parsehub 2.0.34__tar.gz → 2.0.35__tar.gz

{parsehub-2.0.34/src/parsehub.egg-info → parsehub-2.0.35}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.0.34
+Version: 2.0.35
 Summary: 轻量、异步、开箱即用的社交媒体聚合解析库
 Author-email: 梓澪 <zilingmio@gmail.com>
 License: MIT

{parsehub-2.0.34 → parsehub-2.0.35}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "parsehub"
-version = "2.0.34"
+version = "2.0.35"
 description = "轻量、异步、开箱即用的社交媒体聚合解析库"
 readme = "README.md"
 requires-python = ">=3.12.0"

{parsehub-2.0.34 → parsehub-2.0.35}/src/parsehub/parsers/parser/instagram.py

@@ -9,7 +9,7 @@ from ..base.base import BaseParser
 class InstagramParser(BaseParser):
     __platform__ = Platform.INSTAGRAM
     __supported_type__ = ["视频", "图文"]
-    __match__ = r"^(http(s)?://)(www\.|)instagram\.com/(p|reel|share|.*/p|.*/reel)/.*"
+    __match__ = r"^(http(s)?://)(www\.|)instagram\.com/(p|reels|share|.*/p)/.*"
     __redirect_keywords__ = ["share"]
 
     async def _do_parse(self, raw_url: str) -> VideoParseResult | ImageParseResult | MultimediaParseResult:
@@ -67,12 +67,12 @@ class InstagramParser(BaseParser):
                 text = f"Instagram 账号可能已被封禁\n\n使用的Cookie: {cookie}"
             else:
                 text = str(e)
-            raise ParseError(f"无法获取帖子内容: {text}") from e
+            raise ParseError(f"无法获取帖子内容(可能为私人内容): {text}") from e
 
     @staticmethod
     def get_short_code(url: str) -> str | None:
         url = url.removesuffix("/")
-        shortcode = re.search(r"/(share|p|reel|.*/p|.*/reel)/(.*)", url)
+        shortcode = re.search(r"/(share|p|reels|.*/p)/(.*)", url)
         return shortcode.group(2).split("/")[0] if shortcode else None
 
 

{parsehub-2.0.34 → parsehub-2.0.35}/src/parsehub/provider_api/xhs.py

@@ -122,14 +122,14 @@ class XHSAPI:
 
     @staticmethod
     def get_trace_id(img_url: str) -> str:
-        trace_id = img_url.split("/")[-1].split("!")[0]
-        if "spectrum" in img_url:
-            return "spectrum/" + trace_id
-        if "note_pre_post_uhdr" in img_url:
-            return "note_pre_post_uhdr/" + trace_id
-        if "notes_pre_post" in img_url:
-            return "notes_pre_post/" + trace_id
-        return trace_id
+        match = re.search(r"/(spectrum|note_pre_post_uhdr|notes_pre_post|notes_uhdr)/([^/!]+)(?:!.*)?$", img_url)
+        if match:
+            return f"{match.group(1)}/{match.group(2)}"
+
+        match = re.search(r"/([^/!]+)(?:!.*)?$", img_url)
+        if match:
+            return match.group(1)
+        return img_url
 
     def get_raw_image_url(self, ime_url: str) -> str:
         """拼接无水印图片链接"""

{parsehub-2.0.34 → parsehub-2.0.35/src/parsehub.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.0.34
+Version: 2.0.35
 Summary: 轻量、异步、开箱即用的社交媒体聚合解析库
 Author-email: 梓澪 <zilingmio@gmail.com>
 License: MIT

{parsehub-2.0.34 → parsehub-2.0.35}/src/parsehub.egg-info/SOURCES.txt

@@ -65,4 +65,5 @@ src/parsehub/utils/helpers.py
 src/parsehub/utils/media_info.py
 test/test_cli.py
 test/test_cli_config.py
-test/test_core_offline.py
+test/test_core_offline.py
+test/test_downloader.py

{parsehub-2.0.34 → parsehub-2.0.35}/test/test_core_offline.py

@@ -238,6 +238,7 @@ class TestPlatformUrlMatching(unittest.TestCase):
                 "https://www.instagram.com/share/BAexample/",
                 "https://www.instagram.com/user.name/p/C0example/",
                 "https://www.instagram.com/user.name/reel/C0example/",
+                "https://www.instagram.com/reels/DaGI8bPS3ed/",
             ],
             Platform.KUAISHOU: [
                 "https://www.kuaishou.com/short-video/3xexample",

