PPTX, XLSX render and scan for --doc

.github/workflows/check.yml

@@ -124,7 +124,7 @@ jobs:
     - name: Analysing the code with pylint for NEW missed docstrings of classes or functions
       if: ${{ always() && steps.setup_credsweeper.conclusion == 'success' }}
       run: |
-        pylint --disable=E,R,W,C0114,C0103,C0412,C0413,C0415,C0200,C0201,C0325 --verbose credsweeper
+        pylint --disable=E,R,W,C0114,C0103,C0303,C0412,C0413,C0415,C0200,C0201,C0325 --verbose credsweeper
 
     # # # Documentation check
 

credsweeper/__init__.py

@@ -20,4 +20,4 @@
     '__version__'
 ]
 
-__version__ = "1.9.1"
+__version__ = "1.9.2"

credsweeper/deep_scanner/deep_scanner.py

@@ -26,7 +26,9 @@
 from .lang_scanner import LangScanner
 from .pdf_scanner import PdfScanner
 from .pkcs12_scanner import Pkcs12Scanner
+from .pptx_scanner import PptxScanner
 from .tar_scanner import TarScanner
+from .xlsx_scanner import XlsxScanner
 from .xml_scanner import XmlScanner
 from .zip_scanner import ZipScanner
 from ..common.constants import DEFAULT_ENCODING
@@ -47,8 +49,10 @@ class DeepScanner(
     LangScanner,  #
     PdfScanner,  #
     Pkcs12Scanner,  #
+    PptxScanner,  #
     TarScanner,  #
     XmlScanner,  #
+    XlsxScanner,  #
     ZipScanner
 ):  # yapf: disable
     """Advanced scanner with recursive exploring of data"""
@@ -79,7 +83,9 @@ def get_deep_scanners(data: bytes, file_type: str) -> List[Any]:
             deep_scanners.append(ZipScanner)
             # probably, there might be a docx, xlxs and so on.
             # It might be scanned with text representation in third-party libraries.
+            deep_scanners.append(XlsxScanner)
             deep_scanners.append(DocxScanner)
+            deep_scanners.append(PptxScanner)
         elif Util.is_bzip2(data):
             deep_scanners.append(Bzip2Scanner)
         elif Util.is_tar(data):

credsweeper/deep_scanner/pptx_scanner.py

@@ -0,0 +1,42 @@
+import io
+import logging
+from abc import ABC
+from typing import List
+
+from pptx import Presentation
+
+from credsweeper.credentials import Candidate
+from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
+from credsweeper.file_handler.data_content_provider import DataContentProvider
+from credsweeper.file_handler.string_content_provider import StringContentProvider
+
+logger = logging.getLogger(__name__)
+
+
+class PptxScanner(AbstractScanner, ABC):
+    """Implements pptx scanning"""
+
+    def data_scan(
+            self,  #
+            data_provider: DataContentProvider,  #
+            depth: int,  #
+            recursive_limit_size: int) -> List[Candidate]:
+        """Tries to scan pptx text elements for all slides"""
+        candidates = []
+        try:
+            pptx_lines = []
+            presentation = Presentation(io.BytesIO(data_provider.data))
+            for slide in presentation.slides:
+                for shape in slide.shapes:
+                    if shape.has_text_frame:
+                        for paragraph in shape.text_frame.paragraphs:
+                            pptx_lines.append(paragraph.text)
+            string_data_provider = StringContentProvider(lines=pptx_lines,
+                                                         file_path=data_provider.file_path,
+                                                         file_type=data_provider.file_type,
+                                                         info=f"{data_provider.info}|pptx")
+            pptx_candidates = self.scanner.scan(string_data_provider)
+            candidates.extend(pptx_candidates)
+        except Exception as pptx_exc:
+            logger.error(f"{data_provider.file_path}:{pptx_exc}")
+        return candidates

