Add Docker/Lightsail deployment, web search summarization, and fix vite peer dep

- Add backend/frontend Dockerfiles, nginx reverse proxy config, and
  docker-compose.yml to run the app on AWS Lightsail; document the setup
  in docs/deploy-lightsail.md. Fix a .gitignore path anchoring bug that
  left backend/knowledge_base/web_search/ untracked instead of ignored.
- Summarize web search results into structured Markdown via LLM before
  saving them to the local knowledge base, and support regenerating
  existing entries from their source URLs (backend/app/core/memory_kb).
- Downgrade vite to ^6 to match @vitejs/plugin-vue's peer dependency
  range, fixing a failing `npm ci` (found while testing the Docker build).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

backend/.dockerignore

@@ -0,0 +1,10 @@
+.venv/
+.env
+*.db
+*.db-shm
+*.db-wal
+__pycache__/
+*.pyc
+.ruff_cache/
+.pytest_cache/
+knowledge_base/web_search/

backend/.env.example

@@ -20,6 +20,8 @@ DEBUG=false
 TAVILY_API_KEY=
 # 蓄積知識をシステムプロンプトに注入する際の最大件数
 KNOWLEDGE_CONTEXT_LIMIT=15
+# Web検索結果を構造的な要約にまとめる際に使うモデル（未設定ならDEFAULT_MODELを使用）
+SEARCH_SUMMARY_MODEL=
 
 # ローカルMarkdownナレッジベース（backend/knowledge_base/ 配下のファイルを話題に応じて注入）
 LOCAL_KB_DIR=knowledge_base

backend/Dockerfile

@@ -0,0 +1,22 @@
+FROM python:3.12-slim
+
+RUN pip install --no-cache-dir uv
+
+WORKDIR /app
+
+ENV UV_COMPILE_BYTECODE=1 \
+    UV_LINK_MODE=copy \
+    PYTHONUNBUFFERED=1
+
+# 依存関係だけ先にインストールしてレイヤーキャッシュを効かせる
+COPY pyproject.toml uv.lock ./
+RUN uv sync --frozen --no-install-project --no-dev
+
+COPY . .
+RUN uv sync --frozen --no-dev
+
+ENV PATH="/app/.venv/bin:$PATH"
+
+EXPOSE 8000
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]

backend/app/api/chat.py

@@ -11,6 +11,7 @@ from app.db.models import Session, Message
 from app.core.memory_kb import memory as mem
 from app.core import llm
 from app.core.memory_kb import knowledge
+from app.core.memory_kb import local_knowledge
 from app.core.search.websearch import WEB_SEARCH_TOOL
 from app.core.config import DEFAULT_MODEL
 from app.core.memory_kb.tagging import tag_message_by_id
@@ -77,6 +78,13 @@ def delete_session(session_id: str, db: DBSession = Depends(get_db)):
     db.commit()
 
 
+@router.post("/knowledge/regenerate")
+async def regenerate_knowledge(db: DBSession = Depends(get_db)):
+    """既存のKnowledgeEntryを出典URLから取得し直し、構造化要約に再生成する（一括実行用）。"""
+    count = await knowledge.regenerate_from_sources(db)
+    return {"regenerated": count}
+
+
 @router.post("/stream")
 async def stream_chat(req: ChatRequest, db: DBSession = Depends(get_db)):
     # セッション取得 or 新規作成
@@ -126,9 +134,10 @@ async def stream_chat(req: ChatRequest, db: DBSession = Depends(get_db)):
                 ]
                 yield sse({"type": "sources", "value": sources})
                 for s in searches:
-                    summary = "\n".join(r["content"][:300] for r in s["results"] if r["content"])
+                    summary = await knowledge.summarize_results(s["query"], s["results"])
                     if summary:
                         knowledge.save_knowledge(db, s["query"], summary, s["results"])
+                        local_knowledge.save_search_result(s["query"], summary, s["results"])
 
             search_tools = [WEB_SEARCH_TOOL] if len(resolved_context) > len(context) else None
             async for chunk in llm.stream_chat(

backend/app/core/config.py

@@ -16,6 +16,8 @@ TAGGING_MODEL: str | None = os.getenv("TAGGING_MODEL")
 TAVILY_API_KEY: str | None = os.getenv("TAVILY_API_KEY")
 # 蓄積した知識をシステムプロンプトに注入する際の最大件数
 KNOWLEDGE_CONTEXT_LIMIT: int = int(os.getenv("KNOWLEDGE_CONTEXT_LIMIT", "15"))
+# Web検索結果を構造的な要約にまとめる際に使うモデル（未設定ならDEFAULT_MODELを使用）
+SEARCH_SUMMARY_MODEL: str | None = os.getenv("SEARCH_SUMMARY_MODEL")
 
 # ローカルMarkdownナレッジベース（話題に応じて関連ファイルをシステムプロンプトに注入）
 LOCAL_KB_DIR: str = os.getenv("LOCAL_KB_DIR", "knowledge_base")

backend/app/core/memory_kb/knowledge.py

@@ -1,8 +1,133 @@
+import asyncio
+import logging
+import re
+
+import httpx
+import trafilatura
 from sqlalchemy.orm import Session as DBSession
 
-from app.core.config import KNOWLEDGE_CONTEXT_LIMIT
+from app.core import llm
+from app.core.config import KNOWLEDGE_CONTEXT_LIMIT, SEARCH_SUMMARY_MODEL
+from app.core.memory_kb import local_knowledge
 from app.db.models import KnowledgeEntry, KnowledgeSource
 
