feat(clients): add exponential backoff

book/src/README.md

@@ -9,4 +9,5 @@
 - Cron Jobs
 - Subscriptions
 - AI Scraping and Event Driven Actions
-- Blacklisting and Budgeting Depth
+- Blacklisting and Budgeting Depth
+- Exponential Backoff

book/src/rust/getting-started.md

@@ -285,4 +285,4 @@ spider.crawl_url(url, Some(crawler_params), true, "application/jsonl", None::<fn
 
 ## Error Handling
 
-The SDK handles errors returned by the Spider Cloud API and raises appropriate exceptions. If an error occurs during a request, it will be propagated to the caller with a descriptive error message.
+The SDK handles errors returned by the Spider Cloud API and raises appropriate exceptions. If an error occurs during a request, it will be propagated to the caller with a descriptive error message. By default request use a Exponential Backoff to retry as needed.

cli/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "spider-cloud-cli"
-version = "0.1.23"
+version = "0.1.24"
 edition = "2021"
 authors = [ "j-mendez <[email protected]>"]
 description = "The Spider Cloud CLI for web crawling and scraping"
@@ -11,10 +11,10 @@ categories = ["web-programming"]
 include = ["src/*", "../../LICENSE", "README.md"]
 
 [dependencies]
-clap = { version = "4.5.13", features = ["derive"]}
+clap = { version = "4", features = ["derive"]}
 reqwest = { version = "0.12", features = ["json", "stream"] }
 tokio = { version = "1", features = ["rt-multi-thread", "macros"] }
 spider-client = { path = "../rust", version = "0.1" }
-serde = { version = "1.0", features = ["derive"] }
-serde_json = "1.0"
+serde = { version = "1", features = ["derive"] }
+serde_json = "1"
 keyring = { version = "3", features = ["apple-native", "windows-native", "sync-secret-service"] }

cli/src/main.rs

@@ -161,7 +161,10 @@ async fn main() {
                                 params.limit = Some(limit);
                             }
                             println!("Labeling data from URL: {}", url);
-                            match spider.label(&url, Some(params), false, "application/json").await {
+                            match spider
+                                .label(&url, Some(params), false, "application/json")
+                                .await
+                            {
                                 Ok(data) => println!("{}", json!(data)),
                                 Err(e) => eprintln!("Error labeling data: {:?}", e),
                             }

javascript/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@spider-cloud/spider-client",
-  "version": "0.1.23",
+  "version": "0.1.24",
   "description": "Isomorphic Javascript SDK for Spider Cloud services",
   "scripts": {
     "test": "node --import tsx  --test __tests__/*test.ts",
@@ -23,9 +23,12 @@
   "author": "Jeff Mendez<[email protected]>",
   "license": "MIT",
   "devDependencies": {
-    "@types/node": "22.7.5",
-    "dotenv": "^16.4.5",
-    "tsx": "^4.19.1",
-    "typescript": "5.6.3"
+    "@types/node": "22.10.1",
+    "dotenv": "^16.4.7",
+    "tsx": "^4.19.2",
+    "typescript": "5.7.2"
+  },
+  "dependencies": {
+    "exponential-backoff": "^3.1.1"
   }
 }

javascript/src/client.ts

@@ -10,6 +10,7 @@ import {
 } from "./config";
 import { version } from "../package.json";
 import { streamReader } from "./utils/stream-reader";
+import { backOff } from "exponential-backoff";
 
 /**
  * Generic params for core request.
@@ -56,12 +57,15 @@ export class Spider {
     jsonl?: boolean
   ) {
     const headers = jsonl ? this.prepareHeadersJsonL : this.prepareHeaders;
-    const response = await fetch(
-      `${APISchema["url"]}/${ApiVersion.V1}/${endpoint}`,
+    const response = await backOff(
+      () =>
+        fetch(`${APISchema["url"]}/${ApiVersion.V1}/${endpoint}`, {
+          method: "POST",
+          headers: headers,
+          body: JSON.stringify(data),
+        }),
       {
-        method: "POST",
-        headers: headers,
-        body: JSON.stringify(data),
+        numOfAttempts: 5,
       }
     );
 
@@ -82,11 +86,14 @@ export class Spider {
    */
   private async _apiGet(endpoint: string) {
     const headers = this.prepareHeaders;
-    const response = await fetch(
-      `${APISchema["url"]}/${ApiVersion.V1}/${endpoint}`,
+    const response = await backOff(
+      () =>
+        fetch(`${APISchema["url"]}/${ApiVersion.V1}/${endpoint}`, {
+          method: "GET",
+          headers: headers,
+        }),
       {
-        method: "GET",
-        headers: headers,
+        numOfAttempts: 5,
       }
     );
 
@@ -104,11 +111,14 @@ export class Spider {
    */
   private async _apiDelete(endpoint: string) {
     const headers = this.prepareHeaders;
-    const response = await fetch(
-      `${APISchema["url"]}/${ApiVersion.V1}/${endpoint}`,
+    const response = await backOff(
+      () =>
+        fetch(`${APISchema["url"]}/${ApiVersion.V1}/${endpoint}`, {
+          method: "DELETE",
+          headers,
+        }),
       {
-        method: "DELETE",
-        headers,
+        numOfAttempts: 5,
       }
     );
 

python/requirements.txt

@@ -3,4 +3,5 @@ pytest-asyncio
 python-dotenv
 aiohttp
 python-dotenv
-ijson
+ijson
+tenacity

python/setup.py

@@ -8,13 +8,13 @@ def read_file(fname):
 
 setup(
     name="spider-client",
-    version="0.1.23",
+    version="0.1.24",
     url="https://github.com/spider-rs/spider-clients/tree/main/python",
     author="Spider",
     author_email="[email protected]",
     description="Python SDK for Spider Cloud API",
     packages=find_packages(),
-    install_requires=["requests", "ijson"],
+    install_requires=["requests", "ijson", "tenacity", "aiohttp"],
     long_description=read_file("README.md"),
     long_description_content_type="text/markdown",
     classifiers=[

python/spider/async_spider.py

@@ -1,8 +1,5 @@
-import os
-import json
-import logging
+import os, tenacity, json, aiohttp, logging
 from typing import Optional, Dict, Any, AsyncIterator, Callable
-import aiohttp
 from aiohttp import ClientSession, ClientResponse
 from types import TracebackType
 from typing import Type
@@ -35,6 +32,10 @@ async def __aexit__(
         if self.session:
             await self.session.close()
 
+    @tenacity.retry(
+        wait=tenacity.wait_exponential(multiplier=1, min=1, max=60),
+        stop=tenacity.stop_after_attempt(5)
+    )
     async def _request(
         self,
         method: str,
@@ -430,7 +431,7 @@ def _prepare_headers(
         return {
             "Content-Type": content_type,
             "Authorization": f"Bearer {self.api_key}",
-            "User-Agent": "AsyncSpider-Client/0.1.23",
+            "User-Agent": "AsyncSpider-Client/0.1.24",
         }
 
     async def _handle_error(self, response: ClientResponse, action: str) -> None: