Merge pull request #133 from InQuest/dev

Trevor · web-flow · commit 9c541e5c73e4 · 2023-02-20T05:34:17.000-06:00
v1.0.3
diff --git a/config.example.yml b/config.example.yml
@@ -75,9 +75,38 @@ sources:
     url: https://inquest.net/blog/rss
     feed_type: messy
 
-  - name: inquest-blog
+  # Sitemap exmaples
+
+  # Searches for "articles" keyword
+  - name: inquest-sitemap-articles
+    module: sitemap
+    url: https://www.inquest.net/sitemap.xml
+    filter: articles
+
+  # Defaults to "blog" keyword
+  - name: inquest-sitemap-blog
+    module: sitemap
+    url: https://www.inquest.net/sitemap.xml
+
+  # Searches for "articles or security" keywords
+  - name: inquest-sitemap-blog-articles-security
+    module: sitemap
+    url: https://www.inquest.net/sitemap.xml
+    filter: articles|security
+
+  # Specify directories in the filter
+  - name: inquest-sitemap-blog-category
+    module: sitemap
+    url: https://www.inquest.net/sitemap.xml
+    path: /blog/category/
+
+  # Specify filtering for paths
+  # Only returns results under /blog/category/release|solutions
+  - name: inquest-sitemap-release-solutions
     module: sitemap
-    url: https://inquest.net/sitemap.xml
+    url: https://www.inquest.net/sitemap.xml
+    path: /blog/category/
+    filter: release|solutions
 
   - name: image-extraction
     module: image
diff --git a/docs/_static/logo.png b/docs/_static/logo.png
diff --git a/docs/_templates/links.html b/docs/_templates/links.html
@@ -31,8 +31,9 @@ <h3>Other Projects</h3>
 <ul>
     <li><a href="https://github.com/InQuest/ThreatKB">ThreatKB</a></li>
     <li><a href="https://github.com/InQuest/python-iocextract">iocextract</a></li>
-    <li><a href="https://github.com/InQuest/omnibus">Omnibus</a></li>
     <li><a href="https://github.com/InQuest/python-sandboxapi">sandboxapi</a></li>
+    <li><a href="https://github.com/InQuest/python-inquestlabs">inquestlabs
+    </a></li>
 </ul>
 
 <h3>Useful Links</h3>
@@ -46,24 +47,40 @@ <h3>Useful Links</h3>
 <h3>Stay Informed</h3>
 
 <ul>
+    <li>
+        <a href="https://labs.inquest.net/">
+            <img src="_static/logo.png" width="4%" alt="InQuest logo">
+            InQuest Labs
+        </a>
+    </li>
+    <li>
+        <a href="https://inquest.net/newsletter">
+            <img src="_static/logo.png" width="4%" alt="InQuest logo">
+            InQuest Newsletter
+        </a>
+    </li>
     <li>
         <a href="http://blog.inquest.net/">
-            <svg class="icon icon-rss"><use xlink:href="#icon-rss"></use></svg> InQuest Blog
+            <svg class="icon icon-rss"><use xlink:href="#icon-rss"></use></svg>
+            InQuest Blog
         </a>
     </li>
     <li>
         <a href="https://twitter.com/InQuest">
-            <svg class="icon icon-twitter"><use xlink:href="#icon-twitter"></use></svg> Twitter
+            <svg class="icon icon-twitter"><use xlink:href="#icon-twitter"></use></svg>
+            Twitter
         </a>
     </li>
     <li>
         <a href="https://www.linkedin.com/company/inquest.net">
-            <svg class="icon icon-linkedin"><use xlink:href="#icon-linkedin"></use></svg> LinkedIn
+            <svg class="icon icon-linkedin"><use xlink:href="#icon-linkedin"></use></svg>
+            LinkedIn
         </a>
     </li>
     <li>
         <a href="https://github.com/InQuest">
-            <svg class="icon icon-github"><use xlink:href="#icon-github"></use></svg> GitHub
+            <svg class="icon icon-github"><use xlink:href="#icon-github"></use></svg>
+            GitHub
         </a>
     </li>
 </ul>
diff --git a/docs/api.rst b/docs/api.rst
@@ -168,7 +168,7 @@ github
    :member-order: bysource
 
 github_gist
-^^^^^^
+^^^^^^^^^^^
 
 .. automodule:: threatingestor.sources.github_gist
    :members:
diff --git a/docs/conf.py b/docs/conf.py
@@ -20,7 +20,7 @@
 # -- Project information -----------------------------------------------------
 
 project = u'ThreatIngestor'
-copyright = u'2019 InQuest, LLC'
+copyright = u'2019 - 2023 InQuest, LLC'
 author = u'InQuest Labs'
 
 # The short X.Y version
diff --git a/docs/sources/github_gist.rst b/docs/sources/github_gist.rst
@@ -1,9 +1,9 @@
 .. _github-gist-source:
 
 GitHub Gist Username Search
-------------------------
+---------------------------
 
-The **GitHub Gist** source plugin uses GitHub's `gist API`_ to find new gists created by a user, and create a :ref:`Task artifact <task-artifact>` for each.
+The **GitHub Gist** source plugin uses GitHub's gist API to find new gists created by a user, and create a :ref:`Task artifact <task-artifact>` for each.
 