+logger = logging.getLogger(__name__)
+
+_TAG_STRIP_RE = re.compile(r"<(script|style)[^>]*>.*?</\1>", re.S | re.I)
+_HTML_TAG_RE = re.compile(r"<[^>]+>")
+
+_SUMMARY_PROMPT = (
+    "以下はWeb検索「{query}」で得られた複数の検索結果です。"
+    "これらの内容を整理し、Markdown形式で構造的にまとめてください。\n"
+    "- 検索結果間で重複する情報はまとめ、矛盾する情報があれば併記する\n"
+    "- 見出し（##）やトピックごとの箇条書きを使い、要点が一目で分かるようにする\n"
+    "- 各項目の末尾に (出典: サイト名) を付ける\n"
+    "- 説明文や前置きは不要。まとめ本文のみを出力する\n\n"
+    "検索結果:\n{results}"
+)
+
+
+async def summarize_results(query: str, results: list[dict], model: str | None = None) -> str:
+    """Web検索結果（title/url/content のリスト）をLLMで構造的なMarkdown要約にまとめる。
+
+    要約に失敗した場合は空文字を返す（生のスクレイピング結果を未加工のままファイルに
+    書き込むと、ページに残ったスクリプト断片等がセキュリティソフトに誤検知されることがあるため、
+    フォールバックとして生テキストを書き出すことはしない）。
+    """
+    if not results:
+        return ""
+
+    raw = "\n\n".join(
+        f"### {r.get('title') or r['url']}\n{r.get('content', '')[:1500]}"
+        for r in results
+        if r.get("content")
+    )
+    if not raw:
+        return ""
+
+    prompt = _SUMMARY_PROMPT.format(query=query, results=raw)
+    try:
+        return await llm.complete(
+            [{"role": "user", "content": prompt}],
+            model=model or SEARCH_SUMMARY_MODEL,
+        )
+    except Exception:
+        logger.exception("Failed to summarize search results for query=%r", query)
+        return ""
+
+
+def _strip_tags(html: str) -> str:
+    """trafilataruがメインコンテンツを抽出できなかった場合の素朴なフォールバック。"""
+    text = _TAG_STRIP_RE.sub(" ", html)
+    text = _HTML_TAG_RE.sub(" ", text)
+    return re.sub(r"\s+", " ", text).strip()
+
+
+async def _fetch_page_text(url: str, max_chars: int = 4000) -> str:
+    """URLからヘッダー・サイドバー・フッター・広告などを除いた本文だけを抽出する。取得失敗時は空文字。"""
+    try:
+        async with httpx.AsyncClient(timeout=10.0, follow_redirects=True) as client:
+            res = await client.get(url, headers={"User-Agent": "Mozilla/5.0"})
+            res.raise_for_status()
+            html = res.text
+    except Exception:
+        logger.warning("Failed to fetch page for regeneration: %s", url)
+        return ""
+
+    # trafilatura.extract()はCPU負荷のある同期処理のため、そのままawait内で呼ぶと
+    # asyncioのイベントループ全体をブロックしてしまう（チャット応答等が止まる）。
+    # asyncio.to_thread()で別スレッドに逃がす。
+    main_text = await asyncio.to_thread(
+        trafilatura.extract,
+        html,
+        url=url,
+        include_comments=False,
+        include_tables=True,
+        favor_precision=True,
+    )
+    text = main_text if main_text else _strip_tags(html)
+    return text[:max_chars]
+
+
+async def regenerate_from_sources(db: DBSession) -> int:
+    """既存のKnowledgeEntryについて、出典URLから本文を取得し直し、構造的な要約に再生成する。
+
+    KnowledgeSourceにはURLしか保存されていないため、当時の検索結果本文ではなく
+    現時点のページ内容を取得し直す点に注意（記事が更新・削除されている場合がある）。
+    戻り値: 再生成できた件数
+    """
+    entries = db.query(KnowledgeEntry).all()
+    count = 0
+    for entry in entries:
+        if not entry.sources:
+            continue
+
+        contents = await asyncio.gather(*(_fetch_page_text(s.url) for s in entry.sources))
+        results = [
+            {"title": s.title, "url": s.url, "content": content}
+            for s, content in zip(entry.sources, contents)
+            if content
+        ]
+        if not results:
+            continue
+
+        new_summary = await summarize_results(entry.query, results)
+        if not new_summary:
+            continue
+
+        old_summary = entry.summary
+        entry.summary = new_summary
+        db.commit()
+
+        local_knowledge.delete_search_result_file(entry.query, old_summary)
+        local_knowledge.save_search_result(
+            entry.query, new_summary, [{"title": s.title, "url": s.url} for s in entry.sources],
+        )
+        count += 1
+
+    logger.info("Regenerated %d knowledge entries from their sources", count)
+    return count
+
 
 def save_knowledge(db: DBSession, query: str, summary: str, sources: list[dict]) -> KnowledgeEntry:
     """Web検索で得た知見をDBに保存する。"""

backend/app/core/memory_kb/local_knowledge.py

@@ -13,7 +13,7 @@ from sqlalchemy.orm import Session as DBSession
 
 from app.core import llm
 from app.core.config import LOCAL_KB_DIR, LOCAL_KB_EMBEDDING_MODEL, LOCAL_KB_MIN_SCORE, LOCAL_KB_TOP_K
-from app.db.models import LocalKnowledgeDoc
+from app.db.models import KnowledgeEntry, LocalKnowledgeDoc
 
 logger = logging.getLogger(__name__)
 
@@ -43,6 +43,45 @@ def _cosine_similarity(a: list[float], b: list[float]) -> float:
     return dot / (norm_a * norm_b)
 
 
+def save_search_result(query: str, summary: str, sources: list[dict]) -> None:
+    """Web検索結果をローカルナレッジベースにMarkdownとして永続化する。
+
+    同じクエリ・内容の組み合わせは同じファイル名になるため重複保存されない。
+    保存しただけでは埋め込みは計算されず、次回の sync_local_kb() 実行時（=次の会話）に
+    自動的に埋め込まれ、以後の会話で話題に応じて引き出せるようになる。
+    """
+    kb_dir = _kb_dir() / "web_search"
+    kb_dir.mkdir(parents=True, exist_ok=True)
+
+    filename = _hash(query + summary)[:16] + ".md"
+    urls = "\n".join(f"- [{s.get('title') or s['url']}]({s['url']})" for s in sources if s.get("url"))
+    content = f"# {query}\n\n{summary}\n\n## 出典\n{urls}\n"
+    (kb_dir / filename).write_text(content, encoding="utf-8")
+
+
+def delete_search_result_file(query: str, summary: str) -> None:
+    """save_search_result()が書き出したファイルを削除する。要約を再生成して内容が変わった際の旧ファイル掃除用。"""
+    filename = _hash(query + summary)[:16] + ".md"
+    (_kb_dir() / "web_search" / filename).unlink(missing_ok=True)
+
+
+def backfill_search_results(db: DBSession) -> int:
+    """DBに蓄積済みの過去のWeb検索結果(KnowledgeEntry)をすべてMarkdownファイルとして書き出す。
+
+    save_search_result()と同じファイル名規則（内容のハッシュ）を使うため、
+    すでにmd化済みのものは上書きされるだけで重複は増えない。
+    戻り値: 書き出した件数
+    """
+    entries = db.query(KnowledgeEntry).all()
+    count = 0
+    for entry in entries:
+        sources = [{"title": s.title, "url": s.url} for s in entry.sources]
+        save_search_result(entry.query, entry.summary, sources)
+        count += 1
+    logger.info("Backfilled %d search result(s) to local knowledge base", count)
+    return count
+
+
 async def sync_local_kb(db: DBSession) -> None:
     """ナレッジベースディレクトリをスキャンし、新規/変更ファイルの埋め込みを更新する。
     削除されたファイルに対応するレコードも削除する。

backend/pyproject.toml

@@ -18,6 +18,7 @@ dependencies = [
     "httpx>=0.28.1",
     "discord-py>=2.7.1",
     "janome>=0.5.0",
+    "trafilatura>=2.1.0",
 ]
 
