curl_impersonate 0.1.1

data/ext/curl_impersonate/include/curl/urlapi.h

@@ -0,0 +1,155 @@
+#ifndef CURLINC_URLAPI_H
+#define CURLINC_URLAPI_H
+/***************************************************************************
+ *                                  _   _ ____  _
+ *  Project                     ___| | | |  _ \| |
+ *                             / __| | | | |_) | |
+ *                            | (__| |_| |  _ <| |___
+ *                             \___|\___/|_| \_\_____|
+ *
+ * Copyright (C) Daniel Stenberg, <daniel@haxx.se>, et al.
+ *
+ * This software is licensed as described in the file COPYING, which
+ * you should have received as part of this distribution. The terms
+ * are also available at https://curl.se/docs/copyright.html.
+ *
+ * You may opt to use, copy, modify, merge, publish, distribute and/or sell
+ * copies of the Software, and permit persons to whom the Software is
+ * furnished to do so, under the terms of the COPYING file.
+ *
+ * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
+ * KIND, either express or implied.
+ *
+ * SPDX-License-Identifier: curl
+ *
+ ***************************************************************************/
+
+#include "curl.h"
+
+#ifdef  __cplusplus
+extern "C" {
+#endif
+
+/* the error codes for the URL API */
+typedef enum {
+  CURLUE_OK,
+  CURLUE_BAD_HANDLE,          /* 1 */
+  CURLUE_BAD_PARTPOINTER,     /* 2 */
+  CURLUE_MALFORMED_INPUT,     /* 3 */
+  CURLUE_BAD_PORT_NUMBER,     /* 4 */
+  CURLUE_UNSUPPORTED_SCHEME,  /* 5 */
+  CURLUE_URLDECODE,           /* 6 */
+  CURLUE_OUT_OF_MEMORY,       /* 7 */
+  CURLUE_USER_NOT_ALLOWED,    /* 8 */
+  CURLUE_UNKNOWN_PART,        /* 9 */
+  CURLUE_NO_SCHEME,           /* 10 */
+  CURLUE_NO_USER,             /* 11 */
+  CURLUE_NO_PASSWORD,         /* 12 */
+  CURLUE_NO_OPTIONS,          /* 13 */
+  CURLUE_NO_HOST,             /* 14 */
+  CURLUE_NO_PORT,             /* 15 */
+  CURLUE_NO_QUERY,            /* 16 */
+  CURLUE_NO_FRAGMENT,         /* 17 */
+  CURLUE_NO_ZONEID,           /* 18 */
+  CURLUE_BAD_FILE_URL,        /* 19 */
+  CURLUE_BAD_FRAGMENT,        /* 20 */
+  CURLUE_BAD_HOSTNAME,        /* 21 */
+  CURLUE_BAD_IPV6,            /* 22 */
+  CURLUE_BAD_LOGIN,           /* 23 */
+  CURLUE_BAD_PASSWORD,        /* 24 */
+  CURLUE_BAD_PATH,            /* 25 */
+  CURLUE_BAD_QUERY,           /* 26 */
+  CURLUE_BAD_SCHEME,          /* 27 */
+  CURLUE_BAD_SLASHES,         /* 28 */
+  CURLUE_BAD_USER,            /* 29 */
+  CURLUE_LACKS_IDN,           /* 30 */
+  CURLUE_TOO_LARGE,           /* 31 */
+  CURLUE_LAST
+} CURLUcode;
+
+typedef enum {
+  CURLUPART_URL,
+  CURLUPART_SCHEME,
+  CURLUPART_USER,
+  CURLUPART_PASSWORD,
+  CURLUPART_OPTIONS,
+  CURLUPART_HOST,
+  CURLUPART_PORT,
+  CURLUPART_PATH,
+  CURLUPART_QUERY,
+  CURLUPART_FRAGMENT,
+  CURLUPART_ZONEID /* added in 7.65.0 */
+} CURLUPart;
+
+#define CURLU_DEFAULT_PORT (1<<0)       /* return default port number */
+#define CURLU_NO_DEFAULT_PORT (1<<1)    /* act as if no port number was set,