 Configuration Options
 ~~~~~~~~~~~~~~~~~~~~~
diff --git a/requirements-testing.txt b/requirements-testing.txt
@@ -15,3 +15,4 @@ twitter>=1.17.1
 feedparser>=5.2.1
 threatkb
 pymysql
+pyshorteners
diff --git a/requirements.txt b/requirements.txt
@@ -10,3 +10,4 @@ requests
 pytesseract
 numpy
 opencv-python
+pyshorteners
diff --git a/setup.py b/setup.py
@@ -20,7 +20,7 @@
 
 setup(
     name='threatingestor',
-    version='1.0.2',
+    version='1.0.3',
     include_package_data=True,
     install_requires=requires,
     extras_require={
diff --git a/threatingestor/sources/sitemap.py b/threatingestor/sources/sitemap.py
@@ -2,14 +2,17 @@
 import urllib.request
 from urllib.parse import urlparse
 from bs4 import BeautifulSoup
+import regex as re
 
 from threatingestor.sources import Source
 
 class Plugin(Source):
     
-    def __init__(self, name, url):
+    def __init__(self, name, url, filter=None, path=None):
         self.name = name
         self.url = url
+        self.filter = filter
+        self.path = path
 
     def run(self, saved_state):
         saved_state = datetime.datetime.utcnow().isoformat()[:-7] + "Z"
@@ -58,9 +61,35 @@ def run(self, saved_state):
                     "loc": loc
                 }
 
-                # Locates all blog links within the sitemap
-                if "blog" in row["loc"]:
-                    print(row["loc"])
-                    artifacts += self.process_element(row["loc"], self.url)
+                if self.filter is not None:
+                    # Regex input via config.yml
+                    xml_query = re.compile(r"{0}".format(self.filter)).findall(str(self.filter.split('|')))
+
+                    # Iterates over the regex output to locate all provided keywords
+                    for x in xml_query:
+                        # Uses a path instead of a keyword
+                        if self.path is not None:
+                            provided_path = f"{self.path}{x}"
+
+                            if provided_path in row["loc"]:
+                                artifacts += self.process_element(row["loc"], self.url)
+                        
+                        # Only filters using a keyword
+                        if self.path is None:
+                            if x in row["loc"]:
+                                artifacts += self.process_element(row["loc"], self.url)
+                
+                elif self.filter is None and self.path is not None:
+                    # Filters only by path in XML loc, no set filter
+                    # Default: /path/name/*
+                    provided_path = f"{self.path}"
+
+                    if provided_path in row["loc"]:
+                        artifacts += self.process_element(row["loc"], self.url)
+                
+                else:
+                    # Locates all blog links within the sitemap
+                    if "blog" in row["loc"]:
+                        artifacts += self.process_element(row["loc"], self.url)
         
         return saved_state, artifacts
diff --git a/threatingestor/sources/twitter.py b/threatingestor/sources/twitter.py
@@ -4,13 +4,11 @@
 import twitter
 from loguru import logger
 
-
 from threatingestor.sources import Source
-
+from threatingestor.utils.url_controller import UrlController
 
 TWEET_URL = 'https://twitter.com/{user}/status/{id}'
 
-
 class Plugin(Source):
 
     def __init__(self, name, api_key, api_secret_key, access_token, access_token_secret, defanged_only=True, **kwargs):
@@ -85,8 +83,8 @@ def run(self, saved_state):
                 try:
                     tweet['content'] = tweet['content'].replace(url['url'], url['expanded_url'])
                 except KeyError:
-                    # No url/expanded_url, continue without expanding.
-                    pass
+                    # Attempts to expand the URL if not available through Twitter
+                    tweet['content'] = tweet['content'].replace(url['url'], UrlController.expand_url(url['url']))
 
             # Process tweet.
             saved_state = tweet['id']
diff --git a/threatingestor/sources/twitter_follow_links.py b/threatingestor/sources/twitter_follow_links.py
@@ -1,18 +1,16 @@
 from __future__ import absolute_import
 
-
 import re
 import requests
 import twitter
 from loguru import logger
-from threatingestor.sources import Source
 
+from threatingestor.sources import Source
+from threatingestor.utils.url_controller import UrlController
 
 TWEET_URL = 'https://twitter.com/{user}/status/{id}'
-
 WHITELIST_DOMAINS = r"pastebin\.com"
 
-
 class Plugin(Source):
 
     def __init__(self, name, api_key, api_secret_key, access_token, access_token_secret, defanged_only=True, **kwargs):
@@ -97,8 +95,8 @@ def run(self, saved_state):
                         logger.log('NOTIFY', f"Discovered paste: {location}")
 
                 except KeyError:
-                    # No url/expanded_url, continue without expanding.
-                    pass
+                    # Attempts to expand the URL if not available through Twitter
+                    tweet['content'] = tweet['content'].replace(url['url'], UrlController.expand_url(url['url']))
 
         return saved_state, artifacts
 
diff --git a/threatingestor/utils/url_controller.py b/threatingestor/utils/url_controller.py
@@ -0,0 +1,26 @@
+"""
+This script is a standalone utility available to all sources. Currently, this script is only being used for expanding Twitter (t.co) shorteners but can be integrated into other places where URLs are ingested.
+"""
+
+from pyshorteners import Shortener, exceptions
+
+s = Shortener()
+
+class UrlController:
+    def expand_url(url):
+        """
+        Expand ingested URLs with this method.
+
+        If a URL is unknown or cannot be expanded, you'll get the original URL back.
+
+        @param: url (Example: https://inquest.net)
+
+        @rtype: str
+        """
+        
+        try:
+            expanded_link = s.tinyurl.expand(url)
+            return str(expanded_link)
+        # If unable to expand the URL, this exception is thrown
+        except exceptions.ExpandingErrorException:
+            return str(url)