 [project.optional-dependencies]

backend/uv.lock

@@ -235,6 +235,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/f6/22/91616fe707a5c5510de2cac9b046a30defe7007ba8a0c04f9c08f27df312/audioop_lts-0.2.2-cp314-cp314t-win_arm64.whl", hash = "sha256:b492c3b040153e68b9fdaff5913305aaaba5bb433d8a7f73d5cf6a64ed3cc1dd", size = 25206, upload-time = "2025-08-05T16:43:16.444Z" },
 ]
 
+[[package]]
+name = "babel"
+version = "2.18.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/7d/b2/51899539b6ceeeb420d40ed3cd4b7a40519404f9baf3d4ac99dc413a834b/babel-2.18.0.tar.gz", hash = "sha256:b80b99a14bd085fcacfa15c9165f651fbb3406e66cc603abf11c5750937c992d", size = 9959554, upload-time = "2026-02-01T12:30:56.078Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/77/f5/21d2de20e8b8b0408f0681956ca2c69f1320a3848ac50e6e7f39c6159675/babel-2.18.0-py3-none-any.whl", hash = "sha256:e2b422b277c2b9a9630c1d7903c2a00d0830c409c59ac8cae9081c92f1aeba35", size = 10196845, upload-time = "2026-02-01T12:30:53.445Z" },
+]
+
 [[package]]
 name = "boto3"
 version = "1.43.32"
@@ -366,6 +375,35 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6", size = 25335, upload-time = "2022-10-25T02:36:20.889Z" },
 ]
 
+[[package]]
+name = "courlan"
+version = "1.4.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "babel" },
+    { name = "tld" },
+    { name = "urllib3" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/bb/16/2a771612ee0b3acaa95ac21cc7e8a3319e815d6360f8ffc5987d1ce28499/courlan-1.4.0.tar.gz", hash = "sha256:fbbac7b7fcde2195ea08e707609503c81cf39c891e8d26cdb1fed4585782d63d", size = 208997, upload-time = "2026-06-01T17:30:17.306Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/1f/38/ce65091ff20a16e06d17418c4353af5f56d3190821b1a06983c79ae79274/courlan-1.4.0-py3-none-any.whl", hash = "sha256:ad1dbdefd912ca7238d4607dc855df5df097f56bac175dd662c84eed3802f49e", size = 34193, upload-time = "2026-06-01T17:30:14.984Z" },
+]
+
+[[package]]
+name = "dateparser"
+version = "1.4.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "python-dateutil" },
+    { name = "pytz" },
+    { name = "regex" },
+    { name = "tzlocal" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/d3/f4/561c49bca97af561d34eed27e3e831135eb5cb88e754c1150be41820f5c6/dateparser-1.4.1.tar.gz", hash = "sha256:f265df13c0380e2e07543ba74b67c0681aaa1096981ffcd35227e1aa0cb81c7c", size = 314734, upload-time = "2026-06-15T08:45:47.659Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/8b/7c/2e5dcf53909deddd0bf38cbe277ad9806be038276b1c6c436561b4d9b2e2/dateparser-1.4.1-py3-none-any.whl", hash = "sha256:f25d4e051a84be27a35bd297e3e1dc59ff78373701b89be352ba80372d22d0d0", size = 300503, upload-time = "2026-06-15T08:45:45.951Z" },
+]
+
 [[package]]
 name = "discord-py"
 version = "2.7.1"
@@ -648,6 +686,22 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/62/94/3b66b148778ee100dcfd69c2ca22b57b41b44d3063ceec934f209e9184ce/hf_xet-1.5.0-cp37-abi3-win_arm64.whl", hash = "sha256:b6c9df403040248c76d808d3e047d64db2d923bae593eb244c41e425cf6cd7be", size = 3806916, upload-time = "2026-05-06T06:18:21.7Z" },
 ]
 
+[[package]]
+name = "htmldate"
+version = "1.10.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "charset-normalizer" },
+    { name = "dateparser" },
+    { name = "lxml" },
+    { name = "python-dateutil" },
+    { name = "urllib3" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/ad/1f/e7cf83e23d7b68105de8b874a8b36ba23b450d6f71388583e4ca3ce475ca/htmldate-1.10.0.tar.gz", hash = "sha256:a38df10772ab5d7dbb11896e3f6a852a8491fb1b0965465bc174e23fc2baae58", size = 44455, upload-time = "2026-06-01T17:43:53.437Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f7/17/d3356233c826c641f940983d9479eab27faec59d49f4070bc58e80fcc021/htmldate-1.10.0-py3-none-any.whl", hash = "sha256:9211dae35ab94147c8ed9e5fc2c9287a5cf31d2394cb7857e7f5dd814eb2aad6", size = 31561, upload-time = "2026-06-01T17:43:51.797Z" },
+]
+
 [[package]]
 name = "httpcore"
 version = "1.0.9"
@@ -856,6 +910,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/41/45/1a4ed80516f02155c51f51e8cedb3c1902296743db0bbc66608a0db2814f/jsonschema_specifications-2025.9.1-py3-none-any.whl", hash = "sha256:98802fee3a11ee76ecaca44429fda8a41bff98b00a0f2838151b113f210cc6fe", size = 18437, upload-time = "2025-09-08T01:34:57.871Z" },
 ]
 
+[[package]]
+name = "justext"
+version = "3.0.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "lxml", extra = ["html-clean"] },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/49/f3/45890c1b314f0d04e19c1c83d534e611513150939a7cf039664d9ab1e649/justext-3.0.2.tar.gz", hash = "sha256:13496a450c44c4cd5b5a75a5efcd9996066d2a189794ea99a49949685a0beb05", size = 828521, upload-time = "2025-02-25T20:21:49.934Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f2/ac/52f4e86d1924a7fc05af3aeb34488570eccc39b4af90530dd6acecdf16b5/justext-3.0.2-py2.py3-none-any.whl", hash = "sha256:62b1c562b15c3c6265e121cc070874243a443bfd53060e869393f09d6b6cc9a7", size = 837940, upload-time = "2025-02-25T20:21:44.179Z" },
+]
+
 [[package]]
 name = "litellm"
 version = "1.86.2"
@@ -879,6 +945,103 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/4d/37/4da1dd67157aaa11477d6c63e4725216bfc46b4661e581b490d17e5b2831/litellm-1.86.2-py3-none-any.whl", hash = "sha256:27096463be7add661513ada3d9039e8f1a6195859e604d30fde96c939efe0a03", size = 17013061, upload-time = "2026-05-27T16:19:53.219Z" },
 ]
 
