\\nSELECTIVE\\n\\nt\\n\\n\\u00a1HO\\n\\nCANADA\\n\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\n\\/ \\u00c0 JAJA t \\u003Cem\\u003EA\\u003C\\/em\\u003E 14th\\n4A \\u003Cem\\u003EA\\u003C\\/em\\u003E AM \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\nis X \\u0026\\n\\n11 it\\n11 \\u003Cem\\u003EA\\u003C\\/em\\u003E And\",\"\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nINT\\nM \\u003Cem\\u003EA\\u003C\\/em\\u003E AND \\u003Cem\\u003EA\\u003C\\/em\\u003E ASA \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E\\nVIVI\\nv.t +\\nEFTA00251229\\n\\nvari\\n\\nALL\\nIf\\nAND\\nEFTA00251231\\n\\nA.A MA \\u003Cem\\u003EA\\u003C\\/em\\u003E 1 \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\n\\/ I 11\\nG\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E AM \\u003Cem\\u003EA\\u003C\\/em\\u003E M \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E 1 \\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\n.....\",\"OF\\nX\\nthe\\nM\\n\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nAA AM \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\n%\\n\\nG \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E 1 \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E 15\\n\\n*** \\u0022 74 lete\\nX\\n\\n1ADAD ADADA \\u003Cem\\u003EA\\u003C\\/em\\u003E D\\nMA 1 1\\nEFTA00251241\\n\\n1 AFA\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n10\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E M \\u003Cem\\u003EA\\u003C\\/em\\u003E 1 : \\u003Cem\\u003EA\\u003C\\/em\\u003E \\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n\\u003Cem\\u003EA\\u003C\\/em\\u003E 4\\n\\nALL M\"]}},{\"_source\":{\"documentId\":\"b4ec8f68\",\"chunkIndex\":3,\"totalChunks\":6,\"charStart\":20851,\"charEnd\":28049,\"chunkSize\":7198,\"isChunked\":true,\"startPage\":9,\"endPage\":13,\"ORIGIN_FILE_NAME\":\"EFTA02710783.pdf\",\"ORIGIN_FILE_URI\":\"https:\\/\\/www.justice.gov\\/epstein\\/files\\/DataSet 11\\/EFTA02710783.pdf\",\"bucket\":\"amazon-s3x-sync\",\"key\":\"DataSet 11\\/EFTA02710783.pdf\",\"contentType\":\"application\\/pdf\",\"fileSize\":1320596,\"totalWords\":6143,\"totalCharacters\":41391,\"processedAt\":\"2026-01-30T11:55:33Z\",\"indexedAt\":\"2026-01-30T11:55:33Z\",\"source\":\"document-indexing-pipeline\"},\"fields\":{\"ORIGIN_FILE_NAME\":[\"EFTA02710783.pdf\"]},\"highlight\":{\"content\":[\"laration\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n0.00\\n13.00%\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nJerusalem Venture Partners LP\\nLimited Partner\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nVarious\\nVarious\\nAPO2 Declaration\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n3,127.00\\n0.58%\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nArtspace LLC\\nMember\",\"N\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nVarious\\nVarious\\nAPO2 Declaration\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n6,001,180.53\\n100.00%\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nBlue Sunshine, LLC\\nMember\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nVarious\\nVarious\\nAPO2 Declaration\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n0.00\\n12.50%\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nApollo\",\"8.67%\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nAIF LP\\nLimited Partner\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nVarious\\nVarious\\nLDB 2011 LLC\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\n0.00\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nN\\/\\u003Cem\\u003EA\\u003C\\/em\\u003E\\nPAM Centre L.P.\"]}}]},\"aggregations\":{\"unique_count\":{\"value\":598217}}}"}}, "multimedia-search-no-images-produced.json": {"127e48fd0833e9abb7c85793f222f70c65f3fccc": {"t": 1785604121.2134101, "n": 11363, "h": "f3df5b8cfb24638c", "c": "{\n \"hits\": {\n \"total\": {\n \"value\": 3789,\n \"relation\": \"eq\"\n },\n \"max_score\": 19.6206,\n \"hits\": [\n {\n \"_source\": {\n \"documentId\": \"d45058cf\",\n \"chunkIndex\": 0,\n \"totalChunks\": 1,\n \"charStart\": 0,\n \"charEnd\": 31,\n \"chunkSize\": 31,\n \"isChunked\": false,\n \"startPage\": 1,\n \"endPage\": 1,\n \"ORIGIN_FILE_NAME\": \"EFTA00024813.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 8/EFTA00024813.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 8/EFTA00024813.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 2433,\n \"totalWords\": 4,\n \"totalCharacters\": 31,\n \"processedAt\": \"2026-01-21T01:37:27Z\",\n \"indexedAt\": \"2026-01-21T01:37:27Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00024813.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"\\u003Cem\\u003ENo\\u003C/em\\u003E \\u003Cem\\u003EImages\\u003C/em\\u003E \\u003Cem\\u003EProduced\\u003C/em\\u003E\\nEFTA00024813\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"5a351329\",\n \"chunkIndex\": 0,\n \"totalChunks\": 1,\n \"charStart\": 0,\n \"charEnd\": 31,\n \"chunkSize\": 31,\n \"isChunked\": false,\n \"startPage\": 1,\n \"endPage\": 1,\n \"ORIGIN_FILE_NAME\": \"EFTA00029996.