+                                           if the port number matches the
+                                           default for the scheme */
+#define CURLU_DEFAULT_SCHEME (1<<2)     /* return default scheme if
+                                           missing */
+#define CURLU_NON_SUPPORT_SCHEME (1<<3) /* allow non-supported scheme */
+#define CURLU_PATH_AS_IS (1<<4)         /* leave dot sequences */
+#define CURLU_DISALLOW_USER (1<<5)      /* no user+password allowed */
+#define CURLU_URLDECODE (1<<6)          /* URL decode on get */
+#define CURLU_URLENCODE (1<<7)          /* URL encode on set */
+#define CURLU_APPENDQUERY (1<<8)        /* append a form style part */
+#define CURLU_GUESS_SCHEME (1<<9)       /* legacy curl-style guessing */
+#define CURLU_NO_AUTHORITY (1<<10)      /* Allow empty authority when the
+                                           scheme is unknown. */
+#define CURLU_ALLOW_SPACE (1<<11)       /* Allow spaces in the URL */
+#define CURLU_PUNYCODE (1<<12)          /* get the hostname in punycode */
+#define CURLU_PUNY2IDN (1<<13)          /* punycode => IDN conversion */
+#define CURLU_GET_EMPTY (1<<14)         /* allow empty queries and fragments
+                                           when extracting the URL or the
+                                           components */
+#define CURLU_NO_GUESS_SCHEME (1<<15)   /* for get, do not accept a guess */
+
+typedef struct Curl_URL CURLU;
+
+/*
+ * curl_url() creates a new CURLU handle and returns a pointer to it.
+ * Must be freed with curl_url_cleanup().
+ */
+CURL_EXTERN CURLU *curl_url(void);
+
+/*
+ * curl_url_cleanup() frees the CURLU handle and related resources used for
+ * the URL parsing. It will not free strings previously returned with the URL
+ * API.
+ */
+CURL_EXTERN void curl_url_cleanup(CURLU *handle);
+
+/*
+ * curl_url_dup() duplicates a CURLU handle and returns a new copy. The new
+ * handle must also be freed with curl_url_cleanup().
+ */
+CURL_EXTERN CURLU *curl_url_dup(const CURLU *in);
+
+/*
+ * curl_url_get() extracts a specific part of the URL from a CURLU
+ * handle. Returns error code. The returned pointer MUST be freed with
+ * curl_free() afterwards.
+ */
+CURL_EXTERN CURLUcode curl_url_get(const CURLU *handle, CURLUPart what,
+                                   char **part, unsigned int flags);
+
+/*
+ * curl_url_set() sets a specific part of the URL in a CURLU handle. Returns
+ * error code. The passed in string will be copied. Passing a NULL instead of
+ * a part string, clears that part.
+ */
+CURL_EXTERN CURLUcode curl_url_set(CURLU *handle, CURLUPart what,
+                                   const char *part, unsigned int flags);
+
+/*
+ * curl_url_strerror() turns a CURLUcode value into the equivalent human
+ * readable error string. This is useful for printing meaningful error
+ * messages.
+ */
+CURL_EXTERN const char *curl_url_strerror(CURLUcode);
+
+#ifdef __cplusplus
+} /* end of extern "C" */
+#endif
+
+#endif /* CURLINC_URLAPI_H */

