Simple web server for viewing trees

2 files changed, 127 insertions, 0 deletions

diff --git a/src/index.ts b/src/index.ts
new file mode 100644
index 0000000..df0a116
--- /dev/null
+++ b/src/index.ts
@@ -0,0 +1,36 @@
+import { Hono } from "hono";
+import { serve } from "@hono/node-server";
+import { serveStatic } from "@hono/node-server/serve-static";
+import { Eta } from "eta";
+import { getGitHubTree } from "./scraper.js";
+
+const app = new Hono();
+const eta = new Eta({ views: "./views" });
+
+app.use("/static/*", serveStatic({ root: "." }));
+
+app.get("/:owner/:repo/tree/:branch/:path{.*}?", async (c) => {
+  try {
+    const owner = c.req.param("owner");
+    const repo = c.req.param("repo");
+    const branch = c.req.param("branch");
+    const path = c.req.param("path") || "";
+
+    const data = await getGitHubTree(owner, repo, branch, path);
+    const html = await eta.renderAsync("tree.eta", data);
+
+    return c.html(html);
+  } catch (error) {
+    const errorMessage =
+      error instanceof Error ? error.message : "Unknown error";
+    return c.html(
+      `<html><body><h1>Error</h1><p>${errorMessage}</p></body></html>`,
+      500,
+    );
+  }
+});
+
+const port = parseInt(process.env.PORT || "3000", 10);
+serve({ fetch: app.fetch, port }, (info) => {
+  console.log(`Server running on http://localhost:${info.port}`);
+});
diff --git a/src/scraper.ts b/src/scraper.ts
new file mode 100644
index 0000000..add03b2
--- /dev/null
+++ b/src/scraper.ts
@@ -0,0 +1,91 @@
+export interface GitHubTreeItem {
+  name: string;
+  path: string;
+  contentType: "directory" | "file";
+}
+
+export interface GitHubTree {
+  path: string;
+  branch: string;
+  items: GitHubTreeItem[];
+  repo: {
+    name: string;
+    owner: string;
+    isPublic: boolean;
+  };
+}
+
+export async function getGitHubTree(
+  owner: string,
+  repo: string,
+  branch: string,
+  path: string,
+): Promise<GitHubTree> {
+  const url = `https://github.com/${owner}/${repo}/tree/${branch}/${path}`;
+
+  // GitHub throttles/blocks requests without realistic browser headers.
+  // These headers make the request appear as a standard browser visit.
+  const response = await fetch(url, {
+    headers: {
+      "User-Agent":
+        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36",
+      Accept:
+        "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
+      "Accept-Language": "en-US,en;q=0.5",
+    },
+  });
+  const html = await response.text();
+
+  // GitHub uses different formats for root vs subdirectories.
+  let payload;
+
+  // Try root format first.
+  const rootFormatMatches = [
+    ...html.matchAll(
+      /<script type="application\/json" data-target="react-partial\.embeddedData">([^<]+)<\/script>/g,
+    ),
+  ];
+  for (const match of rootFormatMatches) {
+    try {
+      const data = JSON.parse(match[1]);
+      if (data.props?.initialPayload?.tree) {
+        payload = data.props.initialPayload;
+        break;
+      }
+    } catch (e) {
+      continue;
+    }
+  }
+
+  // Try subdirectory format.
+  if (!payload) {
+    const dirFormatMatch = html.match(
+      /<script type="application\/json" data-target="react-app\.embeddedData">([^<]+)<\/script>/,
+    );
+    if (dirFormatMatch) {
+      try {
+        const data = JSON.parse(dirFormatMatch[1]);
+        if (data.payload?.tree) {
+          payload = data.payload;
+        }
+      } catch (e) {
+        // Skip invalid JSON
+      }
+    }
+  }
+
+  if (!payload) {
+    throw new Error("Could not find tree data in embedded JSON");
+  }
+
+  return {
+    path: payload.path,
+    branch: payload.refInfo.name,
+    items: payload.tree.items,
+    repo: {
+      name: payload.repo.name,
+      owner: payload.repo.ownerLogin,
+      isPublic: payload.repo.public,
+    },
+  };
+}