Merge pull request #178 from qaiu/copilot/implement-feishu-share-parser-java

feat: 支持飞书云盘分享解析

README.md

@@ -94,6 +94,7 @@ https://nfd-parser.github.io/nfd-preview/preview.html?src=https%3A%2F%2Flz.qaiu.
 - Onedrive-pod
 - Dropbox-pdp
 - iCloud-pic
+- [飞书云盘-fs](https://www.feishu.cn/)
 ### 专属版提供
 - [夸克云盘-qk](https://pan.quark.cn/)
 - [UC云盘-uc](https://fast.uc.cn/)
@@ -340,6 +341,7 @@ json返回数据格式示例:
 | WPS云文档      | √       | X        | 5G(免费)   | 10M(免费)/2G(会员)  |
 | 夸克网盘        | x       | √        | 10G       | 不限大小            | 
 | UC网盘        | x       | √        | 10G       | 不限大小            | 
+| 飞书云盘        | √       | X        | 15G       | 不限大小            |
 
 # 打包部署
 

parser/src/main/java/cn/qaiu/parser/PanDomainTemplate.java

@@ -313,6 +313,14 @@ public enum PanDomainTemplate {
             "https://pan.quark.cn/s/{shareKey}",
             QkTool.class),
 
+    // https://xxx.feishu.cn/file/VnCxbt35KoowKoxldO3c3C7VnMc
+    // https://xxx.feishu.cn/drive/folder/RQSKf8EQ4l7dMedqzHucpMbancg
+    FS("飞书云盘",
+            compile("https://[^.]+\\.feishu\\.cn/(?:file|drive/folder)/(?<KEY>[A-Za-z0-9_-]+)(\\?.*)?"),
+            "https://feishu.cn/file/{shareKey}",
+            "https://www.feishu.cn/",
+            FsTool.class),
+
     // =====================音乐类解析 分享链接标志->MxxS (单歌曲/普通音质)==========================
     // http://163cn.tv/xxx
     MNES("网易云音乐分享",

parser/src/main/java/cn/qaiu/parser/impl/FsTool.java

@@ -0,0 +1,437 @@
+package cn.qaiu.parser.impl;
+
+import cn.qaiu.entity.FileInfo;
+import cn.qaiu.entity.ShareLinkInfo;
+import cn.qaiu.parser.PanBase;
+import io.vertx.core.Future;
+import io.vertx.core.Promise;
+import io.vertx.core.json.JsonArray;
+import io.vertx.core.json.JsonObject;
+
+import java.net.URLDecoder;
+import java.nio.charset.StandardCharsets;
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+/**
+ * <a href="https://www.feishu.cn/">飞书云盘</a>
+ * <p>
+ * 支持飞书公开分享文件和文件夹的解析。
+ * <ul>
+ *     <li>文件链接: https://xxx.feishu.cn/file/{token}</li>
+ *     <li>文件夹链接: https://xxx.feishu.cn/drive/folder/{token}</li>
+ * </ul>
+ * 飞书下载需要先获取匿名会话Cookie，然后使用Cookie请求下载接口。
+ * </p>
+ */
+public class FsTool extends PanBase {
+
+    private static final String UA = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+            + "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36";
+
+    /**
+     * 飞书 obj_type: type=12 表示上传文件可下载
+     */
+    private static final int OBJ_TYPE_FILE = 12;
+
+    /**
+     * v3 列表 API 支持的 obj_type
+     */
+    private static final int[] LIST_OBJ_TYPES = {
+            0, 2, 22, 44, 3, 30, 8, 11, 12, 84, 123, 124
+    };
+
+    /** 每页返回条目数 */
+    private static final int PAGE_SIZE = 50;
+
+    /**
+     * 从分享链接中提取 tenant 的正则
+     */
+    private static final Pattern TENANT_PATTERN =
+            Pattern.compile("https://([^.]+)\\.feishu\\.cn/");
+
+    /** 解析 Content-Disposition: filename*=UTF-8''xxx */
+    private static final Pattern CD_FILENAME_STAR_PATTERN =
+            Pattern.compile("filename\\*=UTF-8''(.+?)(?:;|$)");
+
+    /** 解析 Content-Disposition: filename="xxx" 或 filename=xxx */
+    private static final Pattern CD_FILENAME_PATTERN =
+            Pattern.compile("filename=\"?([^\";]+)\"?");
+
+    /** 解析 Content-Range 中的总大小 */
+    private static final Pattern CONTENT_RANGE_SIZE_PATTERN =
+            Pattern.compile("/(\\d+)");
+
+    public FsTool(ShareLinkInfo shareLinkInfo) {
+        super(shareLinkInfo);
+    }
+
+    @Override
+    public Future<String> parse() {
+        String shareUrl = shareLinkInfo.getShareUrl();
+        String tenant = extractTenant(shareUrl);
+        String token = shareLinkInfo.getShareKey();
+
+        if (tenant == null || token == null) {
+            fail("无法从链接中提取tenant或token: {}", shareUrl);
+            return promise.future();
+        }
+
+        boolean isFolder = shareUrl.contains("/drive/folder/");
+        if (isFolder) {
+            fetchSessionAndParseFolder(tenant, token, shareUrl);
+        } else {
+            fetchSessionAndParseFile(tenant, token, shareUrl);
+        }
+
+        return promise.future();
+    }
+
+    /**
+     * 获取匿名session后解析文件
+     */
+    private void fetchSessionAndParseFile(String tenant, String token, String shareUrl) {
+        clientSession.getAbs(shareUrl)
+                .putHeader("User-Agent", UA)
