@vicociv/instaloader 0.1.0 → 0.3.0

package/dist/index.js

@@ -66,8 +66,11 @@ __export(index_exports, {
   TwoFactorAuthRequiredException: () => TwoFactorAuthRequiredException,
   defaultIphoneHeaders: () => defaultIphoneHeaders,
   defaultUserAgent: () => defaultUserAgent,
+  extractHashtagFromUrl: () => extractHashtagFromUrl,
   extractHashtags: () => extractHashtags,
   extractMentions: () => extractMentions,
+  extractShortcode: () => extractShortcode,
+  extractUsername: () => extractUsername,
   formatFilename: () => formatFilename,
   formatStringContainsKey: () => formatStringContainsKey,
   getConfigDir: () => getConfigDir,
@@ -76,6 +79,7 @@ __export(index_exports, {
   getJsonStructure: () => getJsonStructure,
   loadStructure: () => loadStructure,
   mediaidToShortcode: () => mediaidToShortcode,
+  parseInstagramUrl: () => parseInstagramUrl,
   resumableIteration: () => resumableIteration,
   sanitizePath: () => sanitizePath,
   shortcodeToMediaid: () => shortcodeToMediaid
@@ -216,9 +220,113 @@ var InvalidIteratorException = class extends InstaloaderException {
   }
 };
 
+// src/utils.ts
+function generateUUID() {
+  if (typeof crypto !== "undefined" && crypto.randomUUID) {
+    return crypto.randomUUID();
+  }
+  const bytes = new Uint8Array(16);
+  if (typeof crypto !== "undefined" && crypto.getRandomValues) {
+    crypto.getRandomValues(bytes);
+  } else {
+    for (let i = 0; i < 16; i++) {
+      bytes[i] = Math.floor(Math.random() * 256);
+    }
+  }
+  bytes[6] = bytes[6] & 15 | 64;
+  bytes[8] = bytes[8] & 63 | 128;
+  const hex = Array.from(bytes).map((b) => b.toString(16).padStart(2, "0")).join("");
+  return `${hex.slice(0, 8)}-${hex.slice(8, 12)}-${hex.slice(12, 16)}-${hex.slice(16, 20)}-${hex.slice(20)}`;
+}
+var SimpleCookieStore = class {
+  cookies = /* @__PURE__ */ new Map();
+  /**
+   * Get cookies for a URL as a key-value object.
+   */
+  getCookies(url) {
+    const domain = this.extractDomain(url);
+    const domainCookies = this.cookies.get(domain);
+    if (!domainCookies) {
+      return {};
+    }
+    return Object.fromEntries(domainCookies);
+  }
+  /**
+   * Set cookies from a key-value object.
+   */
+  setCookies(cookies, url) {
+    const domain = this.extractDomain(url);
+    let domainCookies = this.cookies.get(domain);
+    if (!domainCookies) {
+      domainCookies = /* @__PURE__ */ new Map();
+      this.cookies.set(domain, domainCookies);
+    }
+    for (const [key, value] of Object.entries(cookies)) {
+      domainCookies.set(key, value);
+    }
+  }
+  /**
+   * Parse and store cookies from Set-Cookie headers.
+   */
+  parseSetCookieHeaders(headers, url) {
+    const setCookies = headers.getSetCookie?.() || [];
+    const domain = this.extractDomain(url);
+    let domainCookies = this.cookies.get(domain);
+    if (!domainCookies) {
+      domainCookies = /* @__PURE__ */ new Map();
+      this.cookies.set(domain, domainCookies);
+    }
+    for (const cookieStr of setCookies) {
+      const parsed = this.parseSetCookie(cookieStr);
+      if (parsed) {
+        domainCookies.set(parsed.name, parsed.value);
+      }
+    }
+  }
+  /**
+   * Generate Cookie header string for a URL.
+   */
+  getCookieHeader(url) {
+    const cookies = this.getCookies(url);
+    return Object.entries(cookies).map(([k, v]) => `${k}=${v}`).join("; ");
+  }
+  /**
+   * Clear all cookies.
+   */
+  clear() {
+    this.cookies.clear();
+  }
+  /**
+   * Clear cookies for a specific domain.
