pangea-sdk 3.8.0__py3-none-any.whl → 3.8.0b2__py3-none-any.whl

pangea/services/base.py

@@ -1,40 +1,23 @@
 # Copyright 2022 Pangea Cyber Corporation
 # Author: Pangea Cyber Corporation
-from __future__ import annotations
 
 import copy
 import logging
 from typing import Dict, Optional, Type, Union
 
-from typing_extensions import TypeVar
-
 from pangea.asyncio.request import PangeaRequestAsync
 from pangea.config import PangeaConfig
 from pangea.exceptions import AcceptedRequestException
 from pangea.request import PangeaRequest
 from pangea.response import AttachedFile, PangeaResponse, PangeaResponseResult
 
-TResult = TypeVar("TResult", bound=PangeaResponseResult, default=PangeaResponseResult)
-
 
 class ServiceBase(object):
     service_name: str = "base"
 
     def __init__(
-        self,
-        token: str,
-        config: PangeaConfig | None = None,
-        logger_name: str = "pangea",
-        config_id: str | None = None,
-    ) -> None:
-        """
-        Initializes a new Pangea service client.
-
-        Args:
-            token: Pangea API token.
-            config: Configuration.
-            logger_name: Logger name.
-        """
+        self, token, config: Optional[PangeaConfig] = None, logger_name: str = "pangea", config_id: Optional[str] = None
+    ):
         if not token:
             raise Exception("No token provided")
 
@@ -47,11 +30,11 @@ class ServiceBase(object):
         self.request.set_extra_headers(extra_headers)
 
     @property
-    def token(self) -> str:
+    def token(self):
         return self._token
 
     @token.setter
-    def token(self, value: str) -> None:
+    def token(self, value):
         self._token = value
 
     @property
@@ -72,8 +55,8 @@ class ServiceBase(object):
         exception: Optional[AcceptedRequestException] = None,
         response: Optional[PangeaResponse] = None,
         request_id: Optional[str] = None,
-        result_class: Type[TResult] = PangeaResponseResult,  # type: ignore[assignment]
-    ) -> PangeaResponse[TResult]:
+        result_class: Union[Type[PangeaResponseResult], Type[Dict]] = dict,
+    ) -> PangeaResponse:
         """
         Poll result
 

pangea/services/file_scan.py

@@ -71,7 +71,6 @@ class FileScan(ServiceBase):
     """
 
     service_name = "file-scan"
-    version = "v1"
 
     def file_scan(
         self,

pangea/services/intel.py

@@ -839,7 +839,7 @@ class IpIntel(ServiceBase):
 
     def reputation_bulk(
         self, ips: List[str], verbose: Optional[bool] = None, raw: Optional[bool] = None, provider: Optional[str] = None
-    ) -> PangeaResponse[IPReputationBulkResult]:
+    ) -> PangeaResponse[IPReputationResult]:
         """
         Reputation V2
 
@@ -1195,7 +1195,7 @@ class UrlIntel(ServiceBase):
         verbose: Optional[bool] = None,
         raw: Optional[bool] = None,
         provider: Optional[str] = None,
-    ) -> PangeaResponse[URLReputationBulkResult]:
+    ) -> PangeaResponse[URLReputationResult]:
         """
         Reputation V2
 

pangea/services/redact.py

@@ -1,11 +1,9 @@
 # Copyright 2022 Pangea Cyber Corporation
 # Author: Pangea Cyber Corporation
-from __future__ import annotations
 
 import enum
 from typing import Dict, List, Optional, Union
 
-from pangea.config import PangeaConfig
 from pangea.response import APIRequestModel, APIResponseModel, PangeaResponse, PangeaResponseResult
 from pangea.services.base import ServiceBase
 
@@ -134,24 +132,7 @@ class Redact(ServiceBase):
 
     service_name = "redact"
 
