article-backup 0.3.12__tar.gz → 0.3.13__tar.gz

{article_backup-0.3.12 → article_backup-0.3.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: article-backup
-Version: 0.3.12
+Version: 0.3.13
 Summary: Локальный бэкап статей с Sponsr.ru и Boosty.to в Markdown с Hugo-интеграцией
 Author-email: Eugene Chaykin <eugene@chayk.in>
 License: Apache-2.0

{article_backup-0.3.12 → article_backup-0.3.13}/article_backup.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: article-backup
-Version: 0.3.12
+Version: 0.3.13
 Summary: Локальный бэкап статей с Sponsr.ru и Boosty.to в Markdown с Hugo-интеграцией
 Author-email: Eugene Chaykin <eugene@chayk.in>
 License: Apache-2.0

{article_backup-0.3.12 → article_backup-0.3.13}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "article-backup"
-version = "0.3.12"
+version = "0.3.13"
 description = "Локальный бэкап статей с Sponsr.ru и Boosty.to в Markdown с Hugo-интеграцией"
 readme = "README.md"
 license = {text = "Apache-2.0"}

{article_backup-0.3.12 → article_backup-0.3.13}/src/boosty.py

@@ -3,6 +3,7 @@
 
 import json
 from datetime import datetime, timezone
+from urllib.parse import parse_qsl, urlencode, urlparse
 
 import requests
 
@@ -158,7 +159,7 @@ class BoostyDownloader(BaseDownloader):
         content_blocks = raw_data.get("data", [])
 
         # Извлекаем assets
-        assets = self._extract_assets(content_blocks)
+        assets = self._extract_assets(content_blocks, raw_data.get("signedQuery", ""))
 
         return Post(
             post_id=post_id,
@@ -170,7 +171,7 @@ class BoostyDownloader(BaseDownloader):
             assets=assets,
         )
 
-    def _extract_assets(self, blocks: list[dict]) -> list[dict]:
+    def _extract_assets(self, blocks: list[dict], signed_query: str = "") -> list[dict]:
         """Извлекает URL медиафайлов из блоков контента."""
         assets = []
 
@@ -190,6 +191,16 @@ class BoostyDownloader(BaseDownloader):
                 if url:
                     assets.append({
                         "url": url,
+                        "download_url": self._sign_media_url(url, signed_query),
+                        "alt": block.get("title", block.get("id", "")),
+                    })
+
+            elif block_type == "file":
+                url = block.get("url", "")
+                if url:
+                    assets.append({
+                        "url": url,
+                        "download_url": self._sign_media_url(url, signed_query),
                         "alt": block.get("title", block.get("id", "")),
                     })
 
@@ -244,7 +255,7 @@ class BoostyDownloader(BaseDownloader):
                 continue
 
             # Block-level элементы разрывают параграф
-            if block_type in ("image", "audio_file", "ok_video"):
+            if block_type in ("image", "audio_file", "file", "ok_video"):
                 if current_paragraph:
                     lines.append("".join(current_paragraph))
                     current_paragraph = []
@@ -293,6 +304,15 @@ class BoostyDownloader(BaseDownloader):
             elif url:
                 return f"\n🎵 **{title}**: [слушать]({url})\n"
 
+        elif block_type == "file":
+            url = block.get("url", "")
+            title = block.get("title") or block.get("id") or "file"
+            local = asset_map.get(url)
+            if local:
+                return f"\n📎 [{title}](assets/{local})\n"
+            elif url:
+                return f"\n📎 [{title}]({url})\n"
+
         elif block_type == "ok_video":
             # Определяем ссылку на видео (приоритет: локальный файл > ok.ru/video > videoembed)
             video_url = self._extract_ok_video_player_url(block)
@@ -322,6 +342,20 @@ class BoostyDownloader(BaseDownloader):
 
         return ""
 
+    def _sign_media_url(self, url: str, signed_query: str) -> str:
+        """Добавляет signedQuery Boosty к URL медиа, не перезаписывая существующие параметры."""
+        if not url or not signed_query:
+            return url
+
+        parsed = urlparse(url)
+        params = dict(parse_qsl(parsed.query, keep_blank_values=True))
+        query = signed_query[1:] if signed_query.startswith("?") else signed_query
+        for key, value in parse_qsl(query, keep_blank_values=True):
+            if key not in params:
+                params[key] = value
+
+        return parsed._replace(query=urlencode(params)).geturl()
+
     def _extract_ok_video_player_url(self, block: dict) -> str:
         """Выбирает лучший прямой URL видео из ok_video блока."""
         player_urls = block.get("playerUrls")

{article_backup-0.3.12 → article_backup-0.3.13}/src/downloader.py

@@ -318,6 +318,7 @@ class BaseDownloader(ABC):
 
         def download_one(asset: dict) -> tuple[str, str | None]:
             url = asset["url"]
+            request_url = asset.get("download_url", url)
             force = asset.get("force", False)
             try:
                 # Предварительная проверка (если расширение есть)
@@ -326,7 +327,7 @@ class BaseDownloader(ABC):
                     return url, None
 
                 def do_request():
-                    resp = self.session.get(url, stream=True, timeout=self.TIMEOUT)
+                    resp = self.session.get(request_url, stream=True, timeout=self.TIMEOUT)
                     resp.raise_for_status()
                     return resp
 