+   */
+  clearDomain(url) {
+    const domain = this.extractDomain(url);
+    this.cookies.delete(domain);
+  }
+  extractDomain(url) {
+    try {
+      return new URL(url).hostname;
+    } catch {
+      return url;
+    }
+  }
+  parseSetCookie(cookieStr) {
+    const firstSemi = cookieStr.indexOf(";");
+    const nameValue = firstSemi === -1 ? cookieStr : cookieStr.slice(0, firstSemi);
+    const eqIndex = nameValue.indexOf("=");
+    if (eqIndex === -1) {
+      return null;
+    }
+    const name = nameValue.slice(0, eqIndex).trim();
+    const value = nameValue.slice(eqIndex + 1).trim();
+    if (!name) {
+      return null;
+    }
+    return { name, value };
+  }
+};
+
 // src/instaloadercontext.ts
-var import_tough_cookie = require("tough-cookie");
-var import_uuid = require("uuid");
 function defaultUserAgent() {
   return "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/142.0.0.0 Safari/537.36";
 }
@@ -246,11 +354,18 @@ function defaultIphoneHeaders() {
     "x-ig-mapped-locale": "en-US",
     "x-ig-timezone-offset": String(timezoneOffset),
     "x-ig-www-claim": "0",
-    "x-pigeon-session-id": (0, import_uuid.v4)(),
+    "x-pigeon-session-id": generateUUID(),
     "x-tigon-is-retry": "False",
     "x-whatsapp": "0"
   };
 }
+function getPerRequestHeaders() {
+  return {
+    "x-pigeon-rawclienttime": (Date.now() / 1e3).toFixed(6),
+    "x-ig-connection-speed": `${Math.floor(Math.random() * 19e3) + 1e3}kbps`,
+    "x-pigeon-session-id": generateUUID()
+  };
+}
 function sleep(ms) {
   return new Promise((resolve) => setTimeout(resolve, ms));
 }
@@ -301,16 +416,10 @@ var RateController = class {
       this._queryTimestamps.set(queryType, []);
     }
     const timestamps = this._queryTimestamps.get(queryType);
-    const filteredTimestamps = timestamps.filter(
-      (t) => t > currentTime - 60 * 60
-    );
+    const filteredTimestamps = timestamps.filter((t) => t > currentTime - 60 * 60);
     this._queryTimestamps.set(queryType, filteredTimestamps);
     const perTypeNextRequestTime = () => {
-      const reqs = this._reqsInSlidingWindow(
-        queryType,
-        currentTime,
-        perTypeSlidingWindow
-      );
+      const reqs = this._reqsInSlidingWindow(queryType, currentTime, perTypeSlidingWindow);
       if (reqs.length < this.countPerSlidingWindow(queryType)) {
         return 0;
       } else {
@@ -323,11 +432,7 @@ var RateController = class {
       }
       const gqlAccumulatedSlidingWindow = 600;
       const gqlAccumulatedMaxCount = 275;
-      const reqs = this._reqsInSlidingWindow(
-        null,
-        currentTime,
-        gqlAccumulatedSlidingWindow
-      );
+      const reqs = this._reqsInSlidingWindow(null, currentTime, gqlAccumulatedSlidingWindow);
       if (reqs.length < gqlAccumulatedMaxCount) {
         return 0;
       } else {
@@ -337,33 +442,18 @@ var RateController = class {
     const untrackedNextRequestTime = () => {
       if (untrackedQueries) {
         if (queryType === "iphone") {
-          const reqs = this._reqsInSlidingWindow(
-            queryType,
-            currentTime,
-            iphoneSlidingWindow
-          );
+          const reqs = this._reqsInSlidingWindow(queryType, currentTime, iphoneSlidingWindow);
           this._iphoneEarliestNextRequestTime = Math.min(...reqs) + iphoneSlidingWindow + 18;
         } else {
-          const reqs = this._reqsInSlidingWindow(
-            queryType,
-            currentTime,
-            perTypeSlidingWindow
-          );
+          const reqs = this._reqsInSlidingWindow(queryType, currentTime, perTypeSlidingWindow);
           this._earliestNextRequestTime = Math.min(...reqs) + perTypeSlidingWindow + 6;
         }
       }
-      return Math.max(
-        this._iphoneEarliestNextRequestTime,
-        this._earliestNextRequestTime
-      );
+      return Math.max(this._iphoneEarliestNextRequestTime, this._earliestNextRequestTime);
     };
     const iphoneNextRequest = () => {
       if (queryType === "iphone") {