+[[package]]
+name = "lxml"
+version = "6.1.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/05/3b/aab6728cae887456f409b4d75e8a01856e4f04bd510de38052a47768b680/lxml-6.1.1.tar.gz", hash = "sha256:ba96ae44888e0185281e937633a743ea90d5a196c6000f82565ebb0580012d40", size = 4197430, upload-time = "2026-05-18T19:19:06.424Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/6a/6e/c4add832b6fc1e887125b96f880d7b9b70aae5248718e046b1704bcac4b9/lxml-6.1.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:104c09bda8d2a562824c0e319d0768ce26a779b7601e0931d33b09b53c392ef7", size = 8570821, upload-time = "2026-05-18T19:17:42.068Z" },
+    { url = "https://files.pythonhosted.org/packages/22/00/ff3009c88e65de8011630acf8ab5a09cb2becd2aaf47fba2f3449f6224e9/lxml-6.1.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:25c6997a9a534e016695a0ba06b2f07945de682731ff01065b6d5a4474179da1", size = 4624252, upload-time = "2026-05-18T19:17:47.897Z" },
+    { url = "https://files.pythonhosted.org/packages/42/95/bb63f0fd62e554fe078e1fb3c8fe9083c14ddc7ad7fa178d10e57e071ac7/lxml-6.1.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:c921ba5c51e4e9f63b8b00267d06566e1f63407408a0496da2d1d0bfc819c7fc", size = 4930746, upload-time = "2026-05-18T19:18:29.637Z" },
+    { url = "https://files.pythonhosted.org/packages/eb/99/0013e8d9b5960f4f041cf0b73e2f80c23eb5205b1f7bfb20203243651359/lxml-6.1.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:54a7f95e4de5fb94e2f9f4b9055c6ba33bf3d628fd77a1d647c5923caa2cdcdc", size = 5093723, upload-time = "2026-05-18T19:18:34.168Z" },
+    { url = "https://files.pythonhosted.org/packages/29/91/317b332636bfc7bddcff828d41b3307f50043f4b237e40849c333d80fa1a/lxml-6.1.1-cp312-cp312-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:96f2ec43df44b1f76249ee0a615334f9b5b060e1c8bd90e706dad2d14d02f383", size = 5005557, upload-time = "2026-05-18T19:18:39.798Z" },
+    { url = "https://files.pythonhosted.org/packages/42/2f/cc9bf06afe70f9c9093ae60855d9759da9db601ec4080f7473319666ffd7/lxml-6.1.1-cp312-cp312-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:70ef8a7e102a1508f8121aae5b0867abd663f72c14f0a9c937e6554cb4587b7b", size = 5631036, upload-time = "2026-05-18T19:18:44.858Z" },
+    { url = "https://files.pythonhosted.org/packages/08/f6/af32e23e563971ffb0fb86be52bc5be5c2c118858ffc119bf6a9039b173d/lxml-6.1.1-cp312-cp312-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ebe6af670449830d6d9b752c256a983291c766a1365ba5d5460048f9e33a7818", size = 5240367, upload-time = "2026-05-18T19:18:49.217Z" },
+    { url = "https://files.pythonhosted.org/packages/78/83/8555d40948b09ce86f1bd0c68a7ac31d07b1929f92cc1b074006c97ef2d2/lxml-6.1.1-cp312-cp312-manylinux_2_28_i686.whl", hash = "sha256:27acc820660aaffa4f7c087f29120e12980f7779d56d8492d263170111284740", size = 5350171, upload-time = "2026-05-18T19:18:52.779Z" },
+    { url = "https://files.pythonhosted.org/packages/63/75/5d92da93729b7bad783689e6496049fa40927b45bec7bf183c981de3ca70/lxml-6.1.1-cp312-cp312-manylinux_2_31_armv7l.whl", hash = "sha256:1db753c9115ec7100d073b744d17e25e88a8f90f5c39b2f5dd878149af59671f", size = 4694874, upload-time = "2026-05-18T19:18:55.139Z" },
+    { url = "https://files.pythonhosted.org/packages/c5/b5/3aad415a9a25b822e783f15deeb4dffccf5113030f1afa2222dd929313d9/lxml-6.1.1-cp312-cp312-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:c4f469aebd783bb741c2ecb2a681008fd26bfe5c16a9a72ed5467f834e810df2", size = 5244492, upload-time = "2026-05-18T19:19:01.28Z" },
+    { url = "https://files.pythonhosted.org/packages/f1/a1/5fcf7eb9904b80086aa47dcf0027de07b1bb990afad2e6823144c368ae04/lxml-6.1.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:766b010012d59470072c1816b5b6c69f1d243e5db36ea5968e94accf430a4635", size = 5048232, upload-time = "2026-05-18T19:18:12.67Z" },
+    { url = "https://files.pythonhosted.org/packages/77/74/1f601b63c7a69fcdf10fa9b148c81da8442204194f6c55509cc485c786b9/lxml-6.1.1-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:b8d812c6011c08b8111a15e54dd990b8923692d80adf35488bee34026c35accf", size = 4777023, upload-time = "2026-05-18T19:18:15.928Z" },
+    { url = "https://files.pythonhosted.org/packages/a2/b9/7a78f51aec95b1bf780d78e12705a9f6533284f8693dc5c0e6724fa53d3f/lxml-6.1.1-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:fe0306bd29505a9177aac19f1877174b0e7422c222a59f70b2cd41633448c3dc", size = 5645773, upload-time = "2026-05-18T19:18:23.223Z" },
+    { url = "https://files.pythonhosted.org/packages/a5/6e/98a7b7ad54e4e74fa1f20fff776913980619d0ebe5558232d7da6580bdd8/lxml-6.1.1-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:5ba186ad207446c65d3bb3d3e0412b032b1d9f595e59861e2354798c5703d955", size = 5233088, upload-time = "2026-05-18T19:18:31.433Z" },
+    { url = "https://files.pythonhosted.org/packages/65/d1/bc0ed2427bf609f2ee10da303a6a226f9c8bce94f945dc29a32ce55de6e4/lxml-6.1.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:aa366a1e55b8ebfe8ca8ddc3cfe75c8ebade181aeb0f661d0cb05986b647f72a", size = 5260995, upload-time = "2026-05-18T19:18:37.091Z" },
+    { url = "https://files.pythonhosted.org/packages/69/8b/6772e1a4b513fc50a8d931f19edde0e13ae6918510a1e13ff67864f3e5ed/lxml-6.1.1-cp312-cp312-win32.whl", hash = "sha256:126c93f7f56f0eda92f6d8c619edc463a4f23d9252f1c9d0405a76f25fa9f11a", size = 3596382, upload-time = "2026-05-18T19:17:18.37Z" },
+    { url = "https://files.pythonhosted.org/packages/1b/89/45198e9624762af2dfd2cb8782598477ceb29f6e59caab560388ae1f4ec1/lxml-6.1.1-cp312-cp312-win_amd64.whl", hash = "sha256:26e6eda8d38c1fcab1090dd196ee87cbd13788e531937610e2589085de074e77", size = 3997255, upload-time = "2026-05-18T19:17:56.781Z" },
+    { url = "https://files.pythonhosted.org/packages/90/a9/7a54b6834088d9ae528a7b780584ba6a39a9457b0ac330479f20ffbc9449/lxml-6.1.1-cp312-cp312-win_arm64.whl", hash = "sha256:6540377fbd53fe1b629172288c464fb18db11ce1fa7dc15891da10aa9dcc3e7f", size = 3659610, upload-time = "2026-05-19T19:22:50.843Z" },
+    { url = "https://files.pythonhosted.org/packages/a5/eb/7e6f37c5584ccbb2ff267f56fd0339016938c1c8684cfefab9b33ffc2f36/lxml-6.1.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:68a9198d0fc122d14bb76837de9aa80cf84caed990b5b237f532ed87d3706736", size = 8559780, upload-time = "2026-05-18T19:17:57.661Z" },
+    { url = "https://files.pythonhosted.org/packages/a1/36/587c2521cf23a2cd6c9c22108aa7528f683a1f195ed7ccd23a4b1786ad36/lxml-6.1.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:7d47866cb32fb503450b6edc9df355d10dc49836af2e89901bd6ac6b0896d9d9", size = 4618006, upload-time = "2026-05-18T19:18:04.452Z" },
+    { url = "https://files.pythonhosted.org/packages/6e/ca/ab7bfe2bf4c972af5e7878262845ead3a24a929a9b04bc11c7c1ece6c82a/lxml-6.1.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:eb7c9811bfaa8b1ed5ed319f5d370dfbcaa59d52ea64be2a5a85e18195930354", size = 4924139, upload-time = "2026-05-18T19:19:04.873Z" },
+    { url = "https://files.pythonhosted.org/packages/6b/55/a0c72851dfee5ecc689f949723a73dea457758912542cb955b108eaf0d8f/lxml-6.1.1-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:762ff394d5bd56da0cf034a23dcce4e13923f15321a2adfa2ac00201dc6d3fca", size = 5082329, upload-time = "2026-05-18T19:19:09.728Z" },
+    { url = "https://files.pythonhosted.org/packages/f0/b6/0608f7d61a3b96cc67e5648a3d906e31a5082093e10e7be65b3886289938/lxml-6.1.1-cp313-cp313-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a088f287f7d8275a33c07f2cac6c50b9319309a0200a39e7e75d80c707723099", size = 4993564, upload-time = "2026-05-18T19:19:13.608Z" },
+    { url = "https://files.pythonhosted.org/packages/4c/66/ae227524b066d29d55bf0b453d93d2d793c40218657d643dcbbca13b8faf/lxml-6.1.1-cp313-cp313-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:e902da4b04e6b52e5893900d4b8ab46068f75f3561f01bf1080957f9fd932ed6", size = 5613467, upload-time = "2026-05-18T19:19:16.228Z" },