+                .putHeader("Accept", "text/html,*/*")
+                .send()
+                .onSuccess(res -> {
+                    String dlUrl = buildDownloadUrl(tenant, token);
+
+                    // Range探测获取文件名和大小
+                    clientSession.getAbs(dlUrl)
+                            .putHeader("User-Agent", UA)
+                            .putHeader("Referer", shareUrl)
+                            .putHeader("Range", "bytes=0-0")
+                            .send()
+                            .onSuccess(probeRes -> {
+                                String fileName = parseFileNameFromContentDisposition(
+                                        probeRes.getHeader("Content-Disposition"));
+
+                                Map<String, String> headers = new HashMap<>();
+                                headers.put("Referer", shareUrl);
+                                headers.put("User-Agent", UA);
+
+                                String cookies = extractCookiesFromResponse(probeRes);
+                                if (cookies != null && !cookies.isEmpty()) {
+                                    headers.put("Cookie", cookies);
+                                }
+
+                                if (fileName != null) {
+                                    FileInfo fileInfo = new FileInfo();
+                                    fileInfo.setFileName(fileName);
+                                    fileInfo.setPanType(shareLinkInfo.getType());
+                                    parseSizeFromContentRange(
+                                            probeRes.getHeader("Content-Range"), fileInfo);
+                                    shareLinkInfo.getOtherParam().put("fileInfo", fileInfo);
+                                }
+
+                                completeWithMeta(dlUrl, headers);
+                            })
+                            .onFailure(handleFail("探测文件信息失败"));
+                })
+                .onFailure(handleFail("获取匿名会话失败"));
+    }
+
+    /**
+     * 获取匿名session后解析文件夹（取第一个可下载文件）
+     */
+    private void fetchSessionAndParseFolder(String tenant, String folderToken,
+                                             String shareUrl) {
+        clientSession.getAbs(shareUrl)
+                .putHeader("User-Agent", UA)
+                .putHeader("Accept", "text/html,*/*")
+                .send()
+                .onSuccess(res ->
+                        listFolderAll(tenant, folderToken, "").onSuccess(items -> {
+                            if (items.isEmpty()) {
+                                fail("文件夹中没有可下载的文件");
+                                return;
+                            }
+                            FileInfo first = items.get(0);
+                            String objToken = first.getFileId();
+                            String dlUrl = buildDownloadUrl(tenant, objToken);
+                            String referer = "https://" + tenant
+                                    + ".feishu.cn/drive/folder/" + folderToken;
+
+                            Map<String, String> headers = new HashMap<>();
+                            headers.put("Referer", referer);
+                            headers.put("User-Agent", UA);
+
+                            shareLinkInfo.getOtherParam().put("fileInfo", first);
+                            completeWithMeta(dlUrl, headers);
+                        }).onFailure(t -> fail("列出文件夹内容失败: {}", t.getMessage())))
+                .onFailure(handleFail("获取匿名会话失败"));
+    }
+
+    @Override
+    public Future<List<FileInfo>> parseFileList() {
+        Promise<List<FileInfo>> listPromise = Promise.promise();
+        String shareUrl = shareLinkInfo.getShareUrl();
+        String tenant = extractTenant(shareUrl);
+        String token = shareLinkInfo.getShareKey();
+
+        if (tenant == null || token == null) {
+            listPromise.fail("无法从链接中提取tenant或token: " + shareUrl);
+            return listPromise.future();
+        }
+
+        boolean isFolder = shareUrl.contains("/drive/folder/");
+
+        clientSession.getAbs(shareUrl)
+                .putHeader("User-Agent", UA)
+                .putHeader("Accept", "text/html,*/*")
+                .send()
+                .onSuccess(res -> {
+                    if (isFolder) {