-        const reqs = this._reqsInSlidingWindow(
-          queryType,
-          currentTime,
-          iphoneSlidingWindow
-        );
+        const reqs = this._reqsInSlidingWindow(queryType, currentTime, iphoneSlidingWindow);
         if (reqs.length >= 199) {
           return Math.min(...reqs) + iphoneSlidingWindow + 18;
         }
@@ -431,7 +521,7 @@ var InstaloaderContext = class {
   quiet;
   iphoneSupport;
   fatalStatusCodes;
-  _cookieJar;
+  _cookieStore;
   _csrfToken = null;
   _username = null;
   _userId = null;
@@ -452,13 +542,13 @@ var InstaloaderContext = class {
     this.quiet = options.quiet ?? false;
     this.iphoneSupport = options.iphoneSupport ?? true;
     this.fatalStatusCodes = options.fatalStatusCodes ?? [];
-    this._cookieJar = new import_tough_cookie.CookieJar();
+    this._cookieStore = new SimpleCookieStore();
     this._iphoneHeaders = defaultIphoneHeaders();
     this._initAnonymousCookies();
     this._rateController = options.rateController ? options.rateController(this) : new RateController(this);
   }
   _initAnonymousCookies() {
-    const domain = "www.instagram.com";
+    const url = "https://www.instagram.com/";
     const defaultCookies = {
       sessionid: "",
       mid: "",
@@ -468,15 +558,7 @@ var InstaloaderContext = class {
       s_network: "",
       ds_user_id: ""
     };
-    for (const [name, value] of Object.entries(defaultCookies)) {
-      const cookie = new import_tough_cookie.Cookie({
-        key: name,
-        value,
-        domain,
-        path: "/"
-      });
-      this._cookieJar.setCookieSync(cookie, `https://${domain}/`);
-    }
+    this._cookieStore.setCookies(defaultCookies, url);
   }
   /** True if this instance is logged in. */
   get is_logged_in() {
@@ -569,27 +651,13 @@ var InstaloaderContext = class {
    * Get cookies as a plain object.
    */
   getCookies(url = "https://www.instagram.com/") {
-    const cookies = this._cookieJar.getCookiesSync(url);
-    const result = {};
-    for (const cookie of cookies) {
-      result[cookie.key] = cookie.value;
-    }
-    return result;
+    return this._cookieStore.getCookies(url);
   }
   /**
    * Set cookies from a plain object.
    */
   setCookies(cookies, url = "https://www.instagram.com/") {
-    const domain = new URL(url).hostname;
-    for (const [name, value] of Object.entries(cookies)) {
-      const cookie = new import_tough_cookie.Cookie({
-        key: name,
-        value,
-        domain,
-        path: "/"
-      });
-      this._cookieJar.setCookieSync(cookie, url);
-    }
+    this._cookieStore.setCookies(cookies, url);
   }
   /**
    * Save session data for later restoration.
@@ -601,7 +669,7 @@ var InstaloaderContext = class {
    * Load session data from a saved session.
    */
   loadSession(username, sessionData) {
-    this._cookieJar = new import_tough_cookie.CookieJar();
+    this._cookieStore = new SimpleCookieStore();
     this.setCookies(sessionData);
     this._csrfToken = sessionData["csrftoken"] || null;
     this._username = username;
@@ -614,26 +682,16 @@ var InstaloaderContext = class {
     this.setCookies(cookies);
   }
   /**
-   * Build cookie header string from cookie jar.
+   * Build cookie header string from cookie store.
    */
   _getCookieHeader(url) {
-    const cookies = this._cookieJar.getCookiesSync(url);
-    return cookies.map((c) => `${c.key}=${c.value}`).join("; ");
+    return this._cookieStore.getCookieHeader(url);
   }
   /**
    * Parse and store cookies from Set-Cookie headers.
    */
   _storeCookies(url, headers) {
-    const setCookies = headers.getSetCookie?.() || [];
-    for (const cookieStr of setCookies) {
-      try {
-        const cookie = import_tough_cookie.Cookie.parse(cookieStr);
-        if (cookie) {
-          this._cookieJar.setCookieSync(cookie, url);
-        }
-      } catch {
-      }
-    }
+    this._cookieStore.parseSetCookieHeaders(headers, url);
   }
   /**
    * Format response error message.