data/ext/curl_impersonate/include/curl/websockets.h

@@ -0,0 +1,85 @@
+#ifndef CURLINC_WEBSOCKETS_H
+#define CURLINC_WEBSOCKETS_H
+/***************************************************************************
+ *                                  _   _ ____  _
+ *  Project                     ___| | | |  _ \| |
+ *                             / __| | | | |_) | |
+ *                            | (__| |_| |  _ <| |___
+ *                             \___|\___/|_| \_\_____|
+ *
+ * Copyright (C) Daniel Stenberg, <daniel@haxx.se>, et al.
+ *
+ * This software is licensed as described in the file COPYING, which
+ * you should have received as part of this distribution. The terms
+ * are also available at https://curl.se/docs/copyright.html.
+ *
+ * You may opt to use, copy, modify, merge, publish, distribute and/or sell
+ * copies of the Software, and permit persons to whom the Software is
+ * furnished to do so, under the terms of the COPYING file.
+ *
+ * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
+ * KIND, either express or implied.
+ *
+ * SPDX-License-Identifier: curl
+ *
+ ***************************************************************************/
+
+#ifdef  __cplusplus
+extern "C" {
+#endif
+
+struct curl_ws_frame {
+  int age;              /* zero */
+  int flags;            /* See the CURLWS_* defines */
+  curl_off_t offset;    /* the offset of this data into the frame */
+  curl_off_t bytesleft; /* number of pending bytes left of the payload */
+  size_t len;           /* size of the current data chunk */
+};
+
+/* flag bits */
+#define CURLWS_TEXT       (1<<0)
+#define CURLWS_BINARY     (1<<1)
+#define CURLWS_CONT       (1<<2)
+#define CURLWS_CLOSE      (1<<3)
+#define CURLWS_PING       (1<<4)
+#define CURLWS_OFFSET     (1<<5)
+
+/*
+ * NAME curl_ws_recv()
+ *
+ * DESCRIPTION
+ *
+ * Receives data from the websocket connection. Use after successful
+ * curl_easy_perform() with CURLOPT_CONNECT_ONLY option.
+ */
+CURL_EXTERN CURLcode curl_ws_recv(CURL *curl, void *buffer, size_t buflen,
+                                  size_t *recv,
+                                  const struct curl_ws_frame **metap);
+
+/* flags for curl_ws_send() */
+#define CURLWS_PONG       (1<<6)
+
+/*
+ * NAME curl_ws_send()
+ *
+ * DESCRIPTION
+ *
+ * Sends data over the websocket connection. Use after successful
+ * curl_easy_perform() with CURLOPT_CONNECT_ONLY option.
+ */
+CURL_EXTERN CURLcode curl_ws_send(CURL *curl, const void *buffer,
+                                  size_t buflen, size_t *sent,
+                                  curl_off_t fragsize,
+                                  unsigned int flags);
+
+/* bits for the CURLOPT_WS_OPTIONS bitmask: */
+#define CURLWS_RAW_MODE   (1<<0)
+#define CURLWS_NOAUTOPONG (1<<1)
+
+CURL_EXTERN const struct curl_ws_frame *curl_ws_meta(CURL *curl);
+
+#ifdef  __cplusplus
+}
+#endif
+
+#endif /* CURLINC_WEBSOCKETS_H */

data/lib/curl_impersonate/cookies.rb

@@ -0,0 +1,22 @@
+module CurlImpersonate
+  # Extracts cookies from a raw HTTP header string (the value of Response#headers).
+  # Returns a Hash<String, String>; later Set-Cookie lines with the same name
+  # overwrite earlier ones (matches the Go reference implementation).
+  #
+  # Only the cookie name/value pair is kept — attributes such as Path, Domain,
+  # Expires, Secure are discarded.
+  def self.extract_cookies(headers_str)
+    cookies = {}
+    return cookies if headers_str.nil? || headers_str.empty?
+
+    headers_str.split(/\r?\n/).each do |line|
+      next unless line.downcase.start_with?("set-cookie:")
+      pair = line[("set-cookie:".length)..].split(";", 2).first.to_s.strip
+      next if pair.empty?
+      name, value = pair.split("=", 2)
+      cookies[name] = value.to_s if name && !name.empty?
+    end
+
+    cookies
+  end
+end

data/lib/curl_impersonate/response.rb

@@ -0,0 +1,7 @@
+module CurlImpersonate
+  Response = Struct.new(:status_code, :body, :headers) do
+    def success?
+      (200..299).cover?(status_code)
+    end
+  end
+end

