ronin-web-spider 0.2.0.rc1 → 0.2.0.rc3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e1637185a37e17f587cab3bb0ec451dfa763ab58b167404ec5b1161a4a80316f
-  data.tar.gz: ea11da89c3c232feaca90c103c45cdb653eac9b94c6c97be34998d6b5089e896
+  metadata.gz: ab74fe34ec9f37cba9a8269fa6df15cd4f5404d8b01904ead735fe7d98159ace
+  data.tar.gz: 0d8547dfdd92cef99193fe79c5a944500adb04ab80c6c0a89b000f727e5fafbe
 SHA512:
-  metadata.gz: 4d2f5ac7b650096856b87f5e37cf42044a12db416eab2375715a39073606a1f4c30103fda27cb1faaf9a53533bdf323ae9912787078f24f120366fb519a3b4a1
-  data.tar.gz: b2ae98ce51187a5a65cd2355816b98d1916edb0d731f158e83a9366ec70261ef2e3eae9d5f3abe95b311a766c489064f855b4ee6afa4606592a5f9b560fbcb9d
+  metadata.gz: 0e10c97975ce2dd40b80ec204ac39f2fcecb74ee62af2dd0758e662214c5ce806352107309ece72fd38b0724e8de5e022692661a987975e6bb6266162d958749
+  data.tar.gz: 619387f4795f1efcea2d88e3e06162a05f33aabe9b1cae4da1267e5106ad94e97475e3078ae39497a2616f0636dfa362cc902185f9fc30b9683ca8c92c63d7ae

data/README.md

@@ -32,6 +32,14 @@ ronin-web-spider is a collection of common web spidering routines using the
   * [every_javascript_string][docs-every_javascript_string] - yields every
     single-quoted or double-quoted String literal from all JavaScript source
     code.
+  * [every_javascript_relative_path_string][docs-every_javascript_relative_path_string] -
+    yields every relative path JavaScript string (ex: `foo/bar`).
+  * [every_javascript_absolute_path_string][docs-every_javascript_absolute_path_string] -
+    yields every relative path JavaScript string (ex: `/foo/bar`).
+  * [every_javascript_path_string][docs-every_javascript_path_string] -
+    yields every relative path JavaScript string (ex: `foo/bar` or `/foo/bar`).
+  * [every_javascript_url_string][docs-every_javascript_url_string] -
+    yields every URL JavaScript string (ex: `https://example.com/foo/bar`).
   * [every_javascript_comment][docs-every_javascript_comment] - yields every
     JavaScript comment.
   * [every_comment][docs-every_comment] - yields every HTML or JavaScript
@@ -46,6 +54,10 @@ ronin-web-spider is a collection of common web spidering routines using the
 [docs-every_html_comment]: https://ronin-rb.dev/docs/ronin-web-spider/Ronin/Web/Spider/Agent.html#every_html_comment-instance_method
 [docs-every_javascript]: https://ronin-rb.dev/docs/ronin-web-spider/Ronin/Web/Spider/Agent.html#every_javascript-instance_method
 [docs-every_javascript_string]: https://ronin-rb.dev/docs/ronin-web-spider/Ronin/Web/Spider/Agent.html#every_javascript_string-instance_method
+[docs-every_javascript_relative_path_string]: https://ronin-rb.dev/docs/ronin-web-spider/Ronin/Web/Spider/Agent.html#every_javascript_relative_path_string-instance_method
+[docs-every_javascript_absolute_path_string]: https://ronin-rb.dev/docs/ronin-web-spider/Ronin/Web/Spider/Agent.html#every_javascript_absolute_path_string-instance_method
+[docs-every_javascript_path_string]: https://ronin-rb.dev/docs/ronin-web-spider/Ronin/Web/Spider/Agent.html#every_javascript_path_string-instance_method
+[docs-every_javascript_url_string]: https://ronin-rb.dev/docs/ronin-web-spider/Ronin/Web/Spider/Agent.html#every_javascript_url_string-instance_method
 [docs-every_javascript_comment]: https://ronin-rb.dev/docs/ronin-web-spider/Ronin/Web/Spider/Agent.html#every_javascript_comment-instance_method
 [docs-every_comment]: https://ronin-rb.dev/docs/ronin-web-spider/Ronin/Web/Spider/Agent.html#every_comment-instance_method
 

