bbot 2.1.2.5236rc0__tar.gz → 2.1.2.5240rc0__tar.gz

{bbot-2.1.2.5236rc0 → bbot-2.1.2.5240rc0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: bbot
-Version: 2.1.2.5236rc0
+Version: 2.1.2.5240rc0
 Summary: OSINT automation for hackers.
 Home-page: https://github.com/blacklanternsecurity/bbot
 License: GPL-3.0

{bbot-2.1.2.5236rc0 → bbot-2.1.2.5240rc0}/bbot/__init__.py

@@ -1,4 +1,4 @@
 # version placeholder (replaced by poetry-dynamic-versioning)
-__version__ = "v2.1.2.5236rc"
+__version__ = "v2.1.2.5240rc"
 
 from .scanner import Scanner, Preset

{bbot-2.1.2.5236rc0 → bbot-2.1.2.5240rc0}/bbot/modules/deadly/dastardly.py

@@ -90,7 +90,7 @@ class dastardly(BaseModule):
     def parse_dastardly_xml(self, xml_file):
         try:
             with open(xml_file, "rb") as f:
-                et = etree.parse(f, parser=etree.XMLParser(recover=True))
+                et = etree.parse(f, parser=etree.XMLParser(recover=True, resolve_entities=False))
                 for testsuite in et.iter("testsuite"):
                     yield TestSuite(testsuite)
         except FileNotFoundError:

{bbot-2.1.2.5236rc0 → bbot-2.1.2.5240rc0}/bbot/modules/extractous.py

@@ -81,6 +81,12 @@ class extractous(BaseModule):
     async def handle_event(self, event):
         file_path = event.data["path"]
         content = await self.scan.helpers.run_in_executor_mp(extract_text, file_path)
+        if isinstance(content, tuple):
+            error, traceback = content
+            self.error(f"Error extracting text from {file_path}: {error}")
+            self.trace(traceback)
+            return
+
         if content:
             raw_text_event = self.make_event(
                 content,
@@ -99,49 +105,18 @@ def extract_text(file_path):
     :return: ASCII-encoded plaintext extracted from the document.
     """
 
-    extractable_file_types = [
-        ".csv",
-        ".eml",
-        ".msg",
-        ".epub",
-        ".xlsx",
-        ".xls",
-        ".html",
-        ".htm",
-        ".md",
-        ".org",
-        ".odt",
-        ".pdf",
-        ".txt",
-        ".text",
-        ".log",
-        ".ppt",
-        ".pptx",
-        ".rst",
-        ".rtf",
-        ".tsv",
-        ".doc",
-        ".docx",
-        ".xml",
-    ]
-
-    # If the file can be extracted with extractous use its partition function or try and read it
-    if any(file_path.lower().endswith(file_type) for file_type in extractable_file_types):
-        try:
-            extractor = Extractor()
-            reader = extractor.extract_file(str(file_path))
+    try:
+        extractor = Extractor()
+        reader, metadata = extractor.extract_file(str(file_path))
 
-            result = ""
+        result = ""
+        buffer = reader.read(4096)
+        while len(buffer) > 0:
+            result += buffer.decode("utf-8")
             buffer = reader.read(4096)
-            while len(buffer) > 0:
-                result += buffer.decode("utf-8")
-                buffer = reader.read(4096)
 
-            return result.strip()
+        return result.strip()
+    except Exception as e:
+        import traceback
 
-        except Exception:
-            with open(file_path, "rb") as file:
-                return file.read().decode("utf-8", errors="ignore")
-    else:
-        with open(file_path, "rb") as file:
-            return file.read().decode("utf-8", errors="ignore")
+        return (str(e), traceback.format_exc())

{bbot-2.1.2.5236rc0 → bbot-2.1.2.5240rc0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "bbot"
-version = "v2.1.2.5236rc"
+version = "v2.1.2.5240rc"
 description = "OSINT automation for hackers."
 authors = [
     "TheTechromancer",