-    def __init__(
-        self, token: str, config: PangeaConfig | None = None, logger_name: str = "pangea", config_id: str | None = None
-    ) -> None:
-        """
-        Redact client
-
-        Initializes a new Redact client.
-
-        Args:
-            token: Pangea API token.
-            config: Configuration.
-            logger_name: Logger name.
-            config_id: Configuration ID.
-
-        Examples:
-             config = PangeaConfig(domain="pangea_domain")
-             redact = Redact(token="pangea_token", config=config)
-        """
+    def __init__(self, token, config=None, logger_name="pangea", config_id: Optional[str] = None):
         super().__init__(token, config, logger_name, config_id=config_id)
 
     def redact(

pangea/services/sanitize.py

@@ -0,0 +1,275 @@
+# Copyright 2022 Pangea Cyber Corporation
+# Author: Pangea Cyber Corporation
+import io
+from typing import Dict, List, Optional, Tuple
+
+from pangea.response import APIRequestModel, PangeaResponse, PangeaResponseResult, TransferMethod
+from pangea.services.base import ServiceBase
+from pangea.utils import FileUploadParams, get_file_upload_params
+
+
+class SanitizeFile(APIRequestModel):
+    scan_provider: Optional[str] = None
+    """Provider to use for File Scan."""
+
+    cdr_provider: Optional[str] = None
+    """Provider to use for CDR."""
+
+
+class SanitizeContent(APIRequestModel):
+    url_intel: Optional[bool] = None
+    """Perform URL Intel lookup."""
+
+    url_intel_provider: Optional[str] = None
+    """Provider to use for URL Intel."""
+
+    domain_intel: Optional[bool] = None
+    """Perform Domain Intel lookup."""
+
+    domain_intel_provider: Optional[str] = None
+    """Provider to use for Domain Intel lookup."""
+
+    defang: Optional[bool] = None
+    """Defang external links."""
+
+    defang_threshold: Optional[int] = None
+    """Defang risk threshold."""
+
+    redact: Optional[bool] = None
+    """Redact sensitive content."""
+
+    remove_attachments: Optional[bool] = None
+    """Remove file attachments (PDF only)."""
+
+    remove_interactive: Optional[bool] = None
+    """Remove interactive content (PDF only)."""
+
+
+class SanitizeShareOutput(APIRequestModel):
+    enabled: Optional[bool] = None
+    """Store Sanitized files to Pangea Secure Share."""
+
+    output_folder: Optional[str] = None
+    """
+    Store Sanitized files to this Secure Share folder (will be auto-created if
+    it does not exist)
+    """
+
+
+class SanitizeRequest(APIRequestModel):
+    transfer_method: TransferMethod = TransferMethod.POST_URL
+    source_url: Optional[str] = None
+    share_id: Optional[str] = None
+    file: Optional[SanitizeFile] = None
+    content: Optional[SanitizeContent] = None
+    share_output: Optional[SanitizeShareOutput] = None
+    size: Optional[int] = None
+    crc32c: Optional[str] = None
+    sha256: Optional[str] = None
+    uploaded_file_name: Optional[str] = None
+
+
+class DefangData(PangeaResponseResult):
+    external_urls_count: Optional[int] = None
+    external_domains_count: Optional[int] = None
+    defanged_count: Optional[int] = None
+    url_intel_summary: Optional[str] = None
+    domain_intel_summary: Optional[str] = None
+
+
+class RedactData(PangeaResponseResult):
+    redaction_count: Optional[int] = None
+    summary_counts: Dict = {}
+
+
+class CDR(PangeaResponseResult):
+    file_attachments_removed: Optional[int] = None
+    interactive_contents_removed: Optional[int] = None
+
+
+class SanitizeData(PangeaResponseResult):
+    defang: Optional[DefangData] = None
+    redact: Optional[RedactData] = None
+    malicious_file: Optional[bool] = None
+    cdr: Optional[CDR] = None
+
+