{article_backup-0.3.12 → article_backup-0.3.13}/tests/test_asset_dedup.py

@@ -143,6 +143,38 @@ class AssetDedupTests(unittest.TestCase):
             for fn in filenames:
                 self.assertTrue((assets_dir / fn).exists(), msg=f"missing file: {fn}")
 
+    def test_download_assets_uses_download_url_but_maps_original_url(self):
+        with tempfile.TemporaryDirectory() as tmp:
+            tmp_path = Path(tmp)
+            assets_dir = tmp_path / "assets"
+            assets_dir.mkdir(parents=True, exist_ok=True)
+
+            config = Config(output_dir=tmp_path, auth=Auth())
+            source = Source(platform="boosty", author="author", download_assets=True)
+            dl = _DummyDownloader(config, source, cast(Database, _DummyDB()))
+
+            requested_urls = []
+
+            def fake_get(url: str, stream: bool = True, timeout=None):
+                requested_urls.append(url)
+                return _FakeResponse("audio/mpeg", body=b"audio")
+
+            dl.session.get = fake_get  # type: ignore[method-assign]
+
+            asset_map = dl._download_assets(
+                [
+                    {
+                        "url": "https://cdn.boosty.to/audio/audio-id",
+                        "download_url": "https://cdn.boosty.to/audio/audio-id?sign=abc",
+                        "alt": "audio.mp3",
+                    }
+                ],
+                assets_dir,
+            )
+
+            self.assertEqual(requested_urls, ["https://cdn.boosty.to/audio/audio-id?sign=abc"])
+            self.assertIn("https://cdn.boosty.to/audio/audio-id", asset_map)
+
 
 if __name__ == "__main__":
     unittest.main()

{article_backup-0.3.12 → article_backup-0.3.13}/tests/test_boosty_normalize.py

@@ -143,5 +143,75 @@ class BoostyParagraphTests(unittest.TestCase):
         self.assertIn(')\n\nТекст после', md)
 
 
+class BoostySignedMediaTests(unittest.TestCase):
+    def setUp(self):
+        self.config = Config(output_dir=Path('/tmp/test'), auth=Auth())
+        self.source = Source(platform='boosty', author='test_author')
+        self.db = MagicMock(spec=Database)
+        with patch('src.boosty.load_cookie', return_value='fake'), \
+             patch('src.boosty.load_auth_header', return_value='Bearer fake'):
+            self.downloader = BoostyDownloader(self.config, self.source, self.db)
+
+    def test_parse_post_signs_audio_asset_with_signed_query(self):
+        raw = {
+            'id': 'post-id',
+            'title': 'Post',
+            'createdAt': 1735689600,
+            'signedQuery': '?sign=abc&expires=123',
+            'data': [
+                {
+                    'type': 'audio_file',
+                    'url': 'https://cdn.boosty.to/audio/audio-id',
+                    'title': 'Audio title.mp3',
+                }
+            ],
+        }
+
+        post = self.downloader._parse_post(raw)
+
+        self.assertEqual(post.assets[0]['url'], 'https://cdn.boosty.to/audio/audio-id')
+        self.assertEqual(
+            post.assets[0]['download_url'],
+            'https://cdn.boosty.to/audio/audio-id?sign=abc&expires=123',
+        )
+
+    def test_parse_post_signs_file_asset_with_signed_query(self):
+        raw = {
+            'id': 'post-id',
+            'title': 'Post',
+            'createdAt': 1735689600,
+            'signedQuery': 'sign=abc&expires=123',
+            'data': [
+                {
+                    'type': 'file',
+                    'url': 'https://cdn.boosty.to/file/file-id?name=doc.pdf',
+                    'title': 'doc.pdf',
+                }
+            ],
+        }
+
+        post = self.downloader._parse_post(raw)
+
+        self.assertEqual(post.assets[0]['url'], 'https://cdn.boosty.to/file/file-id?name=doc.pdf')
+        self.assertEqual(
+            post.assets[0]['download_url'],
+            'https://cdn.boosty.to/file/file-id?name=doc.pdf&sign=abc&expires=123',
+        )
+
+    def test_file_block_uses_local_asset_when_downloaded(self):
+        block = {
+            'type': 'file',
+            'url': 'https://cdn.boosty.to/file/file-id',
+            'title': 'doc.pdf',
+        }
+
+        md = self.downloader._block_to_markdown(
+            block,
+            {'https://cdn.boosty.to/file/file-id': 'doc.pdf'},
+        )
+
+        self.assertIn('[doc.pdf](assets/doc.pdf)', md)
+
+
 if __name__ == '__main__':
     unittest.main()