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 8/EFTA00029996.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 8/EFTA00029996.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 2433,\n \"totalWords\": 4,\n \"totalCharacters\": 31,\n \"processedAt\": \"2026-01-21T01:38:21Z\",\n \"indexedAt\": \"2026-01-21T01:38:21Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00029996.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"\\u003Cem\\u003ENo\\u003C/em\\u003E \\u003Cem\\u003EImages\\u003C/em\\u003E \\u003Cem\\u003EProduced\\u003C/em\\u003E\\nEFTA00029996\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"ad3e8c2e\",\n \"chunkIndex\": 0,\n \"totalChunks\": 1,\n \"charStart\": 0,\n \"charEnd\": 31,\n \"chunkSize\": 31,\n \"isChunked\": false,\n \"startPage\": 1,\n \"endPage\": 1,\n \"ORIGIN_FILE_NAME\": \"EFTA00033012.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 8/EFTA00033012.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 8/EFTA00033012.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 2433,\n \"totalWords\": 4,\n \"totalCharacters\": 31,\n \"processedAt\": \"2026-01-21T01:38:47Z\",\n \"indexedAt\": \"2026-01-21T01:38:47Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00033012.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"\\u003Cem\\u003ENo\\u003C/em\\u003E \\u003Cem\\u003EImages\\u003C/em\\u003E \\u003Cem\\u003EProduced\\u003C/em\\u003E\\nEFTA00033012\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"e9730164\",\n \"chunkIndex\": 0,\n \"totalChunks\": 1,\n \"charStart\": 0,\n \"charEnd\": 31,\n \"chunkSize\": 31,\n \"isChunked\": false,\n \"startPage\": 1,\n \"endPage\": 1,\n \"ORIGIN_FILE_NAME\": \"EFTA00033048.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 8/EFTA00033048.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 8/EFTA00033048.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 2433,\n \"totalWords\": 4,\n \"totalCharacters\": 31,\n \"processedAt\": \"2026-01-21T01:38:49Z\",\n \"indexedAt\": \"2026-01-21T01:38:49Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00033048.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"\\u003Cem\\u003ENo\\u003C/em\\u003E \\u003Cem\\u003EImages\\u003C/em\\u003E \\u003Cem\\u003EProduced\\u003C/em\\u003E\\nEFTA00033048\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"4942d5ae\",\n \"chunkIndex\": 0,\n \"totalChunks\": 1,\n \"charStart\": 0,\n \"charEnd\": 31,\n \"chunkSize\": 31,\n \"isChunked\": false,\n \"startPage\": 1,\n \"endPage\": 1,\n \"ORIGIN_FILE_NAME\": \"EFTA00033113.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 8/EFTA00033113.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 8/EFTA00033113.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 2433,\n \"totalWords\": 4,\n \"totalCharacters\": 31,\n \"processedAt\": \"2026-01-21T01:38:51Z\",\n \"indexedAt\": \"2026-01-21T01:38:51Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00033113.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"\\u003Cem\\u003ENo\\u003C/em\\u003E \\u003Cem\\u003EImages\\u003C/em\\u003E \\u003Cem\\u003EProduced\\u003C/em\\u003E\\nEFTA00033113\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"6e5a157e\",\n \"chunkIndex\": 0,\n \"totalChunks\": 1,\n \"charStart\": 0,\n \"charEnd\": 31,\n \"chunkSize\": 31,\n \"isChunked\": false,\n \"startPage\": 1,\n \"endPage\": 1,\n \"ORIGIN_FILE_NAME\": \"EFTA00033116.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 8/EFTA00033116.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 8/EFTA00033116.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 2433,\n \"totalWords\": 4,\n \"totalCharacters\": 31,\n \"processedAt\": \"2026-01-21T01:38:52Z\",\n \"indexedAt\": \"2026-01-21T01:38:52Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00033116.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"\\u003Cem\\u003ENo\\u003C/em\\u003E \\u003Cem\\u003EImages\\u003C/em\\u003E \\u003Cem\\u003EProduced\\u003C/em\\u003E\\nEFTA00033116\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"8bd43a32\",\n \"chunkIndex\": 0,\n \"totalChunks\": 1,\n \"charStart\": 0,\n \"charEnd\": 31,\n \"chunkSize\": 31,\n \"isChunked\": false,\n \"startPage\": 1,\n \"endPage\": 1,\n \"ORIGIN_FILE_NAME\": \"EFTA00033046.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 8/EFTA00033046.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 8/EFTA00033046.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 2433,\n \"totalWords\": 4,\n \"totalCharacters\": 31,\n \"processedAt\": \"2026-01-21T01:38:52Z\",\n \"indexedAt\": \"2026-01-21T01:38:52Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00033046.