+class SanitizeResult(PangeaResponseResult):
+    dest_url: Optional[str] = None
+    dest_share_id: Optional[str] = None
+    data: SanitizeData
+    parameters: Dict = {}
+
+
+class Sanitize(ServiceBase):
+    """Sanitize service client.
+
+    Examples:
+        import os
+
+        # Pangea SDK
+        from pangea.config import PangeaConfig
+        from pangea.services import Sanitize
+
+        PANGEA_SANITIZE_TOKEN = os.getenv("PANGEA_SANITIZE_TOKEN")
+        config = PangeaConfig(domain="pangea.cloud")
+
+        sanitize = Sanitize(token=PANGEA_SANITIZE_TOKEN, config=config)
+    """
+
+    service_name = "sanitize"
+
+    def sanitize(
+        self,
+        transfer_method: TransferMethod = TransferMethod.POST_URL,
+        file_path: Optional[str] = None,
+        file: Optional[io.BufferedReader] = None,
+        source_url: Optional[str] = None,
+        share_id: Optional[str] = None,
+        file_scan: Optional[SanitizeFile] = None,
+        content: Optional[SanitizeContent] = None,
+        share_output: Optional[SanitizeShareOutput] = None,
+        size: Optional[int] = None,
+        crc32c: Optional[str] = None,
+        sha256: Optional[str] = None,
+        uploaded_file_name: Optional[str] = None,
+        sync_call: bool = True,
+    ) -> PangeaResponse[SanitizeResult]:
+        """
+        Sanitize
+
+        Apply file sanitization actions according to specified rules.
+        [**Beta API**](https://pangea.cloud/docs/sdk/python/#beta-releases).
+
+        OperationId: sanitize_post_v1beta_sanitize
+
+        Args:
+            transfer_method: The transfer method used to upload the file data.
+            file_path: Path to file to sanitize.
+            file: File to sanitize.
+            source_url: A URL where the file to be sanitized can be downloaded.
+            share_id: A Pangea Secure Share ID where the file to be sanitized is stored.
+            file_scan: Options for File Scan.
+            content: Options for how the file should be sanitized.
+            share_output: Integration with Secure Share.
+            size: The size (in bytes) of the file. If the upload doesn't match, the call will fail.
+            crc32c: The CRC32C hash of the file data, which will be verified by the server if provided.
+            sha256: The hexadecimal-encoded SHA256 hash of the file data, which will be verified by the server if provided.
+            uploaded_file_name: Name of the user-uploaded file, required for `TransferMethod.PUT_URL` and `TransferMethod.POST_URL`.
+            sync_call: Whether or not to poll on HTTP/202.
+
+        Raises:
+            PangeaAPIException: If an API error happens.
+
+        Returns:
+            The sanitized file and information on the sanitization that was
+            performed.
+
+        Examples:
+            with open("/path/to/file.pdf", "rb") as f:
+                response = sanitize.sanitize(
+                    file=f,
+                    transfer_method=TransferMethod.POST_URL,
+                    uploaded_file_name="uploaded_file",
+                )
+        """
+
+        if file or file_path:
+            if file_path:
+                file = open(file_path, "rb")
+            if transfer_method == TransferMethod.POST_URL and (sha256 is None or crc32c is None or size is None):
+                params = get_file_upload_params(file)  # type: ignore[arg-type]
+                crc32c = params.crc_hex if crc32c is None else crc32c
+                sha256 = params.sha256_hex if sha256 is None else sha256
+                size = params.size if size is None else size
+            else:
+                crc32c, sha256, size = None, None, None