+    { url = "https://files.pythonhosted.org/packages/a6/76/dbe4a00b50385e40194231dcfe5a12c059de7cf90e89c83407d2b085b719/lxml-6.1.1-cp313-cp313-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1d4962d4c66bf830a7e59ed6cfc17d148149898a3aefa8ec6e59763e6e3ed085", size = 5228304, upload-time = "2026-05-18T19:19:19.354Z" },
+    { url = "https://files.pythonhosted.org/packages/1c/01/00b1b8442ed2041793336868ba0b9ea4b13d7da7c085c6404c207a63bf79/lxml-6.1.1-cp313-cp313-manylinux_2_28_i686.whl", hash = "sha256:581d4c8ae690a6609e64862dd6b7c2489635c2d13907fc2b20f2bc200ff1d21e", size = 5341607, upload-time = "2026-05-18T19:19:22.297Z" },
+    { url = "https://files.pythonhosted.org/packages/63/36/1ad29931e9a4638bb707869f01d423a6c815f82152138d1a40dfcfde2b95/lxml-6.1.1-cp313-cp313-manylinux_2_31_armv7l.whl", hash = "sha256:876e1ff5930ed8bf295ec5ef9a8155e9b6b1876bbf1deed8b3a8069311875a8f", size = 4700168, upload-time = "2026-05-18T19:19:25.133Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/d1/a9536cecf9be18a0dc72d32bead283a2332d1ffebd2dd3ac70ce444686e5/lxml-6.1.1-cp313-cp313-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:9eb9b5a968f6e0f6d640092a567e14529ff8cea2e29d00da6f78a79fa49f013c", size = 5232487, upload-time = "2026-05-18T19:19:28.603Z" },
+    { url = "https://files.pythonhosted.org/packages/0e/77/b4fb1e03bf5d130e879214d3100092e386418807fb74dd0adc4b0a48f351/lxml-6.1.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:aa49e06d94aba782c6a02eecb7e507969e7e7a41b267f1b359bb35585f295d5b", size = 5044231, upload-time = "2026-05-18T19:18:42.246Z" },
+    { url = "https://files.pythonhosted.org/packages/26/4c/d00daeeb0a5530c4028a9232aa1b93db3ef4ed2158c116ea73c79a9765b3/lxml-6.1.1-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:70cdfd80589d59e43e18005dd7244e8895e93db8ab6a620b7e23df5445a4e3d2", size = 4769450, upload-time = "2026-05-18T19:18:48.013Z" },
+    { url = "https://files.pythonhosted.org/packages/ed/6a/715a3a8d156ce42f29cf014706f5410c2ff3b02267774110fc23266409fe/lxml-6.1.1-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:aad9aa39483ed8ec44d6d2e59e5b98a0d80676ef0d92f44bfc374836111f62f5", size = 5635874, upload-time = "2026-05-18T19:18:51.914Z" },
+    { url = "https://files.pythonhosted.org/packages/45/37/0544bc21dde2a88f3a17b504e6fc79c0e01d25a33c2f6079724e9e72b9c7/lxml-6.1.1-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:d49514be2f28d895c38cf9d2b72d7b9a07d00314519f456c0b50b53cfcf4c785", size = 5223987, upload-time = "2026-05-18T19:18:59.715Z" },
+    { url = "https://files.pythonhosted.org/packages/4d/f8/f6a5e8185bcb28c2befae3d31f8e3df3b811cb0f47746517a81279fcafe1/lxml-6.1.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:47402e62c52ff5988c1e8c6c63177f5708bccf48e366dea4e3dcf1e645e04947", size = 5250276, upload-time = "2026-05-18T19:19:03.834Z" },
+    { url = "https://files.pythonhosted.org/packages/c7/f2/1a2b9f1b7a49d45495369be7ef9ad05b262930f2eab3e3145706fca8083f/lxml-6.1.1-cp313-cp313-win32.whl", hash = "sha256:3483644525531e1d5762b0c44a8e18b6efba321b6dcf8a8952de10b037618bca", size = 3596903, upload-time = "2026-05-18T19:17:29.863Z" },
+    { url = "https://files.pythonhosted.org/packages/e6/99/f4ffb024f238eec2131aaa09f3278fb6129cf892741bf68e1fc1afb8c100/lxml-6.1.1-cp313-cp313-win_amd64.whl", hash = "sha256:a10bd2fd62e8ce916ececb342f348f190724a098c1faa056fdfb2a22ad5e8660", size = 3995869, upload-time = "2026-05-18T19:18:02.596Z" },
+    { url = "https://files.pythonhosted.org/packages/d1/53/70eb8c5c6037f27448f1e3c54ebede9545a801ae63f0a7254afca4fe8e45/lxml-6.1.1-cp313-cp313-win_arm64.whl", hash = "sha256:424aa57aca0897eb922aef34395bd1289b3b6f04e6bae20ea123c0c7e333cffc", size = 3658490, upload-time = "2026-05-19T19:22:53.846Z" },
+    { url = "https://files.pythonhosted.org/packages/13/e2/2e325795566de01d0d7c3bb57d3c370616b2d07b01214e84eec5d3b10963/lxml-6.1.1-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:19b7ab10b210b0b3ad7985d9ac4eb66ab09a90b20fe6e2f7ba55d01a234345d0", size = 8577146, upload-time = "2026-05-18T19:18:17.765Z" },
+    { url = "https://files.pythonhosted.org/packages/93/cf/5630b5e4be7d2e6bee8efe83865c925221103cf0221303b104ce134b01e2/lxml-6.1.1-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:c08e5c694306507275f2290073350c4f32e383db15213b2c69e7ff39c1193840", size = 4623866, upload-time = "2026-05-18T19:18:30.669Z" },
+    { url = "https://files.pythonhosted.org/packages/d2/51/3904907c063451cf8d4a5c9fe0cad95fa1f4ec57f4e3884fa0731bd7a305/lxml-6.1.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:74a9717fd0d82effef5c2854f0d917231d5324b5a3eb7275c43ac9fa32f97a14", size = 4950022, upload-time = "2026-05-18T19:19:31.958Z" },
+    { url = "https://files.pythonhosted.org/packages/94/cd/9c7611a51c37a2830928405817cc5d56a97f64fab83cc3f628748b135749/lxml-6.1.1-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:efe0374196335f93b53269acd811b944f2e6bdc88e8894f214bd636455484909", size = 5086695, upload-time = "2026-05-18T19:19:34.764Z" },
+    { url = "https://files.pythonhosted.org/packages/da/d6/24e3b5906abb0b674ff2ae195bc3ce59708df2bcd17cf17703b2d7dd643a/lxml-6.1.1-cp314-cp314-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ac931cdc9442c1763b8a8f6cd62c0c938737eafc5be75eff88df55fc73bc0d00", size = 5031642, upload-time = "2026-05-18T19:19:37.771Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/db/6ec54f99019838bff54785c51da07f189eb4676861c5f2730962b0d8d665/lxml-6.1.1-cp314-cp314-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:aee395f5d0927f947758b4ec119fd5fc8ec71f07a1c5c52077b30b04c0fa6955", size = 5647338, upload-time = "2026-05-18T19:19:40.553Z" },
+    { url = "https://files.pythonhosted.org/packages/42/3d/ef4dcfffd22d27a61805d8ed9f7fb888495bc6aa88648fa07c1eaa5586b6/lxml-6.1.1-cp314-cp314-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9395002973c827b3ed67db77e6ec09f092919a587022174554096a269378fb13", size = 5239528, upload-time = "2026-05-18T19:19:43.657Z" },
+    { url = "https://files.pythonhosted.org/packages/62/bb/37fb3f0dff146bdcfa78eec47879273820b2a0bf350ec236ce14bd0b1c26/lxml-6.1.1-cp314-cp314-manylinux_2_28_i686.whl", hash = "sha256:73bc2086f141224ebddb7fc5c6a36ca58b31b94b561e1dfe8e073e3270fad1e7", size = 5350730, upload-time = "2026-05-18T19:19:46.307Z" },
+    { url = "https://files.pythonhosted.org/packages/90/42/43253f168388df4fae1f38c01df36ddb9bee39e2048167b54cdcbae85ea3/lxml-6.1.1-cp314-cp314-manylinux_2_31_armv7l.whl", hash = "sha256:3779def59032b81e44a5f70096ef6bf2082f8d901937dca354474ba09782e245", size = 4697530, upload-time = "2026-05-18T19:19:49.889Z" },
+    { url = "https://files.pythonhosted.org/packages/eb/a8/c5a8504f81bbdfc8e7094c2c850cdb4ed6777fc4d5ddd9e5ab819f3b0d54/lxml-6.1.1-cp314-cp314-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:86c89b9d55ebf820ad7c90bc533410f0d098054f293351f10603c0c46ff598f5", size = 5250670, upload-time = "2026-05-18T19:19:53.199Z" },
+    { url = "https://files.pythonhosted.org/packages/77/b7/c7e76ab18744d75e21f320ebf9ff9d1ceae2b54dd431ea5a64caf26c9672/lxml-6.1.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:19607c6bbff2a44cf3fe8250abccd20942d3462473e0a721d01d379ed017e462", size = 5084485, upload-time = "2026-05-18T19:19:08.422Z" },
+    { url = "https://files.pythonhosted.org/packages/31/31/b35c53f8ef7b7c31cacd23d3638652fff7bcd1deb6eedb709ab43b685908/lxml-6.1.1-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:c6ed5141a5c7507cf3ee76bd363b0d6f801e3321adc35b5d825a23115faa5465", size = 4737635, upload-time = "2026-05-18T19:19:12.321Z" },
+    { url = "https://files.pythonhosted.org/packages/d9/06/31f23c813a7fe8e0cb1b175e915b08c9bf4e86d225b210feadbdbe519667/lxml-6.1.1-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:62aeb7e85b5d60320b9d77eef2e773994e2c0ce10121b277e0a19804e1654a5a", size = 5670681, upload-time = "2026-05-18T19:19:15.001Z" },
+    { url = "https://files.pythonhosted.org/packages/1a/bc/ce619bccc89b1fd9ad8a8e1330ee3f3beff9f2ff95b712d7bbcdd6e22fc3/lxml-6.1.1-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:b1b963fd8f5caa68e99dfae060d54de1fe9cba899b8718b44a00cdca53c3e590", size = 5238229, upload-time = "2026-05-18T19:19:18.131Z" },