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"\\u003Cem\\u003ENo\\u003C/em\\u003E \\u003Cem\\u003EImages\\u003C/em\\u003E \\u003Cem\\u003EProduced\\u003C/em\\u003E\\nEFTA00033046\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"a6585fbb\",\n \"chunkIndex\": 0,\n \"totalChunks\": 1,\n \"charStart\": 0,\n \"charEnd\": 31,\n \"chunkSize\": 31,\n \"isChunked\": false,\n \"startPage\": 1,\n \"endPage\": 1,\n \"ORIGIN_FILE_NAME\": \"EFTA00033114.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 8/EFTA00033114.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 8/EFTA00033114.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 2433,\n \"totalWords\": 4,\n \"totalCharacters\": 31,\n \"processedAt\": \"2026-01-21T01:38:52Z\",\n \"indexedAt\": \"2026-01-21T01:38:52Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00033114.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"\\u003Cem\\u003ENo\\u003C/em\\u003E \\u003Cem\\u003EImages\\u003C/em\\u003E \\u003Cem\\u003EProduced\\u003C/em\\u003E\\nEFTA00033114\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"a7a51452\",\n \"chunkIndex\": 0,\n \"totalChunks\": 1,\n \"charStart\": 0,\n \"charEnd\": 31,\n \"chunkSize\": 31,\n \"isChunked\": false,\n \"startPage\": 1,\n \"endPage\": 1,\n \"ORIGIN_FILE_NAME\": \"EFTA00033130.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 8/EFTA00033130.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 8/EFTA00033130.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 2433,\n \"totalWords\": 4,\n \"totalCharacters\": 31,\n \"processedAt\": \"2026-01-21T01:38:53Z\",\n \"indexedAt\": \"2026-01-21T01:38:53Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00033130.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"\\u003Cem\\u003ENo\\u003C/em\\u003E \\u003Cem\\u003EImages\\u003C/em\\u003E \\u003Cem\\u003EProduced\\u003C/em\\u003E\\nEFTA00033130\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"c09f8a09\",\n \"chunkIndex\": 0,\n \"totalChunks\": 1,\n \"charStart\": 0,\n \"charEnd\": 31,\n \"chunkSize\": 31,\n \"isChunked\": false,\n \"startPage\": 1,\n \"endPage\": 1,\n \"ORIGIN_FILE_NAME\": \"EFTA00033115.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 8/EFTA00033115.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 8/EFTA00033115.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 2433,\n \"totalWords\": 4,\n \"totalCharacters\": 31,\n \"processedAt\": \"2026-01-21T01:38:53Z\",\n \"indexedAt\": \"2026-01-21T01:38:53Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00033115.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"\\u003Cem\\u003ENo\\u003C/em\\u003E \\u003Cem\\u003EImages\\u003C/em\\u003E \\u003Cem\\u003EProduced\\u003C/em\\u003E\\nEFTA00033115\"\n ]\n }\n }\n ]\n },\n \"aggregations\": {\n \"unique_count\": {\n \"value\": 3789\n }\n }\n}"}}, "multimedia-search-trump.json": {"5425da11ff1bb1e3593171a0115a6e278da38d4d": {"t": 1785604122.451554, "n": 15731, "h": "27bbde44abcde027", "c": "{\n \"hits\": {\n \"total\": {\n \"value\": 4727,\n \"relation\": \"eq\"\n },\n \"max_score\": 12.904046,\n \"hits\": [\n {\n \"_source\": {\n \"documentId\": \"30d92271\",\n \"chunkIndex\": 0,\n \"totalChunks\": 1,\n \"charStart\": 0,\n \"charEnd\": 1916,\n \"chunkSize\": 1916,\n \"isChunked\": false,\n \"startPage\": 1,\n \"endPage\": 1,\n \"ORIGIN_FILE_NAME\": \"EFTA00818213.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 9/EFTA00818213.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 9/EFTA00818213.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 76296,\n \"totalWords\": 300,\n \"totalCharacters\": 1916,\n \"processedAt\": \"2026-01-30T18:06:12Z\",\n \"indexedAt\": \"2026-01-30T18:06:12Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00818213.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"Clinton\\nClinton 42, \\u003Cem\\u003ETrump\\u003C/em\\u003E 47\\nTracking\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E +5\\nGeneral Election: \\u003Cem\\u003ETrump\\u003C/em\\u003E vs. Clinton vs.\\nClinton 39, \\u003Cem\\u003ETrump\\u003C/em\\u003E 39,\\nJohnson VS.\",\n \"Stein\\nBloomberg\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E 44, Clinton 39,\\nJohnson 10, Stein 3\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E +5\\nOhio: \\u003Cem\\u003ETrump\\u003C/em\\u003E vs. Clinton\\nBloomberg\\nClinton 43, \\u003Cem\\u003ETrump\\u003C/em\\u003E 48\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E +5\\nMaine: \\u003Cem\\u003ETrump\\u003C/em\\u003E vs.\",\n \"Johnson\\nKSN News/SurveyUSA\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E 48, Clinton 36,\\nvs. Stein\\nJohnson 8, Stein 2\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E +12\\nSouth Carolina: \\u003Cem\\u003ETrump\\u003C/em\\u003E vs. Clinton vs.\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"88e3b63c\",\n \"chunkIndex\": 0,\n \"totalChunks\": 1,\n \"charStart\": 0,\n \"charEnd\": 572,\n \"chunkSize\": 572,\n \"isChunked\": false,\n \"startPage\": 1,\n \"endPage\": 1,\n \"ORIGIN_FILE_NAME\": \"EFTA00716209.