Bug fixes on regexes containing : and default acts array; Add cli for ease of use

Author: PRO-2684

README.md

@@ -24,7 +24,7 @@ Purify URL: Remove redundant tracking parameters, skip redirecting pages, and ex
 
 ### 🚀 Quick Start
 
-Visit our [demo page](https://pro-2684.github.io/?page=purlfy), or try it out with our [Tampermonkey script](https://greasyfork.org/scripts/492480)!
+Visit our [demo page](https://pro-2684.github.io/?page=purlfy), try out our [Tampermonkey script](https://greasyfork.org/scripts/492480), or simply `node cli.js <url[]> [<options>]` to purify a list of URLs (For more information, please refer to the comments in the script).
 
 ```js
 // Somewhat import `Purlfy` class from https://cdn.jsdelivr.net/gh/PRO-2684/pURLfy@latest/purlfy.min.js
@@ -336,7 +336,7 @@ If URL `https://example.com/?key=123` matches this rule, the `key` parameter wil
 
 ### 🖇️ Processors
 
-Some processors support parameters, simply append them to the function name separated by a colon (`:`): `func:arg1:arg2...:argn`. The following processors are currently supported:
+Some processors support parameters, simply append them to the function name separated by a colon (`:`): `func:arg`. The following processors are currently supported:
 
 - `url`: `string->string`, URL decoding (`decodeURIComponent`)
 - `base64`: `string->string`, Base64 decoding (`decodeURIComponent(escape(atob(s.replaceAll('_', '/').replaceAll('-', '+'))))`)

README_zh.md

@@ -24,7 +24,7 @@
 
 ### 🚀 快速开始
 
-访问我们的 [示例页面](https://pro-2684.github.io/?page=purlfy)，或者通过我们的 [Tampermonkey 脚本](https://greasyfork.org/scripts/492480) 来体验！
+访问我们的 [示例页面](https://pro-2684.github.io/?page=purlfy)，体验我们的 [Tampermonkey 脚本](https://greasyfork.org/scripts/492480)，或者直接 `node cli.js <url[]> [<options>]` 来净化一系列 URL (更多信息请参考脚本注释)。
 
 ```js
 // 通过某种方式从 https://cdn.jsdelivr.net/gh/PRO-2684/pURLfy@latest/purlfy.min.js 导入 `Purlfy` 类
@@ -101,7 +101,6 @@ new Purlfy({
 
 - `Purlfy.version: string`: pURLfy 的版本号
 
-
 ## 📖 规则
 
 社区贡献的规则文件托管在 GitHub 上，您可以在 [pURLfy-rules](https://github.com/PRO-2684/pURLfy-rules) 中找到。规则文件的格式如下:
@@ -337,7 +336,7 @@ new Purlfy({
 
 ### 🖇️ 处理器
 
-部分处理器支持传入参数，只需用 `:` 分隔即可：`func:arg1:arg2...:argn`。目前支持的处理器如下:
+部分处理器支持传入参数，只需用 `:` 分隔即可：`func:arg`。目前支持的处理器如下:
 
 - `url`: `string->string`，URL 解码 (`decodeURIComponent`)
 - `base64`: `string->string`，Base64 解码 (`decodeURIComponent(escape(atob(s.replaceAll('_', '/').replaceAll('-', '+'))))`)

cli.js

@@ -0,0 +1,36 @@
+// `node cli.js <url[]> [<options>]`
+// `url` is the URL to purify. You can pass multiple URLs to purify them all.
+// `options` can contain:
+// - `--rules <enabled-rules>`, where `enabled-rules` is a comma-separated list of rules to enable. Default is all rules. Short-hand `-r`.
+
+const Purlfy = require("./purlfy");
+const { parseArgs } = require("node:util");
+
+const options = {
+    rules: {
+        type: "string",
+        short: "r",
+        default: ""
+    }
+};
+const args = process.argv.slice(2);
+const {
+    values,
+    positionals: urls,
+} = parseArgs({ args, options, allowPositionals: true });
+const { rules: rulesStr } = values;
+const enabledRules = rulesStr.trim().length ? rulesStr.split(",").map((rule) => rule.trim()).filter(Boolean) : require("./rules/list.json");
+console.log("Enabled rules:", enabledRules);
+console.log("---");
+
+const purifier = new Purlfy({
+    fetchEnabled: true,
+    lambdaEnabled: true,
+});
+const rules = enabledRules.map((rule) => require(`./rules/${rule}.json`));
+purifier.importRules(...rules);
+for (const url of urls) {
+    purifier.purify(url).then((purified) => {
+        console.log(url, "=>", purified.url);
+    });
+}

purlfy.js

@@ -31,7 +31,10 @@ class Purlfy extends EventTarget {
     static #acts = {
         "url": decodeURIComponent,
         "base64": s => decodeURIComponent(escape(atob(s.replaceAll('_', '/').replaceAll('-', '+')))),
-        "slice": (s, start, end) => s.slice(parseInt(start), end ? parseInt(end) : undefined),
+        "slice": (s, startEnd) => {
+            const [start, end] = startEnd.split(":");
+            return s.slice(parseInt(start), end ? parseInt(end) : undefined)
+        },
         "regex": (s, regex) => {
             const r = new RegExp(regex);
             const m = s.match(r);
@@ -162,16 +165,16 @@ class Purlfy extends EventTarget {
     static #applyActs(input, acts, logFunc) {
         let dest = input;
         for (const cmd of (acts)) {
-            const args = cmd.split(":");
-            const name = args[0];
+            const name = cmd.split(":")[0];
+            const arg = cmd.slice(name.length + 1);
             const act = Purlfy.#acts[name];
             if (!act) {
                 logFunc("Invalid act:", cmd);
                 dest = null;
                 break;
             }
             try {
-                dest = act(dest, ...args.slice(1));
+                dest = act(dest, arg);
             } catch (e) {
                 logFunc(`Error processing input with act "${name}":`, e);
                 dest = null;
@@ -459,7 +462,7 @@ class Purlfy extends EventTarget {
                     logFunc("Visit mode, but got redirected to:", r.url);
                     urlObj = new URL(r.headers.get("location"), urlObj.href);
                 } else {
-                    const dest = Purlfy.#applyActs(html, rule.acts?.length ? rule.acts : ["regex:https?:\/\/.(?:www\.)?[-a-zA-Z0-9@%._\+~#=]{2,256}\.[a-z]{2,6}\b(?:[-a-zA-Z0-9@:%_\+.~#?!&\/\/=]*)"], logFunc);
+                    const dest = Purlfy.#applyActs(html, rule.acts?.length ? rule.acts : [String.raw`regex:https?:\/\/.(?:www\.)?[-a-zA-Z0-9@%._\+~#=]{2,256}\.[a-z]{2,6}\b(?:[-a-zA-Z0-9@:%_\+.~#?!&\/\/=]*)`], logFunc);
                     if (dest && URL.canParse(dest, urlObj.href)) { // Valid URL
                         urlObj = new URL(dest, urlObj.href);
                     } else { // Invalid URL