+                        listFolderAll(tenant, token, "")
+                                .onSuccess(listPromise::complete)
+                                .onFailure(listPromise::fail);
+                    } else {
+                        probeSingleFile(tenant, token, shareUrl)
+                                .onSuccess(fileInfo -> {
+                                    List<FileInfo> list = new ArrayList<>();
+                                    list.add(fileInfo);
+                                    listPromise.complete(list);
+                                })
+                                .onFailure(listPromise::fail);
+                    }
+                })
+                .onFailure(t -> listPromise.fail("获取匿名会话失败: " + t.getMessage()));
+
+        return listPromise.future();
+    }
+
+    /**
+     * 分页获取文件夹所有可下载文件
+     */
+    private Future<List<FileInfo>> listFolderAll(String tenant, String folderToken,
+                                                  String pageLabel) {
+        Promise<List<FileInfo>> p = Promise.promise();
+
+        listFolderPage(tenant, folderToken, pageLabel).onSuccess(pageResult -> {
+            List<FileInfo> items = new ArrayList<>(pageResult.items);
+            if (pageResult.hasMore) {
+                listFolderAll(tenant, folderToken, pageResult.nextLabel)
+                        .onSuccess(moreItems -> {
+                            items.addAll(moreItems);
+                            p.complete(items);
+                        })
+                        .onFailure(p::fail);
+            } else {
+                p.complete(items);
+            }
+        }).onFailure(p::fail);
+
+        return p.future();
+    }
+
+    /**
+     * 列出文件夹内容（单页）
+     */
+    private Future<FolderPageResult> listFolderPage(String tenant, String folderToken,
+                                                     String pageLabel) {
+        Promise<FolderPageResult> p = Promise.promise();
+        String baseUrl = "https://" + tenant + ".feishu.cn";
+
+        StringBuilder urlBuilder = new StringBuilder();
+        urlBuilder.append(baseUrl)
+                .append("/space/api/explorer/v3/children/list/")
+                .append("?length=").append(PAGE_SIZE)
+                .append("&asc=1&rank=5&token=").append(folderToken);
+
+        for (int type : LIST_OBJ_TYPES) {
+            urlBuilder.append("&obj_type=").append(type);
+        }
+
+        if (pageLabel != null && !pageLabel.isEmpty()) {
+            urlBuilder.append("&last_label=").append(pageLabel);
+        }
+
+        String url = urlBuilder.toString();
+        String referer = baseUrl + "/drive/folder/" + folderToken;
+
+        clientSession.getAbs(url)
+                .putHeader("User-Agent", UA)
+                .putHeader("Accept", "application/json, text/plain, */*")
+                .putHeader("Referer", referer)
+                .send()
+                .onSuccess(res -> {
+                    try {
+                        JsonObject json = asJson(res);
+                        int code = json.getInteger("code", -1);
+                        if (code != 0) {
+                            p.fail("飞书API错误: " + json.getString("msg"));
+                            return;
+                        }
+
+                        JsonObject data = json.getJsonObject("data");
+                        JsonObject entities = data.getJsonObject("entities",
+                                new JsonObject());
+                        JsonObject nodes = entities.getJsonObject("nodes",
+                                new JsonObject());
+                        JsonArray nodeList = data.getJsonArray("node_list",
+                                new JsonArray());
+
+                        List<FileInfo> items = new ArrayList<>();
+                        for (int i = 0; i < nodeList.size(); i++) {
+                            String nid = nodeList.getString(i);
+                            JsonObject node = nodes.getJsonObject(nid,
+                                    new JsonObject());
+                            int objType = node.getInteger("type", -1);
+                            String objToken = node.getString("obj_token", "");
+                            String name = node.getString("name", "unknown");
+
+                            // 排除文件夹自身节点
+                            if (objToken.equals(folderToken)) {
+                                continue;
+                            }
+
+                            // 只返回可下载的文件(type=12)
+                            if (objType == OBJ_TYPE_FILE) {
+                                FileInfo fileInfo = new FileInfo();
+                                fileInfo.setFileName(name);
+                                fileInfo.setFileId(objToken);
+                                fileInfo.setPanType(shareLinkInfo.getType());
+                                fileInfo.setFileType("file");
+
+                                JsonObject extra = node.getJsonObject("extra",
+                                        new JsonObject());
+                                try {
+                                    long size = Long.parseLong(
+                                            extra.getString("size", "0"));
+                                    fileInfo.setSize(size);
+                                } catch (NumberFormatException e) {
+                                    log.warn("无法解析文件大小: {}", extra.getString("size"), e);
+                                }
+
+                                fileInfo.setParserUrl(
+                                        buildDownloadUrl(tenant, objToken));
+                                items.add(fileInfo);
+                            }
+                        }
+
+                        boolean hasMore = data.getBoolean("has_more", false);
+                        String nextLabel = data.getString("last_label", "");
+
+                        p.complete(new FolderPageResult(items, hasMore, nextLabel));
+                    } catch (Exception e) {
+                        p.fail("解析文件列表响应失败: " + e.getMessage());
+                    }
+                })
+                .onFailure(t -> p.fail("请求文件列表失败: " + t.getMessage()));
+
+        return p.future();
+    }
+
+    /**
+     * 探测单个文件信息
+     */
+    private Future<FileInfo> probeSingleFile(String tenant, String token,
+                                              String referer) {
+        Promise<FileInfo> p = Promise.promise();
+        String dlUrl = buildDownloadUrl(tenant, token);
+
+        clientSession.getAbs(dlUrl)
+                .putHeader("User-Agent", UA)
+                .putHeader("Referer", referer)
+                .putHeader("Range", "bytes=0-0")
+                .send()
+                .onSuccess(probeRes -> {
+                    FileInfo fileInfo = new FileInfo();
+                    String fileName = parseFileNameFromContentDisposition(
+                            probeRes.getHeader("Content-Disposition"));
+                    if (fileName != null) {
+                        fileInfo.setFileName(fileName);
+                    }
+                    parseSizeFromContentRange(
+                            probeRes.getHeader("Content-Range"), fileInfo);
+                    fileInfo.setFileId(token);
+                    fileInfo.setPanType(shareLinkInfo.getType());
+                    fileInfo.setFileType("file");
+                    fileInfo.setParserUrl(dlUrl);
+                    p.complete(fileInfo);
+                })
+                .onFailure(t -> p.fail("探测文件失败: " + t.getMessage()));
+
+        return p.future();
+    }
+
+    // ─── 工具方法 ────────────────────────────────────────
+
+    private String buildDownloadUrl(String tenant, String objToken) {
+        return "https://" + tenant
+                + ".feishu.cn/space/api/box/stream/download/all/" + objToken;
+    }
+
+    private String extractTenant(String url) {
+        if (url == null) return null;
+        Matcher m = TENANT_PATTERN.matcher(url);
+        if (m.find()) {
+            return m.group(1);
+        }
+        return null;
+    }
+
+    /**
+     * 从Content-Disposition头解析文件名。
+     * 支持 filename*=UTF-8''xxx 和 filename="xxx" 两种格式。
+     */
+    private String parseFileNameFromContentDisposition(String cd) {
+        if (cd == null || cd.isEmpty()) return null;
+
+        // 优先解析 filename*=UTF-8''xxx
+        Matcher m1 = CD_FILENAME_STAR_PATTERN.matcher(cd);
+        if (m1.find()) {
+            try {
+                return URLDecoder.decode(m1.group(1).trim(), StandardCharsets.UTF_8);
+            } catch (Exception ignored) {