+            files: List[Tuple] = [("upload", ("filename", file, "application/octet-stream"))]
+        else:
+            raise ValueError("Need to set file_path or file arguments")
+
+        input = SanitizeRequest(
+            transfer_method=transfer_method,
+            source_url=source_url,
+            share_id=share_id,
+            file=file_scan,
+            content=content,
+            share_output=share_output,
+            crc32c=crc32c,
+            sha256=sha256,
+            size=size,
+            uploaded_file_name=uploaded_file_name,
+        )
+        data = input.dict(exclude_none=True)
+        response = self.request.post("v1beta/sanitize", SanitizeResult, data=data, files=files, poll_result=sync_call)
+        if file_path and file is not None:
+            file.close()
+        return response
+
+    def request_upload_url(
+        self,
+        transfer_method: TransferMethod = TransferMethod.PUT_URL,
+        params: Optional[FileUploadParams] = None,
+        file_scan: Optional[SanitizeFile] = None,
+        content: Optional[SanitizeContent] = None,
+        share_output: Optional[SanitizeShareOutput] = None,
+        size: Optional[int] = None,
+        crc32c: Optional[str] = None,
+        sha256: Optional[str] = None,
+        uploaded_file_name: Optional[str] = None,
+    ) -> PangeaResponse[SanitizeResult]:
+        """
+        Sanitize via presigned URL
+
+        Apply file sanitization actions according to specified rules via a
+        [presigned URL](https://pangea.cloud/docs/api/presigned-urls).
+        [**Beta API**](https://pangea.cloud/docs/sdk/python/#beta-releases).
+
+        OperationId: sanitize_post_v1beta_sanitize 2
+
+        Args:
+            transfer_method: The transfer method used to upload the file data.
+            params: File upload parameters.
+            file_scan: Options for File Scan.
+            content: Options for how the file should be sanitized.
+            share_output: Integration with Secure Share.
+            size: The size (in bytes) of the file. If the upload doesn't match, the call will fail.
+            crc32c: The CRC32C hash of the file data, which will be verified by the server if provided.
+            sha256: The hexadecimal-encoded SHA256 hash of the file data, which will be verified by the server if provided.
+            uploaded_file_name: Name of the user-uploaded file, required for `TransferMethod.PUT_URL` and `TransferMethod.POST_URL`.
+
+        Raises:
+            PangeaAPIException: If an API error happens.
+
+        Returns:
+            A presigned URL.
+
+        Examples:
+            presignedUrl = sanitize.request_upload_url(
+                transfer_method=TransferMethod.PUT_URL,
+                uploaded_file_name="uploaded_file",
+            )
+
+            # Upload file to `presignedUrl.accepted_result.put_url`.
+
+            # Poll for Sanitize's result.
+            response: PangeaResponse[SanitizeResult] = sanitize.poll_result(response=presignedUrl)
+        """
+
+        input = SanitizeRequest(
+            transfer_method=transfer_method,
+            file=file_scan,
+            content=content,
+            share_output=share_output,
+            crc32c=crc32c,
+            sha256=sha256,
+            size=size,
+            uploaded_file_name=uploaded_file_name,
+        )
+        if params is not None and (transfer_method == TransferMethod.POST_URL):
+            input.crc32c = params.crc_hex
+            input.sha256 = params.sha256_hex
+            input.size = params.size
+
+        data = input.dict(exclude_none=True)
+        return self.request.request_presigned_url("v1beta/sanitize", SanitizeResult, data=data)

