aboutsummaryrefslogtreecommitdiff
path: root/castle-search/src/google-links.ts
diff options
context:
space:
mode:
Diffstat (limited to 'castle-search/src/google-links.ts')
-rw-r--r--castle-search/src/google-links.ts15
1 files changed, 15 insertions, 0 deletions
diff --git a/castle-search/src/google-links.ts b/castle-search/src/google-links.ts
new file mode 100644
index 0000000..7500e2d
--- /dev/null
+++ b/castle-search/src/google-links.ts
@@ -0,0 +1,15 @@
+/**
+ * Google wraps every outbound result in `https://www.google.com/goto?url=<opaque
+ * token>`. The token is a protobuf blob with no URL in it and the target appears
+ * nowhere in the page, so the only way to learn it is to follow the link.
+ *
+ * It is followed in Chrome, lazily, one link at a time, when the caller asks
+ * (see `resolveLink` in search.ts) — not here, and not for every result. A
+ * plain HTTP client gets Google's "Verifying your request" countdown after a
+ * handful of requests; the browser, with its own profile, gets the redirect.
+ */
+
+const GOTO = /^https?:\/\/(www\.)?google\.(?:com?\.)?[a-z]{2,3}\/goto\?url=[A-Za-z0-9_-]+$/;
+
+/** Only these may be opened by castle_cdp_resolve — it is not a general navigator. */
+export const isGoogleGoto = (url: string): boolean => GOTO.test(url);