+            }
+        }
+
+        // 降级解析 filename="xxx" 或 filename=xxx
+        Matcher m2 = CD_FILENAME_PATTERN.matcher(cd);
+        if (m2.find()) {
+            try {
+                return URLDecoder.decode(m2.group(1).trim(), StandardCharsets.UTF_8);
+            } catch (Exception ignored) {
+            }
+        }
+
+        return null;
+    }
+
+    private void parseSizeFromContentRange(String cr, FileInfo fileInfo) {
+        if (cr != null) {
+            Matcher m = CONTENT_RANGE_SIZE_PATTERN.matcher(cr);
+            if (m.find()) {
+                fileInfo.setSize(Long.parseLong(m.group(1)));
+            }
+        }
+    }
+
+    private String extractCookiesFromResponse(
+            io.vertx.ext.web.client.HttpResponse<?> response) {
+        List<String> setCookies = response.cookies();
+        if (setCookies == null || setCookies.isEmpty()) return null;
+
+        StringBuilder sb = new StringBuilder();
+        for (String cookie : setCookies) {
+            String nameValue = cookie.split(";")[0].trim();
+            if (!sb.isEmpty()) sb.append("; ");
+            sb.append(nameValue);
+        }
+        return sb.toString();
+    }
+
+    /**
+     * 文件夹分页结果
+     */
+    private record FolderPageResult(List<FileInfo> items, boolean hasMore,
+                                     String nextLabel) {
+    }
+}

parser/src/main/resources/py/feishu-dl.py

@@ -1,355 +0,0 @@
-#!/usr/bin/env python3
-"""
-飞书公开分享 直链解析 + 批量下载 (aria2/Motrix)
-支持: 单文件链接 / 文件夹链接(递归子目录)
-
-用法:
-  python feishu_dl.py <链接>                     # 推送到 Motrix
-  python feishu_dl.py <链接> -d D:/Downloads      # 指定下载目录
-  python feishu_dl.py <链接> --list               # 仅列出文件,不下载
-  python feishu_dl.py <链接> --aria2c              # 输出 aria2c 命令行
-"""
-
-import sys, os, re, json, uuid, ssl, gzip, argparse
-import http.cookiejar
-import urllib.request, urllib.error
-from urllib.parse import unquote, quote
-
-# ─── Motrix aria2 RPC 默认配置 ──────────────────────────
-ARIA2_RPC_URL = "http://localhost:16800/jsonrpc"
-ARIA2_SECRET  = "motrix"
-# ────────────────────────────────────────────────────────
-
-UA = ("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
-      "(KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36")
-
-# 飞书 obj_type 映射 (type=12 上传文件可下载, type=0 文件夹可递归)
-OBJ_TYPES = {
-    0: "📁 文件夹", 2: "📝 旧版文档", 3: "📊 表格", 8: "🧠 思维导图",
-    11: "📽 幻灯片", 12: "📄 文件", 22: "📝 新版文档", 30: "📋 画板",
-    44: "📊 多维表格", 84: "📑 知识库", 123: "❓ 未知", 124: "❓ 未知",
-}
-
-# v3 列表 API 支持的 obj_type
-LIST_OBJ_TYPES = [0, 2, 22, 44, 3, 30, 8, 11, 12, 84, 123, 124]
-
-
-# ─── 网络工具 ────────────────────────────────────────────
-
-def _ctx():
-    ctx = ssl.create_default_context()
-    ctx.check_hostname = False
-    ctx.verify_mode = ssl.CERT_NONE
-    return ctx
-
-def make_opener(jar):
-    return urllib.request.build_opener(
-        urllib.request.HTTPSHandler(context=_ctx()),
-        urllib.request.HTTPCookieProcessor(jar),
-    )
-
-def decode_body(resp):
-    data = resp.read()
-    if resp.headers.get("Content-Encoding") == "gzip":
-        data = gzip.decompress(data)
-    return data.decode("utf-8", errors="replace")
-
-def cookie_string(jar):
-    return "; ".join(f"{c.name}={c.value}" for c in jar)
-
-def human_size(n):
-    for u in ("B", "KB", "MB", "GB"):
-        if n < 1024: return f"{n:.1f} {u}"
-        n /= 1024
-    return f"{n:.1f} TB"
-
-
-# ─── 飞书核心 API ────────────────────────────────────────
-
-def parse_share_url(url):
-    """返回 (tenant, token, link_type:'file'|'folder')"""
-    m = re.match(r'https://([^.]+)\.feishu\.cn/file/([A-Za-z0-9_-]+)', url)
-    if m: return m.group(1), m.group(2), "file"
-    m = re.match(r'https://([^.]+)\.feishu\.cn/drive/folder/([A-Za-z0-9_-]+)', url)
-    if m: return m.group(1), m.group(2), "folder"
-    return None, None, None
-
-
-def fetch_session(share_url):
-    """访问分享页拿匿名 session cookie"""
-    jar = http.cookiejar.CookieJar()
-    opener = make_opener(jar)
-    req = urllib.request.Request(share_url)
-    req.add_header("User-Agent", UA)
-    req.add_header("Accept", "text/html,*/*")
-    opener.open(req, timeout=15).read()
-    return jar
-
-
-def list_folder(tenant, folder_token, jar, page_label=""):
-    """
-    v3 API 列出文件夹内容 (单页)
-    GET /space/api/explorer/v3/children/list/?token=xxx&length=50&...