parsehub-2.0.35/test/test_downloader.py

@@ -0,0 +1,161 @@
+import contextlib
+import threading
+import unittest
+from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
+from pathlib import Path
+from tempfile import TemporaryDirectory
+from typing import ClassVar
+
+from parsehub.errors import DownloadError
+from parsehub.utils.downloader import download
+
+
+class RangeTestHandler(BaseHTTPRequestHandler):
+    content: ClassVar[bytes] = b""
+    support_range: ClassVar[bool] = True
+    fail_all: ClassVar[bool] = False
+    requests: ClassVar[list[tuple[str, str | None]]] = []
+
+    def log_message(self, format: str, *args: object) -> None:
+        return
+
+    def do_HEAD(self) -> None:
+        self.__class__.requests.append(("HEAD", self.headers.get("Range")))
+        if self.fail_all:
+            self.send_response(500)
+            self.end_headers()
+            return
+
+        self.send_response(200)
+        self.send_header("Content-Length", str(len(self.content)))
+        self.send_header("Accept-Ranges", "bytes" if self.support_range else "none")
+        self.end_headers()
+
+    def do_GET(self) -> None:
+        range_header = self.headers.get("Range")
+        self.__class__.requests.append(("GET", range_header))
+        if self.fail_all:
+            self.send_response(500)
+            self.end_headers()
+            return
+
+        if range_header and self.support_range:
+            start, end = self._parse_range(range_header)
+            if start >= len(self.content):
+                self.send_response(416)
+                self.send_header("Content-Range", f"bytes */{len(self.content)}")
+                self.end_headers()
+                return
+
+            end = min(end, len(self.content) - 1)
+            body = self.content[start : end + 1]
+            self.send_response(206)
+            self.send_header("Content-Length", str(len(body)))
+            self.send_header("Content-Range", f"bytes {start}-{end}/{len(self.content)}")
+            self.send_header("Accept-Ranges", "bytes")
+            self.end_headers()
+            self.wfile.write(body)
+            return
+
+        self.send_response(200)
+        self.send_header("Content-Length", str(len(self.content)))
+        self.send_header("Accept-Ranges", "none")
+        self.end_headers()
+        self.wfile.write(self.content)
+
+    @staticmethod
+    def _parse_range(header: str) -> tuple[int, int]:
+        prefix = "bytes="
+        if not header.startswith(prefix):
+            return 0, 0
+        start_text, end_text = header.removeprefix(prefix).split("-", 1)
+        return int(start_text), int(end_text)
+
+
+@contextlib.contextmanager
+def range_server(*, content: bytes, support_range: bool = True, fail_all: bool = False):
+    class Handler(RangeTestHandler):
+        pass
+
+    Handler.content = content
+    Handler.support_range = support_range
+    Handler.fail_all = fail_all
+    Handler.requests = []
+
+    server = ThreadingHTTPServer(("127.0.0.1", 0), Handler)
+    thread = threading.Thread(target=server.serve_forever, daemon=True)
+    thread.start()
+    try:
+        yield f"http://127.0.0.1:{server.server_port}/file.bin", Handler
+    finally:
+        server.shutdown()
+        server.server_close()
+        thread.join(timeout=5)
+
+
+class DownloaderTest(unittest.IsolatedAsyncioTestCase):
+    async def test_download_uses_range_parts_when_server_supports_range(self):
+        content = bytes(range(251)) * 20
+        progresses: list[tuple[int, int]] = []
+
+        async def progress(current: int, total: int) -> None:
+            progresses.append((current, total))
+
+        with TemporaryDirectory() as tmp, range_server(content=content, support_range=True) as (url, handler):
+            target = Path(tmp) / "video.bin"
+
+            path = await download(
+                url,
+                target,
+                progress=progress,
+                connections=4,
+                min_split_size=512,
+                chunk_size=128,
+            )
+
+            self.assertEqual(Path(path), target)
+            self.assertEqual(target.read_bytes(), content)
+            self.assertEqual(progresses[-1], (len(content), len(content)))
+            range_gets = [range_header for method, range_header in handler.requests if method == "GET" and range_header]
+            self.assertGreaterEqual(len(range_gets), 2)
+            self.assertFalse(list(Path(tmp).glob(".*.parsehub-tmp")))
+
+    async def test_download_falls_back_to_single_request_when_range_is_ignored(self):
+        content = b"fallback-body" * 100
+
+        with TemporaryDirectory() as tmp, range_server(content=content, support_range=False) as (url, handler):
+            target = Path(tmp) / "image.bin"
+
+            await download(url, target, connections=4, min_split_size=10, chunk_size=32)
+
+            self.assertEqual(target.read_bytes(), content)
+            self.assertIn(("GET", "bytes=0-0"), handler.requests)
+            self.assertIn(("GET", None), handler.requests)
+            self.assertFalse(list(Path(tmp).glob(".*.parsehub-tmp")))
+
+    async def test_download_keeps_existing_file_when_request_fails(self):
+        with TemporaryDirectory() as tmp, range_server(content=b"new", support_range=True, fail_all=True) as (url, _):
+            target = Path(tmp) / "video.bin"
+            target.write_bytes(b"old")
+
+            with self.assertRaises(DownloadError):
+                await download(url, target, connections=4, max_retries=0)
+
+            self.assertEqual(target.read_bytes(), b"old")
+            self.assertFalse(list(Path(tmp).glob(".*.parsehub-tmp")))
+
+    async def test_connections_one_uses_single_request(self):
+        content = b"single" * 200
+
+        with TemporaryDirectory() as tmp, range_server(content=content, support_range=True) as (url, handler):
+            target = Path(tmp) / "single.bin"
+
+            await download(url, target, connections=1, min_split_size=10)
+
+            self.assertEqual(target.read_bytes(), content)
+            range_gets = [range_header for method, range_header in handler.requests if method == "GET" and range_header]
+            self.assertEqual(range_gets, [])
+
+
+if __name__ == "__main__":
+    unittest.main()