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 9/EFTA00716209.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 9/EFTA00716209.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 23437,\n \"totalWords\": 92,\n \"totalCharacters\": 572,\n \"processedAt\": \"2026-01-30T17:50:54Z\",\n \"indexedAt\": \"2026-01-30T17:50:55Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00716209.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"Clinton\\nCNN/ORC\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E 48, Clinton 45\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E +3\\nGeneral Election: \\u003Cem\\u003ETrump\\u003C/em\\u003E vs. Clinton\\nCBS News\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E 44, Clinton 43\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E +1\\nGeneral Election: \\u003Cem\\u003ETrump\\u003C/em\\u003E vs.\",\n \"Stein\\nClinton 39, \\u003Cem\\u003ETrump\\u003C/em\\u003E 44, Johnson 9, Stein 3\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E +5\\nGeneral Election: \\u003Cem\\u003ETrump\\u003C/em\\u003E vs. Clinton vs.\",\n \"CBS News\\nJohnson\\nClinton 39, \\u003Cem\\u003ETrump\\u003C/em\\u003E 40, Johnson 12\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E +1\\nEFTA00716209\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"6a571f60\",\n \"chunkIndex\": 2,\n \"totalChunks\": 18,\n \"charStart\": 13925,\n \"charEnd\": 21886,\n \"chunkSize\": 7961,\n \"isChunked\": true,\n \"startPage\": 4,\n \"endPage\": 7,\n \"ORIGIN_FILE_NAME\": \"EFTA00263367.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 9/EFTA00263367.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 9/EFTA00263367.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 11360342,\n \"totalWords\": 19267,\n \"totalCharacters\": 126207,\n \"processedAt\": \"2026-01-30T16:45:46Z\",\n \"indexedAt\": \"2026-01-30T16:45:48Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00263367.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"5/22/22, 1:11 PM\\nDonald \\u003Cem\\u003ETrump\\u003C/em\\u003E .\",\n \". [62] It was\\nunprofitable, and \\u003Cem\\u003ETrump\\u003C/em\\u003E paid Holiday $70 million in May\\n\\u003Cem\\u003ETRUMP\\u003C/em\\u003E\\n1986 to take sole control. [63] \\u003Cem\\u003ETrump\\u003C/em\\u003E had earlier bought a hotel\\nand casino\",\n \"\\u003Cem\\u003ETrump\\u003C/em\\u003E Hotels & Casino Resorts (THCR), which assumed ownership of\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E Plaza, \\u003Cem\\u003ETrump\\u003C/em\\u003E Castle, and the \\u003Cem\\u003ETrump\\u003C/em\\u003E Casino in Gary, Indiana. [71] THCR purchased\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"f3b8ffff\",\n \"chunkIndex\": 1,\n \"totalChunks\": 2,\n \"charStart\": 7000,\n \"charEnd\": 12825,\n \"chunkSize\": 5825,\n \"isChunked\": true,\n \"startPage\": 3,\n \"endPage\": 7,\n \"ORIGIN_FILE_NAME\": \"EFTA00699322.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 9/EFTA00699322.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 9/EFTA00699322.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 470862,\n \"totalWords\": 2241,\n \"totalCharacters\": 12825,\n \"processedAt\": \"2026-01-30T17:48:13Z\",\n \"indexedAt\": \"2026-01-30T17:48:14Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00699322.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"That's why \\u003Cem\\u003ETrump\\u003C/em\\u003E.\",\n \"\\u003E\\u003E Donald \\u003Cem\\u003ETrump\\u003C/em\\u003E and Hillary Clinton are in a bar.\",\n \"\\u003Cem\\u003ETrump\\u003C/em\\u003E: \\\"No, the other one.\\\"\\nHillary: \\\"You mean the massive voter fraud?\\\"\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E: \\\"No, the other one.\\\"\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"2b2df2b4\",\n \"chunkIndex\": 1,\n \"totalChunks\": 2,\n \"charStart\": 7000,\n \"charEnd\": 13037,\n \"chunkSize\": 6037,\n \"isChunked\": true,\n \"startPage\": 4,\n \"endPage\": 8,\n \"ORIGIN_FILE_NAME\": \"EFTA00699314.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 9/EFTA00699314.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 9/EFTA00699314.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 485755,\n \"totalWords\": 2286,\n \"totalCharacters\": 13037,\n \"processedAt\": \"2026-01-30T17:48:13Z\",\n \"indexedAt\": \"2026-01-30T17:48:14Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00699314.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"\\u003E\\u003E Donald \\u003Cem\\u003ETrump\\u003C/em\\u003E and Hillary Clinton are in a bar.\",\n \"\\u003Cem\\u003ETrump\\u003C/em\\u003E: \\\"No the other one:\\\"\\n\\u003E\\u003E Hillary: \\\"The IRS targeting conservatives?\\\"\\n\\u003E\\u003E \\u003Cem\\u003ETrump\\u003C/em\\u003E: \\\"No the other one:\\\"\\nHillary: \\\"Turning Libya into chaos?\\\"\",\n \"\\u003E\\u003E \\u003Cem\\u003ETrump\\u003C/em\\u003E: \\\"No the other one:\\\"\\n\\u003E\\u003E Hillary: \\\"Turning our backs on Israel?\\\"\\n\\u003E\\u003E \\u003Cem\\u003ETrump\\u003C/em\\u003E: \\\"No the other one:\\\"\\nHillary: \\\"The joke Iran Nuke deal?\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"5f3ae20f\",\n \"chunkIndex\": 0,\n \"totalChunks\": 2,\n \"charStart\": 0,\n \"charEnd\": 6844,\n \"chunkSize\": 6844,\n \"isChunked\": true,\n \"startPage\": 1,\n \"endPage\": 6,\n \"ORIGIN_FILE_NAME\": \"EFTA01022627.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 9/EFTA01022627.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 9/EFTA01022627.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 622790,\n \"totalWords\": 2392,\n \"totalCharacters\": 12795,\n \"processedAt\": \"2026-01-30T18:40:35Z\",\n \"indexedAt\": \"2026-01-30T18:40:35Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA01022627.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"\\u003Cem\\u003ETrump\\u003C/em\\u003E: Hello, Bob.\\nBW: President \\u003Cem\\u003ETrump\\u003C/em\\u003E, how are you?\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E: How are you? How are you doing? Okay?\\nBW: Real well.\",\n \"\\u003Cem\\u003ETrump\\u003C/em\\u003E: Right.\",\n \"\\u003Cem\\u003ETrump\\u003C/em\\u003E: Good.\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"11c99673\",\n \"chunkIndex\": 1,\n \"totalChunks\": 2,\n \"charStart\": 7000,\n \"charEnd\": 13563,\n \"chunkSize\": 6563,\n \"isChunked\": true,\n \"startPage\": 4,\n \"endPage\": 8,\n \"ORIGIN_FILE_NAME\": \"EFTA00832161.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 9/EFTA00832161.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 9/EFTA00832161.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 512313,\n \"totalWords\": 2339,\n \"totalCharacters\": 13563,\n \"processedAt\": \"2026-01-30T18:09:53Z\",\n \"indexedAt\": \"2026-01-30T18:09:53Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00832161.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"That's why \\u003Cem\\u003ETrump\\u003C/em\\u003E.\",\n \"\\u003Cem\\u003ETrump\\u003C/em\\u003E: \\\"No, the other one.\\\"\",\n \"\\u003Cem\\u003ETrump\\u003C/em\\u003E: \\\"No, the other one.\\\"\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"318d22dc\",\n \"chunkIndex\": 6,\n \"totalChunks\": 8,\n \"charStart\": 42000,\n \"charEnd\": 49831,\n \"chunkSize\": 7831,\n \"isChunked\": true,\n \"startPage\": 12,\n \"endPage\": 15,\n \"ORIGIN_FILE_NAME\": \"EFTA00263405.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 9/EFTA00263405.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 9/EFTA00263405.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 4687526,\n \"totalWords\": 7886,\n \"totalCharacters\": 50618,\n \"processedAt\": \"2026-01-30T16:45:18Z\",\n \"indexedAt\": \"2026-01-30T16:45:19Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA00263405.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"8]\\nIn June 2018, the New York attorney general's office filed a civil suit against the foundation,\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E, and his adult children, seeking $2.8 million\",\n \"[141]\\nFilm and television\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E made cameo appearances in many films and television shows from 1985 to 2001. [142]\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E had a sporadic relationship with\",\n \"to deliver the $1 trillion infrastructure\\nspending plan he had campaigned on. [242]\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E speaks to automobile\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E is the only modern U.S. president\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"95107e13\",\n \"chunkIndex\": 2,\n \"totalChunks\": 3,\n \"charStart\": 13477,\n \"charEnd\": 21229,\n \"chunkSize\": 7752,\n \"isChunked\": true,\n \"startPage\": 3,\n \"endPage\": 6,\n \"ORIGIN_FILE_NAME\": \"EFTA01660679.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 10/EFTA01660679.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 10/EFTA01660679.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 473834,\n \"totalWords\": 3533,\n \"totalCharacters\": 21229,\n \"processedAt\": \"2026-02-04T00:50:59Z\",\n \"indexedAt\": \"2026-02-04T00:51:00Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA01660679.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"Victim 1 saw Donald \\u003Cem\\u003ETrump\\u003C/em\\u003E and wanted to meet him. A\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E\\nunknown man approached her and offered to introduce her to \\u003Cem\\u003ETrump\\u003C/em\\u003E.