+    { url = "https://files.pythonhosted.org/packages/2f/5d/b329acbbedc0b619ebc2be6cf7ee9ed07e80892c88d4dfd612c33805789a/lxml-6.1.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:63876be28efefa04a1df615b46770e82042cce445cfdce55160522f57b231ccb", size = 5264191, upload-time = "2026-05-18T19:19:21.118Z" },
+    { url = "https://files.pythonhosted.org/packages/d6/85/be36fb1425b30db3c3f9df75fe86343ebffb79e6320bd7f588e25bfeac39/lxml-6.1.1-cp314-cp314-win32.whl", hash = "sha256:7f7a92e8583f06b1fd49d01158143b8461cfcd135dcb10ec807270a3051bd603", size = 3657202, upload-time = "2026-05-18T19:17:39.509Z" },
+    { url = "https://files.pythonhosted.org/packages/b8/ce/3cf9a827342269f54d405a6202397de63f07c69cbd6ce7d183a3f0cba1e9/lxml-6.1.1-cp314-cp314-win_amd64.whl", hash = "sha256:b2d444f2e66624d68e9c6b211e28a76e22fff5fcabcfff4deac18b529b7d4137", size = 4064497, upload-time = "2026-05-18T19:18:14.662Z" },
+    { url = "https://files.pythonhosted.org/packages/d9/3e/1a957bde8f0760039e627f94699f82caa782c9d838d86c3d28245ee67212/lxml-6.1.1-cp314-cp314-win_arm64.whl", hash = "sha256:3fd9728a2735fda14f4e8235830c86b539e9661e849665bf926d3f867943b4bf", size = 3741991, upload-time = "2026-05-19T19:22:59.111Z" },
+    { url = "https://files.pythonhosted.org/packages/78/b2/00ed55b3a2efa4658fb795c38d1090ec9b3e8a6c3683d4441fa517f09c3b/lxml-6.1.1-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:787b2496d0dbe8cd180984e8d29e3a6f76e7ea34db781cb3bd55e4ba1ef8b4ee", size = 8827545, upload-time = "2026-05-18T19:18:41.193Z" },
+    { url = "https://files.pythonhosted.org/packages/c0/73/74573db19baa618d5f266f2407898b087ff6927115b00b71e5fc1b700847/lxml-6.1.1-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:2c8daa471358dc2d6fcf02165e80ec68f77871a286df95bc5cc3816153b0fd2c", size = 4735736, upload-time = "2026-05-18T19:18:46.761Z" },
+    { url = "https://files.pythonhosted.org/packages/16/02/6f7061f4f95f51e545d48e87647c54791d204a4e881be4156e7a26ba5338/lxml-6.1.1-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:acd7d70b64c0aae0c7922cca83d288a16f5f6da523637697872253415269baef", size = 4970291, upload-time = "2026-05-18T19:19:56.215Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/02/55fc057d8283427dea7d6edb102e7a840239c77a64a983d92f62a304c0e9/lxml-6.1.1-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:4f0dd2f01f9f8a89f565d000e03abcf0a13d692a346c8d22f628d49af098777a", size = 5102822, upload-time = "2026-05-18T19:19:59.223Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/48/8e1cf78d89d66850121d9255a2a24414c98f775da93b90cf976956c24b14/lxml-6.1.1-cp314-cp314t-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0b7e8a14c8634bf6f7a568634cb395305a6d964aeb5b7ee32248094bed3a7e2c", size = 5027923, upload-time = "2026-05-18T19:20:01.549Z" },
+    { url = "https://files.pythonhosted.org/packages/ed/00/0632a0647612c8af24d26997b3b961397daa9d5b2581444805933629a4cb/lxml-6.1.1-cp314-cp314t-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:86281fbdd6a8162756f8d603f37e3435bfa38043adb79c6dc6a2dfee065e7525", size = 5595843, upload-time = "2026-05-18T19:20:03.93Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/86/ab008a7dc360711b66858d61c80a5979a70a09f2aa2b05d9698df80b803d/lxml-6.1.1-cp314-cp314t-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c5d7152ec39ca7c402d8fb9bad86140a15b9503bd0c54484e3f1bbe3dd37ceca", size = 5224515, upload-time = "2026-05-18T19:20:06.381Z" },
+    { url = "https://files.pythonhosted.org/packages/75/c6/2702ff375e728e34f56d9a45339a9cf7e4427e917f542225242d63a05afa/lxml-6.1.1-cp314-cp314t-manylinux_2_28_i686.whl", hash = "sha256:88d8cb75b9d82858497a5393e3c63cfbf03035225e4b35a49ed7ccb151e4dc0e", size = 5312511, upload-time = "2026-05-18T19:20:09.308Z" },
+    { url = "https://files.pythonhosted.org/packages/b7/57/a5807c98f87a86f10ef9ffab35516df7c0f0c4b6d5d33e9f608ab9c04a31/lxml-6.1.1-cp314-cp314t-manylinux_2_31_armv7l.whl", hash = "sha256:f64ec5397ea6a41fc1b4af0380d79b44a755b5531dcaccd9940fb260dca93038", size = 4639206, upload-time = "2026-05-18T19:20:11.704Z" },
+    { url = "https://files.pythonhosted.org/packages/1f/e1/8a0a2c35734812395f4da4eaf33748a7e5705bfb2a58b128da764339d5ec/lxml-6.1.1-cp314-cp314t-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:d34bbf07dbc7ca5970671b1512e928991fb5e9d95365636c9b2d8b4f53af405e", size = 5232404, upload-time = "2026-05-18T19:20:14.064Z" },
+    { url = "https://files.pythonhosted.org/packages/c2/e2/0e6a4dd5ad84d01d99aa7bae7cfefd4a760a0e0f8176818241de17d9b6c0/lxml-6.1.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:17e0e18d4ad8adbd0399291bc44845b69d9dd68439a3cdebdf35ff902ec05072", size = 5083769, upload-time = "2026-05-18T19:19:23.758Z" },
+    { url = "https://files.pythonhosted.org/packages/a0/7e/161f33d463f6ffc1c7679104b65086dea120080d49dde4d238f015aaee2f/lxml-6.1.1-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:3ab541146f1f6968c462d6c2ac495148e8cdba2f8347700b2141b6ec5a75bf52", size = 4758936, upload-time = "2026-05-18T19:19:27.256Z" },
+    { url = "https://files.pythonhosted.org/packages/f1/fb/2369825e3f6ca99305bf9f7b7085fda91c8b0922a89e54d900974aa3ef85/lxml-6.1.1-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:2a0217714657e023ef4293500f65aa20fce6164c8fd6b08fa5bd4a859fb14b9b", size = 5620296, upload-time = "2026-05-18T19:19:29.993Z" },
+    { url = "https://files.pythonhosted.org/packages/30/90/d61e383146f74c5ab683947ea14dc7b82778838ab9b95ea73a23b60d0191/lxml-6.1.1-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:05a82eb6e1530a64f26225b55cbd178113bd0b5af1c2b625f25e5296742c26d2", size = 5228598, upload-time = "2026-05-18T19:19:33.523Z" },
+    { url = "https://files.pythonhosted.org/packages/76/2d/2dafd8149e94b05bb070690efd5bb2680720681e03ff03fc57d2b70a1105/lxml-6.1.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:9e36f163528fc50cbef305f02a5fd66d404edf7049cdaff211dbc2cba5a7013e", size = 5247845, upload-time = "2026-05-18T19:19:36.649Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/68/b30e913340c380ddac9580c6e6230991fc37240ec4f64704833e4f3e2769/lxml-6.1.1-cp314-cp314t-win32.whl", hash = "sha256:649dda677cf3bd6ac9ae14007ba0c824ded8ce5808b53fc7431d9140399118c1", size = 3897345, upload-time = "2026-05-18T19:17:33.562Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/4e/9eb2af5335545f9fbcd7af57bcf87c6025d31eaa31b14ec184a6c8675328/lxml-6.1.1-cp314-cp314t-win_amd64.whl", hash = "sha256:793033d6c5cdf33a573f910d9bea14ef8f5771820411d118da8e1182edb53d5e", size = 4393350, upload-time = "2026-05-18T19:18:10.076Z" },
+    { url = "https://files.pythonhosted.org/packages/7f/2c/0f1e93c636720e8a3eb59af2bfda99d98b55891e1c53bc30c2e0e865f01b/lxml-6.1.1-cp314-cp314t-win_arm64.whl", hash = "sha256:58bb955caba94e467d2a96da17660d2d704e0675894cba21ab8a775b8621fd1c", size = 3817223, upload-time = "2026-05-19T19:22:56.823Z" },
+]
+
+[package.optional-dependencies]
+html-clean = [
+    { name = "lxml-html-clean" },
+]
+
+[[package]]
+name = "lxml-html-clean"
+version = "0.4.5"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "lxml" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/0a/63/195dfdde380a84df309e3bccf4384b034b745dba43426886f7ae623b4fba/lxml_html_clean-0.4.5.tar.gz", hash = "sha256:e2a4c7d5beedd17cd7b484d848a0571e54baa239a4f9df5546e3acba7f990560", size = 24142, upload-time = "2026-05-20T12:17:53.574Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/6a/bd/6e2b76a6c5dee10397db9c929f0c5066766ec1036046f0335b7ca7ca08b8/lxml_html_clean-0.4.5-py3-none-any.whl", hash = "sha256:c76fcadd1e5bfb9b8bafc2200d51e4e78eb0dad67f56881c21dfb6484c7e7746", size = 14573, upload-time = "2026-05-20T12:17:52.215Z" },
+]
+
 [[package]]
 name = "mako"
 version = "1.3.12"
@@ -1139,6 +1302,7 @@ dependencies = [
     { name = "python-dotenv" },
     { name = "sqlalchemy" },
     { name = "sse-starlette" },
+    { name = "trafilatura" },
     { name = "uvicorn" },
 ]
 