-    """
-    base = f"https://{tenant}.feishu.cn"
-    params = ["length=50", "asc=1", "rank=5", f"token={folder_token}"]
-    for t in LIST_OBJ_TYPES:
-        params.append(f"obj_type={t}")
-    if page_label:
-        params.append(f"last_label={quote(page_label, safe='')}")
-
-    url = f"{base}/space/api/explorer/v3/children/list/?{'&'.join(params)}"
-    opener = make_opener(jar)
-    req = urllib.request.Request(url)
-    req.add_header("User-Agent", UA)
-    req.add_header("Accept", "application/json, text/plain, */*")
-    req.add_header("Referer", f"{base}/drive/folder/{folder_token}")
-
-    resp = opener.open(req, timeout=15)
-    data = json.loads(decode_body(resp))
-    if data.get("code") != 0:
-        raise RuntimeError(f"API error: {data.get('msg')}")
-
-    d = data["data"]
-    nodes = d.get("entities", {}).get("nodes", {})
-    node_list = d.get("node_list", [])
-
-    items = []
-    for nid in node_list:
-        node = nodes.get(nid, {})
-        obj_type = node.get("type", -1)
-        obj_token = node.get("obj_token", "")
-        name = node.get("name", "unknown")
-        extra = node.get("extra", {})
-        try:   size = int(extra.get("size", "0"))
-        except: size = 0
-        items.append({
-            "name": name, "obj_token": obj_token, "type": obj_type,
-            "size": size, "url": node.get("url", ""),
-            "is_folder": obj_type == 0,
-            "type_name": OBJ_TYPES.get(obj_type, f"❓ type={obj_type}"),
-        })
-
-    # 排除文件夹自身节点
-    items = [it for it in items if it["obj_token"] != folder_token]
-    return items, d.get("has_more", False), d.get("last_label", "")
-
-
-def list_folder_all(tenant, folder_token, jar):
-    """分页获取文件夹全部内容"""
-    all_items, label = [], ""
-    while True:
-        items, has_more, label = list_folder(tenant, folder_token, jar, label)
-        all_items.extend(items)
-        if not has_more: break
-    return all_items
-
-
-def walk_folder(tenant, folder_token, jar, prefix="", depth=0):
-    """递归遍历, 返回扁平列表 [{..., path:"a/b/file.txt"}]"""
-    if depth > 10:  # 防止无限递归
-        return []
-    items = list_folder_all(tenant, folder_token, jar)
-    result = []
-    for it in items:
-        if it["is_folder"]:
-            sub = walk_folder(tenant, it["obj_token"], jar,
-                              prefix=f"{prefix}{it['name']}/", depth=depth+1)
-            result.extend(sub)
-        else:
-            it["path"] = f"{prefix}{it['name']}"
-            result.append(it)
-    return result
-
-
-def probe_file(tenant, obj_token, jar, referer):
-    """Range 探测文件名 + 大小 (只取1字节)"""
-    dl_url = f"https://{tenant}.feishu.cn/space/api/box/stream/download/all/{obj_token}"
-    opener = make_opener(jar)
-    req = urllib.request.Request(dl_url)
-    req.add_header("User-Agent", UA)
-    req.add_header("Referer", referer)
-    req.add_header("Range", "bytes=0-0")
-
-    resp = opener.open(req, timeout=15)
-    cd = resp.headers.get("Content-Disposition", "")
-    cr = resp.headers.get("Content-Range", "")
-    resp.read()
-
-    filename = ""
-    m = re.search(r"filename\*=UTF-8''(.+?)(?:;|$)", cd)
-    if m: filename = unquote(m.group(1).strip())
-    if not filename:
-        m = re.search(r'filename="?([^";]+)"?', cd)
-        if m: filename = unquote(m.group(1).strip())
-
-    total = 0
-    m = re.search(r'/(\d+)', cr)
-    if m: total = int(m.group(1))
-    return filename, total
-
-
-# ─── aria2 RPC ───────────────────────────────────────────
-
-def aria2_add(dl_url, cs, referer, filename, out_dir=None):
-    opts = {"header": [f"Cookie: {cs}", f"Referer: {referer}", f"User-Agent: {UA}"]}
-    if filename: opts["out"] = filename
-    if out_dir:  opts["dir"] = out_dir
-    payload = json.dumps({
-        "jsonrpc": "2.0", "id": str(uuid.uuid4()),
-        "method": "aria2.addUri",
-        "params": [f"token:{ARIA2_SECRET}", [dl_url], opts],
-    }).encode()
-    req = urllib.request.Request(ARIA2_RPC_URL, data=payload,
-                                 headers={"Content-Type": "application/json"})
-    resp = urllib.request.urlopen(req, timeout=10)
-    return json.loads(resp.read().decode()).get("result", "")
-
-
-def push_one(dl_url, cs, referer, filename, out_dir, quiet=False):
-    try:
-        gid = aria2_add(dl_url, cs, referer, filename, out_dir)
-        if gid:
-            if not quiet: print(f"      [✓] GID={gid}  {filename}")
-            return True
-    except urllib.error.URLError:
-        if not quiet:
-            print(f"      [✗] Motrix 未启动, RPC: {ARIA2_RPC_URL}")
-    except Exception as e:
-        if not quiet: print(f"      [✗] {e}")
-    return False
-
-
-def print_aria2c(dl_url, cs, referer, filename, out_dir):
-    print(f'aria2c --header="Cookie: {cs}" \\')
-    print(f'  --header="Referer: {referer}" \\')
-    print(f'  --header="User-Agent: {UA}" \\')
-    if filename: print(f'  -o "{filename}" \\')
-    if out_dir:  print(f'  -d "{out_dir}" \\')
-    print(f'  "{dl_url}"')
-
-
-# ─── 主流程 ──────────────────────────────────────────────
-
-def handle_file(tenant, token, jar, args):
-    share_url = f"https://{tenant}.feishu.cn/file/{token}"
-    dl_url = f"https://{tenant}.feishu.cn/space/api/box/stream/download/all/{token}"
-    cs = cookie_string(jar)
-
-    print(f"[2/3] 探测文件 ...")