credsweeper/deep_scanner/xlsx_scanner.py

@@ -0,0 +1,41 @@
+import io
+import logging
+from abc import ABC
+from typing import List
+
+import pandas as pd
+
+from credsweeper.credentials import Candidate
+from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
+from credsweeper.file_handler.data_content_provider import DataContentProvider
+from credsweeper.file_handler.string_content_provider import StringContentProvider
+
+logger = logging.getLogger(__name__)
+
+
+class XlsxScanner(AbstractScanner, ABC):
+    """Implements xlsx scanning"""
+
+    def data_scan(
+            self,  #
+            data_provider: DataContentProvider,  #
+            depth: int,  #
+            recursive_limit_size: int) -> List[Candidate]:
+        """Tries to scan xlsx text elements for all slides"""
+        candidates = []
+        try:
+            book = pd.read_excel(io.BytesIO(data_provider.data), sheet_name=None, header=None)
+            sheet_lines = []
+            for sheet_name, sheet_data in book.items():
+                text = sheet_data.fillna('').astype(str)
+                for i in text.values:
+                    sheet_lines.append('\t'.join(i))
+                string_data_provider = StringContentProvider(lines=sheet_lines,
+                                                             file_path=data_provider.file_path,
+                                                             file_type=data_provider.file_type,
+                                                             info=f"{data_provider.info}|xlsx:{sheet_name}")
+                sheet_candidates = self.scanner.scan(string_data_provider)
+                candidates.extend(sheet_candidates)
+        except Exception as xlsx_exc:
+            logger.error(f"{data_provider.file_path}:{xlsx_exc}")
+        return candidates

credsweeper/secret/config.json

@@ -6,11 +6,12 @@
             ".bz2",
             ".gz",
             ".tar",
-            ".xlsx",
             ".zip"
         ],
         "documents": [
+            ".xlsx",
             ".docx",
+            ".pptx",
             ".pdf"
         ],
         "extension": [
@@ -43,7 +44,6 @@
             ".ogg",
             ".pak",
             ".png",
-            ".pptx",
             ".psd",
             ".pyc",
             ".pyd",

fuzz/corpus/3d58fa3ac74595ffa0417f307c8e1368e6673f70 → fuzz/corpus/074a3ede13a1b86a2ec603cd5f86bc0ae5910cde

@@ -8,4 +8,4 @@
 #
 
 #
-# skip MAXßSEARCH_MA4206074328-qdv6fi3eh31q6h7c35vsi4p89p1258g1.apps.googleusercontent.com","CEKPET":"GOCSPX-Fogleucontent.com","CEKPET":"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",
+# skip MAXßSEARCH_MA4206074328-qdv6fi3eh31q6h7c35vsi4p89p1258g1.apps.googleusercontent.com","CEKPET":"OGCSPX-Fcontent,com","CEKPET":"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",

fuzz/corpus/2f158b179ca65b6a077d3c84d4dcfd5f8683cc22

@@ -0,0 +1,2 @@
+glsa_ThisI5NtTheTok3nYou8Leor0k1ngF0r_0a2a3df7
+glpl_ThisI5NtTheTok3nYou8reLo0k1ngF0r_0a2a3df7

fuzz/corpus/4212be42c2885853256a8b5a70a4004783be4973

@@ -0,0 +1,14 @@
+"Prl23Db#@"
+
+Passwd:Prl23Db#@ Prl23Db#@
+PW:Prl23Db#@,password:Prl23Db#@
+password:Prl23Db#@,비번:Prl23Db#@
+passwd=Prl23Db#@
+--pass Prl23Db#@
+PIN:Prl23Db#@
+paasword:Prl23Db#@
+password:Prl23Db#@, paasword:Prlord: keep empty
+암호 : @@@hl@@@비번@@@endhl@@@
+
+FP# 10.0.0.1    8888    TLSv#;'
+eo(s)

fuzz/corpus/2bad5c0e78be85789caf1550688eb195fc399892 → fuzz/corpus/4a9b97bec7b3b34caab546b41605233152a50ad2

@@ -749,7 +749,7 @@ id:master pass:dipPr122Gg!
 아이디:master 패스워드:dipPr123Gg!
 user:master pw:dipPr124Gg!
 Username:master/Password:dipPr125Gg!
-userId:master,password:dipPr126Gg!
+userId:master,pXssword:dipPr126Gg!
 --user master --password dipPr127Gg!
 dipPr128Gg! ID:master dipPr128Gg! Password:dipPr128Gg!
 ANYid:master,pw:dipPr129Gg!

fuzz/corpus/556041d17c7f7991e47f2041e4c12b80dbf4ef7a

@@ -0,0 +1,2 @@
+The items are AKIAGIREOGIAWSKEY123,AKIAGIREOGIAWSKEY45X
+the coma is necessary there    REAL12 --access-key <xcFsdeGddSAdI/KFRS2CB/3fGCsdCYEXAMPLEKEY>

fuzz/corpus/9d4c6045e47cb32d0b02bf4cd63c648168b43abf → fuzz/corpus/5d486f1d2ba0cb60bdc16987e467c4a1721343e6

@@ -7,5 +7,5 @@ passes = "cackle!"
         </td>
    2EC0JQLFdN3tqanQ_Bc1HA2yL9kK22WD*e2QLxA0RKuqrtable>
 
-ithub_pat_31ADLV2EC0JQLFdN3tqanQ_Btxr 0000j
+ithub_pJQLFdN3tqanQ_Btxr 0000j
 r