@@ -1174,6 +1338,7 @@ requires-dist = [
     { name = "python-dotenv", specifier = ">=1.0.0" },
     { name = "sqlalchemy", specifier = ">=2.0.0" },
     { name = "sse-starlette", specifier = ">=2.1.0" },
+    { name = "trafilatura", specifier = ">=2.1.0" },
     { name = "uvicorn", specifier = ">=0.30.0" },
 ]
 provides-extras = ["dev"]
@@ -1477,6 +1642,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/0b/d7/1959b9648791274998a9c3526f6d0ec8fd2233e4d4acce81bbae76b44b2a/python_dotenv-1.2.2-py3-none-any.whl", hash = "sha256:1d8214789a24de455a8b8bd8ae6fe3c6b69a5e3d64aa8a8e5d68e694bbcb285a", size = 22101, upload-time = "2026-03-01T16:00:25.09Z" },
 ]
 
+[[package]]
+name = "pytz"
+version = "2026.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/ff/46/dd499ec9038423421951e4fad73051febaa13d2df82b4064f87af8b8c0c3/pytz-2026.2.tar.gz", hash = "sha256:0e60b47b29f21574376f218fe21abc009894a2321ea16c6754f3cad6eb7cdd6a", size = 320861, upload-time = "2026-05-04T01:35:29.667Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ec/dd/96da98f892250475bdf2328112d7468abdd4acc7b902b6af23f4ed958ea0/pytz-2026.2-py2.py3-none-any.whl", hash = "sha256:04156e608bee23d3792fd45c94ae47fae1036688e75032eea2e3bf0323d1f126", size = 510141, upload-time = "2026-05-04T01:35:27.408Z" },
+]
+
 [[package]]
 name = "pyyaml"
 version = "6.0.3"
@@ -1941,6 +2115,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/16/5b/f2aa703a4fc5d2dff73460a7d46cc2f3f44aa0f3dd8eeb20d2a0ecf68862/tiktoken-0.13.0-cp314-cp314t-win_amd64.whl", hash = "sha256:85b78cc3a2c3d48723ca751fa981f1fedccd54194ca0471b957364353a898b07", size = 918110, upload-time = "2026-05-15T04:51:17.237Z" },
 ]
 