@@ -657,7 +715,8 @@ var InstaloaderContext = class {
       host = "www.instagram.com",
       usePost = false,
       attempt = 1,
-      headers: extraHeaders
+      headers: extraHeaders,
+      refreshDynamicHeaders = false
     } = options;
     const isGraphqlQuery = "query_hash" in params && path2.includes("graphql/query");
     const isDocIdQuery = "doc_id" in params && path2.includes("graphql/query");
@@ -678,10 +737,17 @@ var InstaloaderContext = class {
         await this._rateController.waitBeforeQuery("other");
       }
       const url = new URL(`https://${host}/${path2}`);
+      let headersToUse = extraHeaders;
+      if (refreshDynamicHeaders && extraHeaders) {
+        headersToUse = {
+          ...extraHeaders,
+          ...getPerRequestHeaders()
+        };
+      }
       const headers = {
         ...this._defaultHttpHeader(true),
         Cookie: this._getCookieHeader(url.toString()),
-        ...extraHeaders
+        ...headersToUse
       };
       if (this._csrfToken) {
         headers["X-CSRFToken"] = this._csrfToken;
@@ -703,10 +769,7 @@ var InstaloaderContext = class {
         });
       } else {
         for (const [key, value] of Object.entries(params)) {
-          url.searchParams.set(
-            key,
-            typeof value === "string" ? value : JSON.stringify(value)
-          );
+          url.searchParams.set(key, typeof value === "string" ? value : JSON.stringify(value));
         }
         response = await fetch(url.toString(), {
           method: "GET",
@@ -729,9 +792,7 @@ var InstaloaderContext = class {
 HTTP redirect from ${url} to ${redirectUrl}`);
           if (redirectUrl.startsWith("https://www.instagram.com/accounts/login") || redirectUrl.startsWith("https://i.instagram.com/accounts/login")) {
             if (!this.is_logged_in) {
-              throw new LoginRequiredException(
-                "Redirected to login page. Use login() first."
-              );
+              throw new LoginRequiredException("Redirected to login page. Use login() first.");
             }
             throw new AbortDownloadException(
               "Redirected to login page. You've been logged out, please wait some time, recreate the session and try again"
@@ -803,8 +864,10 @@ HTTP redirect from ${url} to ${redirectUrl}`);
       }
       return this.getJson(path2, params, {
         host,
-        usePost,
+        // usePost is intentionally omitted to default to GET on retry
         attempt: attempt + 1,
+        refreshDynamicHeaders: true,
+        // Refresh headers on retry to appear as different client
         ...extraHeaders !== void 0 && { headers: extraHeaders }
       });
     }
@@ -836,11 +899,17 @@ HTTP redirect from ${url} to ${redirectUrl}`);
     return respJson;
   }
   /**
-   * Do a doc_id-based GraphQL Query using POST.
+   * Do a doc_id-based GraphQL Query.
+   *
+   * Uses GET for anonymous requests (works without login) and POST for authenticated
+   * requests. This is the correct behavior - Instagram's API accepts GET for public
+   * data but requires POST with session for authenticated operations.
    */
   async doc_id_graphql_query(docId, variables, referer) {
+    const perRequestHeaders = getPerRequestHeaders();
     const headers = {
       ...this._defaultHttpHeader(true),
+      ...perRequestHeaders,
       authority: "www.instagram.com",
       scheme: "https",
       accept: "*/*"
@@ -851,10 +920,11 @@ HTTP redirect from ${url} to ${redirectUrl}`);
       headers["referer"] = encodeURIComponent(referer);
     }
     const variablesJson = JSON.stringify(variables);
+    const usePost = this.is_logged_in;
     const respJson = await this.getJson(
       "graphql/query",
       { variables: variablesJson, doc_id: docId, server_timestamps: "true" },
-      { usePost: true, headers }
+      { usePost, headers }
     );
     if (!("status" in respJson)) {
       this.error('GraphQL response did not contain a "status" field.');
@@ -863,12 +933,14 @@ HTTP redirect from ${url} to ${redirectUrl}`);
   }
   /**
    * JSON request to i.instagram.com.