pangea/services/share/file_format.py

@@ -0,0 +1,170 @@
+import enum
+
+
+class FileFormat(str, enum.Enum):
+    F3G2 = "3G2"
+    F3GP = "3GP"
+    F3MF = "3MF"
+    F7Z = "7Z"
+    A = "A"
+    AAC = "AAC"
+    ACCDB = "ACCDB"
+    AIFF = "AIFF"
+    AMF = "AMF"
+    AMR = "AMR"
+    APE = "APE"
+    ASF = "ASF"
+    ATOM = "ATOM"
+    AU = "AU"
+    AVI = "AVI"
+    AVIF = "AVIF"
+    BIN = "BIN"
+    BMP = "BMP"
+    BPG = "BPG"
+    BZ2 = "BZ2"
+    CAB = "CAB"
+    CLASS = "CLASS"
+    CPIO = "CPIO"
+    CRX = "CRX"
+    CSV = "CSV"
+    DAE = "DAE"
+    DBF = "DBF"
+    DCM = "DCM"
+    DEB = "DEB"
+    DJVU = "DJVU"
+    DLL = "DLL"
+    DOC = "DOC"
+    DOCX = "DOCX"
+    DWG = "DWG"
+    EOT = "EOT"
+    EPUB = "EPUB"
+    EXE = "EXE"
+    FDF = "FDF"
+    FITS = "FITS"
+    FLAC = "FLAC"
+    FLV = "FLV"
+    GBR = "GBR"
+    GEOJSON = "GEOJSON"
+    GIF = "GIF"
+    GLB = "GLB"
+    GML = "GML"
+    GPX = "GPX"
+    GZ = "GZ"
+    HAR = "HAR"
+    HDR = "HDR"
+    HEIC = "HEIC"
+    HEIF = "HEIF"
+    HTML = "HTML"
+    ICNS = "ICNS"
+    ICO = "ICO"
+    ICS = "ICS"
+    ISO = "ISO"
+    JAR = "JAR"
+    JP2 = "JP2"
+    JPF = "JPF"
+    JPG = "JPG"
+    JPM = "JPM"
+    JS = "JS"
+    JSON = "JSON"
+    JXL = "JXL"
+    JXR = "JXR"
+    KML = "KML"
+    LIT = "LIT"
+    LNK = "LNK"
+    LUA = "LUA"
+    LZ = "LZ"
+    M3U = "M3U"
+    M4A = "M4A"
+    MACHO = "MACHO"
+    MDB = "MDB"
+    MIDI = "MIDI"
+    MKV = "MKV"
+    MOBI = "MOBI"
+    MOV = "MOV"
+    MP3 = "MP3"
+    MP4 = "MP4"
+    MPC = "MPC"
+    MPEG = "MPEG"
+    MQV = "MQV"
+    MRC = "MRC"
+    MSG = "MSG"
+    MSI = "MSI"
+    NDJSON = "NDJSON"
+    NES = "NES"
+    ODC = "ODC"
+    ODF = "ODF"
+    ODG = "ODG"
+    ODP = "ODP"
+    ODS = "ODS"
+    ODT = "ODT"
+    OGA = "OGA"
+    OGV = "OGV"
+    OTF = "OTF"
+    OTG = "OTG"
+    OTP = "OTP"
+    OTS = "OTS"
+    OTT = "OTT"
+    OWL = "OWL"
+    P7S = "P7S"
+    PAT = "PAT"
+    PDF = "PDF"
+    PHP = "PHP"
+    PL = "PL"
+    PNG = "PNG"
+    PPT = "PPT"
+    PPTX = "PPTX"
+    PS = "PS"
+    PSD = "PSD"
+    PUB = "PUB"
+    PY = "PY"
+    QCP = "QCP"
+    RAR = "RAR"
+    RMVB = "RMVB"
+    RPM = "RPM"
+    RSS = "RSS"
+    RTF = "RTF"
+    SHP = "SHP"
+    SHX = "SHX"
+    SO = "SO"
+    SQLITE = "SQLITE"
+    SRT = "SRT"
+    SVG = "SVG"
+    SWF = "SWF"
+    SXC = "SXC"
+    TAR = "TAR"
+    TCL = "TCL"
+    TCX = "TCX"
+    TIFF = "TIFF"
+    TORRENT = "TORRENT"
+    TSV = "TSV"
+    TTC = "TTC"
+    TTF = "TTF"
+    TXT = "TXT"
+    VCF = "VCF"
+    VOC = "VOC"
+    VTT = "VTT"
+    WARC = "WARC"
+    WASM = "WASM"
+    WAV = "WAV"
+    WEBM = "WEBM"
+    WEBP = "WEBP"
+    WOFF = "WOFF"
+    WOFF2 = "WOFF2"
+    X3D = "X3D"
+    XAR = "XAR"
+    XCF = "XCF"
+    XFDF = "XFDF"
+    XLF = "XLF"
+    XLS = "XLS"
+    XLSX = "XLSX"
+    XML = "XML"
+    XPM = "XPM"
+    XZ = "XZ"
+    ZIP = "ZIP"
+    ZST = "ZST"
+
+    def __str__(self):
+        return str(self.value)
+
+    def __repr__(self):
+        return str(self.value)