\",\n \"\\u003Cem\\u003Etrump\\u003C/em\\u003E would auction them\\nDonald \\u003Cem\\u003ETrump\\u003C/em\\u003E, Donald \\u003Cem\\u003ETrump\\u003C/em\\u003E\\nEFTA01660683\\n\\noff He measured the children's vulva and vaginas by entering a finger and\\nJr., Ivanka\",\n \"The guests were elder men and included Elon\\n\\u003Cem\\u003ETrump\\u003C/em\\u003E, Allan Dershowitz, Bob\\nMusk. Don jr. \\u003Cem\\u003ETrump\\u003C/em\\u003E, Ivanka \\u003Cem\\u003ETrump\\u003C/em\\u003E, and Eric \\u003Cem\\u003ETrump\\u003C/em\\u003E were there.\"\n ]\n }\n },\n {\n \"_source\": {\n \"documentId\": \"e2a307be\",\n \"chunkIndex\": 1,\n \"totalChunks\": 4,\n \"charStart\": 7000,\n \"charEnd\": 13792,\n \"chunkSize\": 6792,\n \"isChunked\": true,\n \"startPage\": 2,\n \"endPage\": 6,\n \"ORIGIN_FILE_NAME\": \"EFTA01433755.pdf\",\n \"ORIGIN_FILE_URI\": \"https://www.justice.gov/epstein/files/DataSet 10/EFTA01433755.pdf\",\n \"bucket\": \"amazon-s3x-sync\",\n \"key\": \"DataSet 10/EFTA01433755.pdf\",\n \"contentType\": \"application/pdf\",\n \"fileSize\": 717648,\n \"totalWords\": 3475,\n \"totalCharacters\": 21824,\n \"processedAt\": \"2026-01-30T13:00:21Z\",\n \"indexedAt\": \"2026-01-30T13:00:22Z\",\n \"source\": \"document-indexing-pipeline\"\n },\n \"fields\": {\n \"ORIGIN_FILE_NAME\": [\n \"EFTA01433755.pdf\"\n ]\n },\n \"highlight\": {\n \"content\": [\n \"response from Attorney\\nhttps://www.globalresearch.ca/katie-johnson-v-donald-j-\\u003Cem\\u003Etrump\\u003C/em\\u003E-and-jeffrey-e-\\nepstein-\\u003Cem\\u003Etrump\\u003C/em\\u003E-child-rape-clain-for-100-million-denied-by-\\u003Cem\\u003Etrump\\u003C/em\\u003E-attorney\",\n \"\\u003Cem\\u003ETrump\\u003C/em\\u003E and Jeffrey E.\",\n \"\\u003Cem\\u003ETrump\\u003C/em\\u003E denied Harth's claims, but she withdrew her suit after \\u003Cem\\u003ETrump\\u003C/em\\u003E settled\\nhis dispute with her husband.\"\n ]\n }\n }\n ]\n },\n \"aggregations\": {\n \"unique_count\": {\n \"value\": 4727\n }\n }\n}"}}, "process_efta.py": {"d33df51bb0121445c0656a4a5364f31e64802d7f": {"t": 1785604143.9650512, "n": 5888, "h": "1b069b7445efe5d0", "c": "import os\nimport re\nimport glob\nimport tempfile\nimport shutil\n\nOUTPUT_FILE = \"HASHES_made.txt\"\nBASE_DIR = \"EFTA\"\n\n\ndef parse_txt_file(filepath):\n last_modified = None\n etag = None\n try:\n with open(filepath, \"r\", encoding=\"utf-8\", errors=\"ignore\") as f:\n for line in f:\n line = line.strip()\n if line.startswith(\"Last-Modified:\"):\n last_modified = line.split(\"Last-Modified:\", 1)[1].strip()\n elif line.startswith(\"Etag:\"):\n etag = line.split(\"Etag:\", 1)[1].strip()\n except Exception as e:\n print(f\"Error reading {filepath}: {e}\")\n return last_modified, etag\n\n\ndef get_output_name(txt_filename):\n base = os.path.basename(txt_filename)\n if base.endswith(\"_pdf.txt\"):\n return base[:-len(\"_pdf.txt\")] + \".pdf\"\n if base.endswith(\".txt\"):\n base = base[:-4]\n if not re.search(r'\\.(pdf|mp4|mp3|jpg|jpeg|png|gif|mov|avi|mkv|doc|docx|xls|xlsx|zip|rar)$', base, re.IGNORECASE):\n base = base + \".pdf\"\n return base\n\n\ndef get_number(name):\n m = re.search(r'EFTA(\\d+)', os.path.basename(str(name)))\n return int(m.group(1)) if m else None\n\n\ndef collect_all_txt_files(base_dir):\n \"\"\"Walk ALL subdirectories and collect every .txt file, sorted by EFTA number then filename.\"\"\"\n all_files = []\n for root, dirs, files in os.walk(base_dir):\n dirs.sort() # walk subdirs in alphabetical order\n for fname in files:\n if fname.endswith(\".txt\"):\n all_files.append(os.path.join(root, fname))\n\n # Sort by numeric EFTA number first, then by filename (to keep mp4/pdf etc. stable)\n all_files.sort(key=lambda f: (get_number(f) or 0, os.path.basename(f)))\n return all_files\n\n\ndef load_hashes_file(output_file):\n \"\"\"Load HASHES_made.txt. Returns list of [name, line] and set of names.\"\"\"\n entries = []\n existing = set()\n if os.path.exists(output_file):\n with open(output_file, \"r\", encoding=\"utf-8\") as f:\n for raw in f:\n stripped = raw.strip()\n if stripped:\n name = stripped.split(\":\", 1)[0].strip()\n entries.append([name, stripped])\n existing.add(name)\n return entries, existing\n\n\ndef write_file(output_file, entries):\n \"\"\"Atomically rewrite the output file.\"\"\"\n dir_name = os.path.dirname(os.path.abspath(output_file)) or \".\"\n tmp_fd, tmp_path = tempfile.mkstemp(dir=dir_name, suffix=\".tmp\")\n try:\n with os.fdopen(tmp_fd, \"w\", encoding=\"utf-8\") as f:\n for name, line in entries:\n f.write(line + \"\\n\")\n shutil.move(tmp_path, output_file)\n except Exception:\n if os.path.exists(tmp_path):\n os.unlink(tmp_path)\n raise\n\n\ndef main():\n if not os.path.isdir(BASE_DIR):\n print(f\"ERROR: Directory '{BASE_DIR}' not found. Run this script from the parent folder of EFTA/.\")\n return\n\n # Step 1: Collect ALL txt files across ALL subdirs, sorted by number\n print(\"Scanning all subdirectories in EFTA/ ...\")\n all_files = collect_all_txt_files(BASE_DIR)\n print(f\"Found {len(all_files)} .txt files total.