+   * Each request uses fresh dynamic headers to appear as different clients.
    */
   async get_iphone_json(path2, params) {
+    const perRequestHeaders = getPerRequestHeaders();
     const headers = {
       ...this._iphoneHeaders,
-      "ig-intended-user-id": this._userId || "",
-      "x-pigeon-rawclienttime": (Date.now() / 1e3).toFixed(6)
+      ...perRequestHeaders,
+      "ig-intended-user-id": this._userId || ""
     };
     const cookies = this.getCookies("https://i.instagram.com/");
     const headerCookiesMapping = {
@@ -923,9 +995,7 @@ HTTP redirect from ${url} to ${redirectUrl}`);
         this._responseError(response.status, response.statusText, url)
       );
     }
-    throw new ConnectionException(
-      this._responseError(response.status, response.statusText, url)
-    );
+    throw new ConnectionException(this._responseError(response.status, response.statusText, url));
   }
   /**
    * Test if logged in by querying the current user.
@@ -947,7 +1017,7 @@ HTTP redirect from ${url} to ${redirectUrl}`);
    * Login to Instagram.
    */
   async login(username, password) {
-    this._cookieJar = new import_tough_cookie.CookieJar();
+    this._cookieStore = new SimpleCookieStore();
     this._initAnonymousCookies();
     const initUrl = "https://www.instagram.com/";
     const initResponse = await fetch(initUrl, {
@@ -1067,7 +1137,7 @@ HTTP redirect from ${url} to ${redirectUrl}`);
       throw new InvalidArgumentException("No two-factor authentication pending.");
     }
     const { csrfToken, cookies, username, twoFactorId } = this._twoFactorAuthPending;
-    this._cookieJar = new import_tough_cookie.CookieJar();
+    this._cookieStore = new SimpleCookieStore();
     this.setCookies(cookies);
     const loginUrl = "https://www.instagram.com/accounts/login/ajax/two_factor/";
     const response = await fetch(loginUrl, {
@@ -1449,6 +1519,47 @@ function extractMentions(text) {
   }
   return matches;
 }
+var POST_URL_REGEX = /(?:https?:\/\/)?(?:www\.)?instagram\.com\/(?:p|reel|tv)\/([A-Za-z0-9_-]+)/;
+var PROFILE_URL_REGEX = /(?:https?:\/\/)?(?:www\.)?instagram\.com\/([A-Za-z0-9._]+)\/?(?:\?.*)?$/;
+var HASHTAG_URL_REGEX = /(?:https?:\/\/)?(?:www\.)?instagram\.com\/explore\/tags\/([^/?]+)/;
+function parseInstagramUrl(url) {
+  const postMatch = url.match(POST_URL_REGEX);
+  if (postMatch && postMatch[1]) {
+    return { type: "post", shortcode: postMatch[1] };
+  }
+  const hashtagMatch = url.match(HASHTAG_URL_REGEX);
+  if (hashtagMatch && hashtagMatch[1]) {
+    return { type: "hashtag", hashtag: hashtagMatch[1] };
+  }
+  const profileMatch = url.match(PROFILE_URL_REGEX);
+  if (profileMatch && profileMatch[1]) {
+    const nonProfilePaths = [
+      "explore",
+      "accounts",
+      "directory",
+      "about",
+      "legal",
+      "developer",
+      "stories"
+    ];
+    if (!nonProfilePaths.includes(profileMatch[1].toLowerCase())) {
+      return { type: "profile", username: profileMatch[1] };
+    }
+  }
+  return { type: "unknown" };
+}
+function extractShortcode(url) {
+  const match = url.match(POST_URL_REGEX);
+  return match ? match[1] : null;
+}
+function extractUsername(url) {
+  const parsed = parseInstagramUrl(url);
+  return parsed.type === "profile" ? parsed.username ?? null : null;
+}
+function extractHashtagFromUrl(url) {
+  const match = url.match(HASHTAG_URL_REGEX);
+  return match ? match[1] : null;
+}
 function ellipsifyCaption(caption) {
   const pcaption = caption.split("\n").filter((s) => s).map((s) => s.replace(/\//g, "\u2215")).join(" ").trim();
   return pcaption.length > 31 ? pcaption.slice(0, 30) + "\u2026" : pcaption;
@@ -3212,7 +3323,9 @@ var Instaloader = class {
       ...options.sleep !== void 0 && { sleep: options.sleep },
       ...options.quiet !== void 0 && { quiet: options.quiet },
       ...options.userAgent !== void 0 && { userAgent: options.userAgent },
-      ...options.maxConnectionAttempts !== void 0 && { maxConnectionAttempts: options.maxConnectionAttempts },
+      ...options.maxConnectionAttempts !== void 0 && {
+        maxConnectionAttempts: options.maxConnectionAttempts
+      },
       ...options.requestTimeout !== void 0 && { requestTimeout: options.requestTimeout },
       ...options.rateController !== void 0 && { rateController: options.rateController },
       ...options.fatalStatusCodes !== void 0 && { fatalStatusCodes: options.fatalStatusCodes },
@@ -3317,7 +3430,7 @@ var Instaloader = class {
    * Load session from file.
