Fix #43: 建议添加音频下载

Signed-off-by: Mr-Neutr0n <64578610+Mr-Neutr0n@users.noreply.github.com>

src/tchmaterial_parser/api.py

@@ -85,6 +85,33 @@ def parse(url: str, bookmarks: bool) -> list[tuple[str, str, str, list[dict]]] |
         data: dict = response.json()
 
         # 3. 获取资源标题、下载链接及章节目录
+        def get_audio_info(audio_data: dict, root_title: str | None = None) -> tuple[str, str, str, list[dict]] | None: # 解析教材关联的音频资源（如英语教材听力）
+            # 音频资源的标题存放在 global_title 字典中（键为语言代码，如 zh-CN）
+            title_data = audio_data.get("global_title")
+            audio_title = title_data.get("zh-CN") or title_data.get("en") if isinstance(title_data, dict) else title_data or audio_data.get("title") or audio_data.get("id")
+            title: str = f"{root_title} - {audio_title}" if root_title else audio_title
+            resource_url: str | None = None
+            resource_format = "mp3"
+
+            # 优先选择转码后的 MP3 文件（ti_file_flag 为 href），否则回退到源文件
+            for item in audio_data["ti_items"]:
+                if item.get("ti_file_flag") not in ("href", "source") or item.get("ti_format") != "mp3":
+                    continue
+
+                resource_url = item.get("ti_storage") # 获取并构造资源的 URL
+                if resource_url:
+                    resource_url = resource_url.replace("cs_path:${ref-path}", "https://r1-ndr-private.ykt.cbern.com.cn")
+                else:
+                    resource_url = next((url for url in item.get("ti_storages") or [] if url), None)
+                if resource_url:
+                    resource_format = item.get("ti_format") or "mp3"
+                    break
+
+            if not resource_url:
+                return None
+
+            return title, resource_url, resource_format, []
+
         def get_resource_info(resource_data: dict, root_title: str | None = None) -> tuple[str, str, str, list[dict]] | None:
             title: str = f"{root_title} - {resource_data.get('title') or resource_data.get('id')}" if root_title else resource_data.get("title") or resource_data.get("id")
             resource_url: str | None = None
@@ -221,6 +248,17 @@ def parse(url: str, bookmarks: bool) -> list[tuple[str, str, str, list[dict]]] |
             if resource_info:
                 resources_info.append(resource_info)
 
+            if content_type == "assets_document": # 教材可能带有配套的音频资源（如英语教材听力）
+                try:
+                    audios_resp = session.get(f"https://s-file-1.ykt.cbern.com.cn/zxx/ndrs/resources/{content_id}/relation_audios.json")
+                    audios_data: list[dict] = audios_resp.json()
+                    for audio in audios_data:
+                        audio_info = get_audio_info(audio, data.get("title"))
+                        if audio_info:
+                            resources_info.append(audio_info)
+                except Exception: # 音频资源不是必需的，获取失败时直接跳过
+                    pass
+
         return resources_info
 
     except Exception as e:

tests/test_audio_parse.py

@@ -0,0 +1,110 @@
+import unittest
+
+from src.tchmaterial_parser import api
+
+
+class FakeResponse:
+    def __init__(self, json_data: object) -> None:
+        self._json = json_data
+
+    def json(self) -> object:
+        return self._json
+
+
+class FakeSession:
+    def __init__(self, details: dict, audios: list[dict]) -> None:
+        self.details = details
+        self.audios = audios
+
+    def get(self, url: str, *args: tuple, **kwargs: dict) -> FakeResponse:
+        if "relation_audios.json" in url:
+            return FakeResponse(self.audios)
+        return FakeResponse(self.details)
+
+
+DETAILS = {
+    "id": "book-1",
+    "title": "英语七年级上册",
+    "ti_items": [
+        {
+            "ti_is_source_file": True,
+            "ti_format": "pdf",
+            "ti_storage": "cs_path:${ref-path}/edu_product/esp/assets/book-1.pkg/英语七年级上册.pdf",
+        },
+    ],
+}
+
+AUDIOS = [
+    {
+        "id": "audio-1",
+        "global_title": {"zh-CN": "1 Starter Section 2 Activity 2"},
+        "ti_items": [
+            {
+                "ti_file_flag": "href",
+                "ti_format": "mp3",
+                "ti_storage": "cs_path:${ref-path}/edu_product/esp/assets/audio-1.t/1.mp3",
+            },
+            {
+                "ti_file_flag": "source",
+                "ti_format": "wav",
+                "ti_storage": "cs_path:${ref-path}/edu_product/esp/assets/audio-1.t/1.wav",
+            },
+        ],
+    },
+    {
+        "id": "audio-2",
+        "global_title": {"zh-CN": "2 Starter Section 3 Activity 1"},
+        "ti_items": [
+            {
+                "ti_file_flag": "href",
+                "ti_format": "mp3",
+                "ti_storage": "cs_path:${ref-path}/edu_product/esp/assets/audio-2.t/2.mp3",
+            },
+        ],
+    },
+]
+
+
+class AudioParseTest(unittest.TestCase):
+    def setUp(self) -> None:
+        self.addCleanup(setattr, api, "session", api.session)
+
+    def parse_book(self) -> list[tuple[str, str, str, list[dict]]] | None:
+        api.session = FakeSession(DETAILS, AUDIOS)
+        url = "https://basic.smartedu.cn/tchMaterial/detail?contentType=assets_document&contentId=book-1&catalogType=tchMaterial&subCatalog=tchMaterial"
+        return api.parse(url, False)
+
+    def test_textbook_with_audio_returns_pdf_and_mp3s(self) -> None:
+        results = self.parse_book()
+        self.assertIsNotNone(results)
+        self.assertEqual(len(results), 3)
+        self.assertEqual(results[0][2], "pdf")
+        self.assertEqual(results[1][1], "https://r1-ndr-private.ykt.cbern.com.cn/edu_product/esp/assets/audio-1.t/1.mp3")
+        self.assertEqual(results[1][2], "mp3")
+        self.assertEqual(results[1][0], "英语七年级上册 - 1 Starter Section 2 Activity 2")
+        self.assertEqual(results[2][0], "英语七年级上册 - 2 Starter Section 3 Activity 1")
+
+    def test_textbook_without_audio_returns_only_pdf(self) -> None:
+        api.session = FakeSession(DETAILS, [])
+        url = "https://basic.smartedu.cn/tchMaterial/detail?contentType=assets_document&contentId=book-1&catalogType=tchMaterial&subCatalog=tchMaterial"
+        results = api.parse(url, False)
+        self.assertIsNotNone(results)
+        self.assertEqual(len(results), 1)
+        self.assertEqual(results[0][2], "pdf")
+
+    def test_audio_fetch_failure_is_ignored(self) -> None:
+        class FailingAudiosSession(FakeSession):
+            def get(self, url: str, *args: tuple, **kwargs: dict) -> FakeResponse:
+                if "relation_audios.json" in url:
+                    raise RuntimeError("network error")
+                return super().get(url, *args, **kwargs)
+
+        api.session = FailingAudiosSession(DETAILS, [])
+        url = "https://basic.smartedu.cn/tchMaterial/detail?contentType=assets_document&contentId=book-1&catalogType=tchMaterial&subCatalog=tchMaterial"
+        results = api.parse(url, False)
+        self.assertIsNotNone(results)
+        self.assertEqual(len(results), 1)
+
+
+if __name__ == "__main__":
+    unittest.main()