data/lib/ronin/web/spider/agent.rb

@@ -325,9 +325,9 @@ module Ronin
         # @api private
         #
         # @since 0.1.1
-        JAVASCRIPT_INLINE_REGEX = %r{
+        JAVASCRIPT_INLINE_REGEX_REGEX = %r{
           (?# match before the regex to avoid matching division operators )
-          (?:[\{\[\(;:,]\s*|=\s*)
+          (?:[\{\[\(;:,]\s*|=\s*|return\s*)
           /
             (?# inline regex contents )
             (?:
@@ -350,7 +350,7 @@ module Ronin
         # @api private
         #
         # @since 0.1.1
-        JAVASCRIPT_TEMPLATE_LITERAL = /`(?:\\`|[^`])+`/m
+        JAVASCRIPT_TEMPLATE_LITERAL_REGEX = /`(?:\\`|[^`])+`/m
 
         #
         # Passes every JavaScript string value to the given block.
@@ -395,8 +395,8 @@ module Ronin
                   yield string
                 end
               else
-                scanner.skip(JAVASCRIPT_INLINE_REGEX) ||
-                  scanner.skip(JAVASCRIPT_TEMPLATE_LITERAL) ||
+                scanner.skip(JAVASCRIPT_INLINE_REGEX_REGEX) ||
+                  scanner.skip(JAVASCRIPT_TEMPLATE_LITERAL_REGEX) ||
                   scanner.getch
               end
             end
@@ -410,7 +410,11 @@ module Ronin
         # @note
         #   This matches `foo/bar`, `foo/bar.ext`, `../foo`, and `foo.ext`,
         #   but *not* `/foo`, `foo`, or `foo.`.
-        JAVASCRIPT_RELATIVE_PATH = %r{
+        #
+        # @api private
+        #
+        # @since 0.2.0
+        JAVASCRIPT_RELATIVE_PATH_REGEX = %r{
           \A
             (?:
                [^/\\. ]+\.[a-z0-9]+ (?# filename.ext)
@@ -450,7 +454,7 @@ module Ronin
         #
         def every_javascript_relative_path_string(&block)
           every_javascript_string do |string,page|
-            if string =~ JAVASCRIPT_RELATIVE_PATH
+            if string =~ JAVASCRIPT_RELATIVE_PATH_REGEX
               if block.arity == 2
                 yield string, page
               else
@@ -463,7 +467,11 @@ module Ronin
         alias every_js_relative_path_string every_javascript_relative_path_string
 
         # Regular expression that matches absolute paths within JavaScript.
-        JAVASCRIPT_ABSOLUTE_PATH = %r{\A(?:/[^/\\ ]+)+\z}
+        #
+        # @api private
+        #
+        # @since 0.2.0
+        JAVASCRIPT_ABSOLUTE_PATH_REGEX = %r{\A(?:/[^/\\ ]+)+\z}
 
         #
         # Passes every JavaScript absolute path string to the given block.
@@ -495,7 +503,7 @@ module Ronin
         #
         def every_javascript_absolute_path_string(&block)
           every_javascript_string do |string,page|
-            if string =~ JAVASCRIPT_ABSOLUTE_PATH
+            if string =~ JAVASCRIPT_ABSOLUTE_PATH_REGEX
               if block.arity == 2
                 yield string, page
               else
@@ -541,6 +549,13 @@ module Ronin
 
         alias every_js_path_string every_javascript_path_string
 
+        # Regular expression for identifying URLs.
+        #
+        # @api private
+        #
+        # @since 0.2.0
+        URL_REGEX = /\A#{Support::Text::Patterns::URL}\z/
+
         #
         # Passes every JavaScript URL string to the given block.
         #
@@ -570,7 +585,7 @@ module Ronin
         #
         def every_javascript_url_string(&block)
           every_javascript_string do |string,page|
-            if string =~ Support::Text::Patterns::URL
+            if string =~ URL_REGEX
               if block.arity == 2
                 yield string, page
               else

data/lib/ronin/web/spider/version.rb

@@ -22,7 +22,7 @@ module Ronin
   module Web
     module Spider
       # ronin-web-spider version
-      VERSION = '0.2.0.rc1'
+      VERSION = '0.2.0.rc3'
     end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ronin-web-spider
 version: !ruby/object:Gem::Version
-  version: 0.2.0.rc1
+  version: 0.2.0.rc3
 platform: ruby
 authors:
 - Postmodern
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-06-23 00:00:00.000000000 Z
+date: 2024-07-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: spidr