+[[package]]
+name = "tld"
+version = "0.13.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/5c/5d/76b4383ac4e5b5e254e50c09807b3e13820bed6d6c11cd540264988d6802/tld-0.13.2.tar.gz", hash = "sha256:d983fa92b9d717400742fca844e29d5e18271079c7bcfabf66d01b39b4a14345", size = 467175, upload-time = "2026-03-06T23:50:34.498Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/9e/90/39a85a4b63c84213e78b3c17d22e1bf45328acf8ebb33ef93be30d0a3911/tld-0.13.2-py2.py3-none-any.whl", hash = "sha256:9b8fdbdb880e7ba65b216a4937f2c94c49a7226723783d5838fc958ac76f4e0c", size = 296743, upload-time = "2026-03-06T23:50:32.465Z" },
+]
+
 [[package]]
 name = "tokenizers"
 version = "0.23.1"
@@ -1980,6 +2163,24 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/16/e1/3079a9ff9b8e11b846c6ac5c8b5bfb7ff225eee721825310c91b3b50304f/tqdm-4.67.3-py3-none-any.whl", hash = "sha256:ee1e4c0e59148062281c49d80b25b67771a127c85fc9676d3be5f243206826bf", size = 78374, upload-time = "2026-02-03T17:35:50.982Z" },
 ]
 
+[[package]]
+name = "trafilatura"
+version = "2.1.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "certifi" },
+    { name = "charset-normalizer" },
+    { name = "courlan" },
+    { name = "htmldate" },
+    { name = "justext" },
+    { name = "lxml" },
+    { name = "urllib3" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/e8/19/24833e905df2d80e3bb67424f95febcc17709a1f61a522120bc438afca70/trafilatura-2.1.0.tar.gz", hash = "sha256:f689e2116fc89c7bc0b9a296d01dcfe2eb0b5455f8c371a77dc0db1f06a05643", size = 263876, upload-time = "2026-06-07T17:43:31.829Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0e/78/4ad99d79aee2784f49f20fd0a29058ce4c032fe4439047924c43521cd211/trafilatura-2.1.0-py3-none-any.whl", hash = "sha256:0eded5207a806445ddebbe36eae30b9035fe6a2f233c36f6fe82663fca8b9d30", size = 134600, upload-time = "2026-06-07T17:43:28.404Z" },
+]
+
 [[package]]
 name = "typer"
 version = "0.25.1"