    */
   async loadSessionFromFile(username, filename) {
-    let targetFile = filename ?? getDefaultSessionFilename(username);
+    const targetFile = filename ?? getDefaultSessionFilename(username);
     if (!fs.existsSync(targetFile)) {
       throw new Error(`Session file not found: ${targetFile}`);
     }
@@ -3372,7 +3485,9 @@ var Instaloader = class {
       }
     });
     if (!response.ok) {
-      throw new ConnectionException(`Failed to download: ${response.status} ${response.statusText}`);
+      throw new ConnectionException(
+        `Failed to download: ${response.status} ${response.statusText}`
+      );
     }
     let finalFilename = nominalFilename;
     const contentType = response.headers.get("Content-Type");
@@ -3471,11 +3586,21 @@ var Instaloader = class {
           }
           if (node.is_video) {
             if (this.downloadVideos && node.video_url) {
-              const dl = await this.downloadPic(filename, node.video_url, post.date_utc, `${index + 1}`);
+              const dl = await this.downloadPic(
+                filename,
+                node.video_url,
+                post.date_utc,
+                `${index + 1}`
+              );
               downloaded = downloaded || dl;
             }
           } else if (node.display_url) {
-            const dl = await this.downloadPic(filename, node.display_url, post.date_utc, `${index + 1}`);
+            const dl = await this.downloadPic(
+              filename,
+              node.display_url,
+              post.date_utc,
+              `${index + 1}`
+            );
             downloaded = downloaded || dl;
           }
           index++;
@@ -3532,7 +3657,10 @@ var Instaloader = class {
       }
       if (displayedCount !== void 0) {
         const width = displayedCount.toString().length;
-        this.context.log(`[${number.toString().padStart(width)}/${displayedCount.toString().padStart(width)}] `, false);
+        this.context.log(
+          `[${number.toString().padStart(width)}/${displayedCount.toString().padStart(width)}] `,
+          false
+        );
       } else {
         this.context.log(`[${number.toString().padStart(3)}] `, false);
       }
@@ -3614,7 +3742,12 @@ var Instaloader = class {
   async downloadProfilePic(profile) {
     const url = await profile.getProfilePicUrl();
     if (!url) return;
-    const dirname2 = formatFilename(this.dirnamePattern, profile, profile.username.toLowerCase(), this.sanitizePaths);
+    const dirname2 = formatFilename(
+      this.dirnamePattern,
+      profile,
+      profile.username.toLowerCase(),
+      this.sanitizePaths
+    );
     const filename = path.join(dirname2, `${profile.username.toLowerCase()}_profile_pic`);
     await this.downloadPic(filename, url, /* @__PURE__ */ new Date());
     this.context.log("");
@@ -3710,8 +3843,11 @@ var Instaloader = class {
   TwoFactorAuthRequiredException,
   defaultIphoneHeaders,
   defaultUserAgent,
+  extractHashtagFromUrl,
   extractHashtags,
   extractMentions,
+  extractShortcode,
+  extractUsername,
   formatFilename,
   formatStringContainsKey,
   getConfigDir,
@@ -3720,6 +3856,7 @@ var Instaloader = class {
   getJsonStructure,
   loadStructure,
   mediaidToShortcode,
+  parseInstagramUrl,
   resumableIteration,
   sanitizePath,
   shortcodeToMediaid