\")\n\n if all_files:\n first_num = get_number(all_files[0])\n last_num = get_number(all_files[-1])\n print(f\"Range: EFTA{first_num:08d} → EFTA{last_num:08d}\")\n\n # Step 2: Load what's already in HASHES_made.txt\n print(\"\\nLoading existing HASHES_made.txt...\")\n entries, existing = load_hashes_file(OUTPUT_FILE)\n print(f\"Already recorded: {len(existing)} entries.\")\n\n # Step 3: Check for gaps in existing file\n recorded_numbers = {} # number -> [names] (could have mp4 + pdf for same number)\n for name, line in entries:\n n = get_number(name)\n if n is not None:\n recorded_numbers.setdefault(n, []).append(name)\n\n all_file_numbers = set(get_number(f) for f in all_files if get_number(f) is not None)\n recorded_set = set(recorded_numbers.keys())\n gaps = sorted(all_file_numbers - recorded_set)\n\n if gaps:\n print(f\"Found {len(gaps)} gap(s) — these numbers exist in EFTA/ but are missing from HASHES_made.txt.\")\n else:\n print(\"No gaps found.\")\n\n # Step 4: Build a combined ordered list\n # Strategy: merge everything — existing entries + new/gap entries — sorted by number then name\n # Use a dict keyed by output_name to deduplicate\n combined = {} # output_name -> line\n\n # Seed with existing\n for name, line in entries:\n combined[name] = line\n\n # Process all files in order, adding anything not yet recorded\n new_count = 0\n skip_count = 0\n\n for filepath in all_files:\n output_name = get_output_name(filepath)\n if output_name in combined:\n skip_count += 1\n continue\n\n last_modified, etag = parse_txt_file(filepath)\n if last_modified and etag:\n combined[output_name] = f\"{output_name}: {last_modified}, {etag}\"\n new_count += 1\n if new_count % 10000 == 0:\n print(f\" Processed {new_count} new entries...\")\n else:\n print(f\" Skipping (no data): {filepath}\")\n\n print(f\"\\nNew entries to add: {new_count} | Skipped (exist): {skip_count}\")\n\n # Step 5: Sort everything by EFTA number then output name\n print(\"Sorting all entries...\")\n sorted_entries = sorted(\n combined.items(),\n key=lambda kv: (get_number(kv[0]) or 0, kv[0])\n )\n\n # Step 6: Write the fully sorted file\n print(f\"Writing {len(sorted_entries)} entries to {OUTPUT_FILE} ...\")\n write_file(OUTPUT_FILE, sorted_entries)\n\n print(f\"\\n=== Done ===\")\n print(f\"Total entries in file: {len(sorted_entries)}\")\n print(f\"New entries added: {new_count}\")\n print(f\"Skipped (existed): {skip_count}\")\n\n\nif __name__ == \"__main__\":\n main()\n"}}, "set_mtime_from_last_modified.py": {"8c6a081769a6d0b3da48ea30374c9ace0a5c05b2": {"t": 1785604146.0134835, "n": 5230, "h": "6c1a40287d330c59", "c": "#!/usr/bin/env python3\n\"\"\"\nScan all .txt files under a root folder (default: `EFTA/`), extract an HTTP-style\n\"Last-Modified\" header from each file, convert it to US/Eastern and set the\nfile's mtime/atime to that datetime.\n\nUsage examples:\n python set_mtime_from_last_modified.py # runs against EFTA/ and applies changes\n python set_mtime_from_last_modified.py --dry-run # only shows what would change\n\nNotes:\n- Requires Python 3.9+ for zoneinfo. If zoneinfo isn't available, falls back to\n fixed -05:00 (EST) offset.\n- The script tries to parse RFC-2822 style dates using email.utils.parsedate_to_datetime.\n- By default the timestamp is set to the exact instant represented by the header\n (so timezone-aware). If you want the \"wallclock\" Eastern time to be used as\n the file's local displayed time regardless of the machine timezone, use\n --use-est-wallclock.\n\"\"\"\n\nfrom pathlib import Path\nimport re\nimport os\nimport sys\nimport argparse\nfrom email.utils import parsedate_to_datetime\nimport datetime\n\n# Try to get America/New_York timezone; fall back to fixed -05:00 if unavailable\ntry:\n from zoneinfo import ZoneInfo\n NY_TZ = ZoneInfo(\"America/New_York\")\nexcept Exception:\n NY_TZ = datetime.timezone(datetime.timedelta(hours=-5))\n\nLM_RE = re.compile(r\"(?mi)^Last-Modified:\\s*(.+)$\")\n\n\ndef extract_last_modified(text: str):\n m = LM_RE.search(text)\n return m.group(1).strip() if m else None\n\n\ndef parsed_datetime(value: str):\n # returns a timezone-aware datetime on success, or raises\n dt = parsedate_to_datetime(value)\n if dt is None:\n raise ValueError(f\"Could not parse date: {value!r}\")\n # parsedate_to_datetime may return naive datetimes for some inputs; assume UTC then\n if dt.tzinfo is None:\n dt = dt.replace(tzinfo=datetime.timezone.utc)\n return dt\n\n\ndef set_file_mtime(path: Path, dt: datetime.datetime, use_wallclock=False):\n \"\"\"\n Set file mtime/atime. If use_wallclock is False, dt is treated as absolute (tz-aware)\n and converted to epoch seconds. If True, dt is converted to America/New_York,\n stripped of tzinfo, then interpreted as local time for the epoch calculation.