-    filename, size = probe_file(tenant, token, jar, share_url)
-    print(f"      {filename}  ({human_size(size)})")
-
-    if args.list: return
-    if args.aria2c:
-        print_aria2c(dl_url, cs, share_url, filename, args.dir); return
-
-    print(f"[3/3] 推送到 Motrix ...")
-    if not push_one(dl_url, cs, share_url, filename, args.dir):
-        print(f"\n  降级输出 aria2c 命令:\n")
-        print_aria2c(dl_url, cs, share_url, filename, args.dir)
-
-
-def handle_folder(tenant, token, jar, args):
-    base = f"https://{tenant}.feishu.cn"
-    cs = cookie_string(jar)
-
-    print(f"[2/4] 递归扫描文件夹 ...")
-    all_files = walk_folder(tenant, token, jar)
-
-    downloadable = [f for f in all_files if f["type"] == 12]
-    skipped      = [f for f in all_files if f["type"] != 12]
-
-    print(f"      共 {len(all_files)} 项: "
-          f"{len(downloadable)} 可下载, {len(skipped)} 在线文档(跳过)")
-
-    if skipped:
-        print(f"\n  ⏭ 跳过的在线文档:")
-        for f in skipped:
-            print(f"    {f['type_name']}  {f['path']}")
-
-    if not downloadable:
-        print("\n  没有可下载的文件"); return
-
-    # 探测真实文件名和大小
-    print(f"\n[3/4] 探测文件信息 ...")
-    total_size = 0
-    for f in downloadable:
-        referer = f.get("url", f"{base}/drive/folder/{token}")
-        try:
-            real_name, size = probe_file(tenant, f["obj_token"], jar, referer)
-            f["real_name"] = real_name or f["name"]
-            f["size"] = size or f["size"]
-        except:
-            f["real_name"] = f["name"]
-        total_size += f["size"]
-
-    # 打印文件列表
-    print(f"\n  {'─'*60}")
-    print(f"  {'#':>3}  {'文件名':<35} {'大小':>10}  路径")
-    print(f"  {'─'*60}")
-    for i, f in enumerate(downloadable):
-        sz = human_size(f["size"]) if f["size"] else "  ?"
-        print(f"  {i+1:>3}  {f['real_name']:<35} {sz:>10}  {f['path']}")
-    print(f"  {'─'*60}")
-    print(f"  合计: {len(downloadable)} 文件, {human_size(total_size)}")
-
-    if args.list: return
-
-    # 下载
-    print(f"\n[4/4] {'aria2c 命令' if args.aria2c else '推送 Motrix'} ...")
-    ok = 0
-    for f in downloadable:
-        dl_url = f"{base}/space/api/box/stream/download/all/{f['obj_token']}"
-        sub = os.path.dirname(f["path"])
-        out_dir = os.path.join(args.dir, sub) if args.dir and sub else (args.dir or None)
-
-        if args.aria2c:
-            print_aria2c(dl_url, cs, base, f["real_name"], out_dir)
-            print()
-            ok += 1
-        else:
-            if push_one(dl_url, cs, base, f["real_name"], out_dir, quiet=True):
-                ok += 1
-                print(f"      [✓] {f['real_name']}")
-            else:
-                print(f"      [✗] {f['real_name']} — Motrix 未响应")
-                print(f"          降级 aria2c:\n")
-                print_aria2c(dl_url, cs, base, f["real_name"], out_dir)
-                return  # Motrix 挂了就不继续了
-
-    print(f"\n      完成! {ok}/{len(downloadable)}")
-
-
-# ─── 入口 ────────────────────────────────────────────────
-
-def main():
-    ap = argparse.ArgumentParser(description="飞书分享解析下载器 v2")
-    ap.add_argument("url", help="飞书分享链接 (文件/文件夹)")
-    ap.add_argument("-d", "--dir", default=None, help="下载目录")
-    ap.add_argument("--list", action="store_true", help="仅列出,不下载")
-    ap.add_argument("--aria2c", action="store_true", help="输出 aria2c 命令")
-    args = ap.parse_args()
-
-    tenant, token, lt = parse_share_url(args.url)
-    if not token:
-        print(f"[✗] 不支持的链接: {args.url}")
-        print(f"    格式: https://xxx.feishu.cn/file/xxxToken")
-        print(f"          https://xxx.feishu.cn/drive/folder/xxxToken")
-        sys.exit(1)
-
-    print(f"\n{'📄' if lt=='file' else '📁'} 飞书分享解析  [{lt}]  {tenant}/{token}")
-
-    print(f"[1/{3 if lt=='file' else 4}] 获取匿名会话 ...")