data/lib/curl_impersonate/version.rb

@@ -0,0 +1,3 @@
+module CurlImpersonate
+  VERSION = "0.1.1"
+end

data/lib/curl_impersonate.rb

@@ -0,0 +1,61 @@
+require "curl_impersonate/version"
+
+module CurlImpersonate
+  class Error < StandardError; end
+end
+
+require "curl_impersonate/response"
+require "curl_impersonate/cookies"
+
+# The C extension grabs CurlImpersonate::Error and CurlImpersonate::Response
+# via rb_const_get during Init, so both must be defined before this require.
+require "curl_impersonate/curl_impersonate"
+
+module CurlImpersonate
+  DEFAULT_IMPERSONATE = "chrome131".freeze
+  DEFAULT_TIMEOUT_SEC = 15
+
+  def self.do_request(url:,
+                      impersonate: DEFAULT_IMPERSONATE,
+                      headers: {},
+                      post_data: "",
+                      follow_redirects: true,
+                      timeout_sec: DEFAULT_TIMEOUT_SEC,
+                      proxy: "")
+    string_headers = headers.each_with_object({}) { |(k, v), h| h[k.to_s] = v.to_s }
+    proxy_url, proxy_userpwd = parse_proxy(proxy.to_s)
+    _do_request_native(
+      url.to_s,
+      impersonate.to_s,
+      string_headers,
+      post_data.to_s,
+      follow_redirects ? true : false,
+      Integer(timeout_sec),
+      proxy_url,
+      proxy_userpwd,
+    )
+  end
+
+  # Split "scheme://user:pass@host:port" into ("scheme://host:port", "user:pass").
+  # Returns ("", "") for empty input. If there is no "@" the whole string is
+  # treated as the proxy URL with empty auth. Port-only or scheme-less inputs
+  # are passed through to libcurl, which has its own defaulting logic.
+  def self.parse_proxy(proxy)
+    return ["", ""] if proxy.nil? || proxy.empty?
+
+    scheme = ""
+    rest = proxy
+    if (idx = proxy.index("://"))
+      scheme = proxy[0..(idx + 2)]
+      rest = proxy[(idx + 3)..]
+    end
+
+    if (idx = rest.rindex("@"))
+      auth = rest[0...idx]
+      host = rest[(idx + 1)..]
+      [scheme + host, auth]
+    else
+      [proxy, ""]
+    end
+  end
+end

metadata

@@ -0,0 +1,124 @@
+--- !ruby/object:Gem::Specification
+name: curl_impersonate
+version: !ruby/object:Gem::Version
+  version: 0.1.1
+platform: ruby
+authors:
+- TeamMilestone
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2026-05-27 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
+- !ruby/object:Gem::Dependency
+  name: rake-compiler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.2'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.2'
+- !ruby/object:Gem::Dependency
+  name: rake-compiler-dock
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.5'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.5'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.12'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.12'
+description: Generate real-browser TLS/JA3 fingerprints from Ruby by calling the BoringSSL-backed
+  libcurl-impersonate C library.
+email:
+- alfonso@team-milestone.io
+executables: []
+extensions:
+- ext/curl_impersonate/extconf.rb
+extra_rdoc_files: []
+files:
+- LICENSE
+- README.md
+- ext/curl_impersonate/curl_impersonate.c
+- ext/curl_impersonate/extconf.rb
+- ext/curl_impersonate/include/curl/curl.h
+- ext/curl_impersonate/include/curl/curlver.h
+- ext/curl_impersonate/include/curl/easy.h
+- ext/curl_impersonate/include/curl/header.h
+- ext/curl_impersonate/include/curl/mprintf.h
+- ext/curl_impersonate/include/curl/multi.h
+- ext/curl_impersonate/include/curl/options.h
+- ext/curl_impersonate/include/curl/stdcheaders.h
+- ext/curl_impersonate/include/curl/system.h
+- ext/curl_impersonate/include/curl/typecheck-gcc.h
+- ext/curl_impersonate/include/curl/urlapi.h
+- ext/curl_impersonate/include/curl/websockets.h
+- lib/curl_impersonate.rb
+- lib/curl_impersonate/cookies.rb
+- lib/curl_impersonate/response.rb
+- lib/curl_impersonate/version.rb
+homepage: https://github.com/TeamMilestone/ruby-curl-impersonate
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/TeamMilestone/ruby-curl-impersonate
+  source_code_uri: https://github.com/TeamMilestone/ruby-curl-impersonate
+  bug_tracker_uri: https://github.com/TeamMilestone/ruby-curl-impersonate/issues
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '3.0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.5.22
+signing_key:
+specification_version: 4
+summary: Ruby bindings for libcurl-impersonate — browser-identical TLS fingerprints
+test_files: []