\n \"\"\"\n if use_wallclock:\n # convert to Eastern, drop tzinfo => naive wallclock\n dt_est = dt.astimezone(NY_TZ).replace(tzinfo=None)\n # interpret that naive time as local timezone\n local_tz = datetime.datetime.now().astimezone().tzinfo\n dt_localized = dt_est.replace(tzinfo=local_tz)\n ts = dt_localized.timestamp()\n else:\n # canonical: use the absolute instant represented by the datetime\n dt_canonical = dt.astimezone(NY_TZ)\n ts = dt_canonical.timestamp()\n\n os.utime(path, (ts, ts))\n return datetime.datetime.fromtimestamp(ts, datetime.timezone.utc).astimezone(NY_TZ)\n\n\ndef process_file(path: Path, apply: bool, use_wallclock: bool):\n try:\n text = path.read_text(errors='ignore')\n except Exception as e:\n print(f\"Failed to read {path}: {e}\")\n return\n lm = extract_last_modified(text)\n if not lm:\n print(f\"No Last-Modified header: {path}\")\n return\n try:\n dt = parsed_datetime(lm)\n except Exception as e:\n print(f\"Failed to parse Last-Modified for {path}: {lm!r} ({e})\")\n return\n\n dt_est = dt.astimezone(NY_TZ)\n if apply:\n try:\n new_dt = set_file_mtime(path, dt, use_wallclock=use_wallclock)\n print(f\"Set: {path} -> {new_dt.isoformat()}\")\n except Exception as e:\n print(f\"Failed to set mtime for {path}: {e}\")\n else:\n if use_wallclock:\n # show the wallclock time we'd set\n wallclock = dt.astimezone(NY_TZ).replace(tzinfo=None)\n print(f\"Would set (wallclock): {path} -> {wallclock.isoformat()} [America/New_York]\")\n else:\n print(f\"Would set: {path} -> {dt_est.isoformat()} [America/New_York]\")\n\n\ndef main(argv=None):\n p = argparse.ArgumentParser(description=\"Set file mtimes from Last-Modified headers inside text files\")\n p.add_argument('--root', '-r', default='EFTA', help='Root folder to scan (default: EFTA)')\n p.add_argument('--ext', default='.txt', help='File extension to look for (default: .txt)')\n p.add_argument('--dry-run', action='store_true', help=\"Don't change files, only show what would be done\")\n p.add_argument('--use-est-wallclock', action='store_true', help=('Interpret the Eastern time as a wallclock and set the file mtime so the file\\n'\n ' displays that Eastern local time on the current machine (useful if\\n'\n ' you want the file timestamp to match the EST time literally).'))\n args = p.parse_args(argv)\n\n root = Path(args.root)\n if not root.exists():\n print(f\"Root not found: {root}\")\n return 2\n\n files = list(root.rglob(f'*{args.ext}'))\n if not files:\n print(f\"No files matching *{args.ext} under {root}\")\n return 0\n\n for f in files:\n process_file(f, apply=not args.dry_run, use_wallclock=args.use_est_wallclock)\n\n return 0\n\n\nif __name__ == '__main__':\n raise SystemExit(main())\n"}}, "zip_sum.py": {"22cc9b34398cadd70dbab3f1bc217547bbac5f39": {"t": 1785604147.1794703, "n": 2563, "h": "7d6529030b40f494", "c": "import urllib.request\nimport time\n\n# Define the headers dictionary\nheaders = {\n \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/144.0.0.0 Safari/537.36\",\n \"Accept-Language\": \"en-US,en;q=0.9\",\n \"Accept-Encoding\": \"gzip, deflate, br\",\n \"Referer\": \"https://www.justice.gov/epstein/doj-disclosures\",\n \"Origin\": \"https://www.justice.gov\",\n \"Cookie\": \"justiceGovAgeVerified=true\" # Using Cookie header as provided\n}\n\ndef fetch_head(url):\n try:\n req = urllib.request.Request(url, method='HEAD')\n # Add all headers from the dictionary\n for key, value in headers.items():\n req.add_header(key, value)\n with urllib.request.urlopen(req) as response:\n headers_resp = response.headers # Renamed to avoid conflict with 'headers' dict\n status = response.status\n last_modified = headers_resp.get('Last-Modified', 'N/A')\n date = headers_resp.get('Date', 'N/A')\n content_length = headers_resp.get('Content-Length', 'N/A')\n etag = headers_resp.get('ETag', 'N/A')\n content_type = headers_resp.get('Content-Type', 'N/A')\n return last_modified, date, content_length, etag, content_type, status\n except Exception as e:\n return 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 0 # 0 for error\n\n# Initial fetch\ndatasets = range(1, 13)\nlast_modifieds = {}\nlast_etags = {}\n\nwith open('zip_hashes.txt', 'w') as f:\n f.write('Last-Modified, Date, Content-Length, Etag, Content-Type, Status-code\\n')\n for i in datasets:\n url = f'https://www.justice.gov/epstein/files/DataSet%20{i}.zip'\n lm, dt, cl, et, ct, st = fetch_head(url)\n if st != 200:\n lm, dt, cl, et, ct = 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'\n line = f'DataSet {i}: {lm}, {dt}, {cl}, {et}, {ct}, {st}\\n'\n f.write(line)\n last_modifieds[i] = lm\n last_etags[i] = et\n\n# Continuous checking\nwhile True:\n time.sleep(300) # 5 minutes\n with open('zip_hashes.txt', 'a') as f:\n for i in datasets:\n url = f'https://www.justice.gov/epstein/files/DataSet%20{i}.zip'\n lm, dt, cl, et, ct, st = fetch_head(url)\n if st != 200:\n lm, dt, cl, et, ct = 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'\n if lm != last_modifieds[i] and et != last_etags[i]:\n line = f'DataSet {i}: {lm}, {dt}, {cl}, {et}, {ct}, {st}\\n'\n f.write(line)\n last_modifieds[i] = lm\n last_etags[i] = et"}}}} |