-    jar = fetch_session(args.url)
-    print(f"      {sum(1 for _ in jar)} cookies")
-
-    if lt == "file":
-        handle_file(tenant, token, jar, args)
-    else:
-        handle_folder(tenant, token, jar, args)
-    print()
-
-
-if __name__ == "__main__":
-    main()

parser/src/test/java/cn/qaiu/parser/PanDomainTemplateTest.java

@@ -250,6 +250,72 @@ public class PanDomainTemplateTest {
         assertEquals("151bR-nk-tOBm9QAFaozJIVt2WYyCMkoz", m2.group("KEY"));
     }
 
+    @Test
+    public void testFsPatternMatching() {
+        Pattern fsPattern = PanDomainTemplate.FS.getPattern();
+
+        // 文件链接
+        Matcher m1 = fsPattern.matcher(
+                "https://kcncuknojm60.feishu.cn/file/VnCxbt35KoowKoxldO3c3C7VnMc");
+        assertTrue("FS should match file link", m1.matches());
+        assertEquals("VnCxbt35KoowKoxldO3c3C7VnMc", m1.group("KEY"));
+
+        // 文件链接带 ?from=from_copylink
+        Matcher m2 = fsPattern.matcher(
+                "https://kcncuknojm60.feishu.cn/file/VnCxbt35KoowKoxldO3c3C7VnMc?from=from_copylink");
+        assertTrue("FS should match file link with query param", m2.matches());
+        assertEquals("VnCxbt35KoowKoxldO3c3C7VnMc", m2.group("KEY"));
+
+        // 文件夹链接
+        Matcher m3 = fsPattern.matcher(
+                "https://kcncuknojm60.feishu.cn/drive/folder/RQSKf8EQ4l7dMedqzHucpMbancg");
+        assertTrue("FS should match folder link", m3.matches());
+        assertEquals("RQSKf8EQ4l7dMedqzHucpMbancg", m3.group("KEY"));
+
+        // 文件夹链接带 ?from=from_copylink
+        Matcher m4 = fsPattern.matcher(
+                "https://kcncuknojm60.feishu.cn/drive/folder/RQSKf8EQ4l7dMedqzHucpMbancg?from=from_copylink");
+        assertTrue("FS should match folder link with query param", m4.matches());
+        assertEquals("RQSKf8EQ4l7dMedqzHucpMbancg", m4.group("KEY"));
+
+        // 不同的 tenant 子域名
+        Matcher m5 = fsPattern.matcher(
+                "https://pokepangle.feishu.cn/file/VW30bpK74ontiTxvRg1cZcgvnGg");
+        assertTrue("FS should match different tenant", m5.matches());
+        assertEquals("VW30bpK74ontiTxvRg1cZcgvnGg", m5.group("KEY"));
+
+        // 负例: 非feishu域名不匹配
+        assertFalse("FS should NOT match non-feishu domain",
+                fsPattern.matcher("https://evil.com/file/abc123").matches());
+
+        // 负例: feishu.cn上的其他路径不匹配
+        assertFalse("FS should NOT match other feishu paths",
+                fsPattern.matcher("https://xxx.feishu.cn/docs/abc123").matches());
+    }
+
+    @Test
+    public void testFsFromShareUrl() {
+        // 测试文件链接解析
+        String fileUrl = "https://kcncuknojm60.feishu.cn/file/VnCxbt35KoowKoxldO3c3C7VnMc?from=from_copylink";
+        ParserCreate parserCreate = ParserCreate.fromShareUrl(fileUrl);
+        ShareLinkInfo info = parserCreate.getShareLinkInfo();
+
+        assertNotNull("ShareLinkInfo should not be null", info);
+        assertEquals("fs", info.getType());
+        assertEquals("飞书云盘", info.getPanName());
+        assertEquals("VnCxbt35KoowKoxldO3c3C7VnMc", info.getShareKey());
+
+        // 测试文件夹链接解析
+        String folderUrl = "https://kcncuknojm60.feishu.cn/drive/folder/RQSKf8EQ4l7dMedqzHucpMbancg";
+        ParserCreate parserCreate2 = ParserCreate.fromShareUrl(folderUrl);
+        ShareLinkInfo info2 = parserCreate2.getShareLinkInfo();
+
+        assertNotNull("ShareLinkInfo should not be null", info2);
+        assertEquals("fs", info2.getType());
+        assertEquals("飞书云盘", info2.getPanName());
+        assertEquals("RQSKf8EQ4l7dMedqzHucpMbancg", info2.getShareKey());
+    }
+
     @Test
     public void verifyDuplicates() {