ปกป้องและวิเคราะห์ไฟล์

import glasswall


# Load the Glasswall Editor library
editor = glasswall.Editor(r"C:\gwpw\libraries\10.0")

# Use the default policy to sanitise a file, writing the sanitised file to a new path
editor.protect_file(
    input_file=r"C:\gwpw\input\TestFile_11.doc",
    output_file=r"C:\gwpw\output\editor\protect_f2f\TestFile_11.doc",
)

import glasswall


# Load the Glasswall Editor library
editor = glasswall.Editor(r"C:\gwpw\libraries\10.0")

# Use the default policy to sanitise a file in memory, returning the file bytes in memory
file_bytes = editor.protect_file(
    input_file=r"C:\gwpw\input\TestFile_11.doc"
)

assert file_bytes[:8] == b'\xd0\xcf\x11\xe0\xa1\xb1\x1a\xe1'

import glasswall


# Load the Glasswall Editor library
editor = glasswall.Editor(r"C:\gwpw\libraries\10.0")

# Read file from disk to memory
with open(r"C:\gwpw\input\TestFile_11.doc", "rb") as f:
    input_bytes = f.read()

# Use the default policy to sanitise a file
file_bytes = editor.protect_file(
    input_file=input_bytes,
)

assert file_bytes[:8] == b'\xd0\xcf\x11\xe0\xa1\xb1\x1a\xe1'

import glasswall


# Load the Glasswall Editor library
editor = glasswall.Editor(r"C:\gwpw\libraries\10.0")

# Use the default policy to protect a directory of files, writing the sanitised files to a new directory.
editor.protect_directory(
    input_directory=r"C:\gwpw\input",
    output_directory=r"C:\gwpw\output\editor\protect_directory"
)

import glasswall


# Load the Glasswall Editor library
editor = glasswall.Editor(r"C:\gwpw\libraries\10.0")

# Use the default policy to protect a directory of files, writing the sanitised files to a new directory.
editor.protect_directory(
    input_directory=r"C:\gwpw\input_with_unsupported_file_types",
    output_directory=r"C:\gwpw\output\editor\protect_directory_unsupported",
    raise_unsupported=False
)

import glasswall


# Load the Glasswall Editor library
editor = glasswall.Editor(r"C:\gwpw\libraries\10.0")

# Use a custom Editor policy to sanitise all files in the input directory
# and write them to the input_sanitised directory. If macros are present
# in ppt or word files, the file will be marked as non-conforming and blocked.
# If internal or external hyperlinks are present in word files they will not
# be sanitised, and will remain in the regenerated document.
editor.protect_directory(
    input_directory=r"C:\gwpw\input",
    output_directory=r"C:\gwpw\output\editor\protect_directory_custom",
    content_management_policy=glasswall.content_management.policies.Editor(
        default="sanitise",
        config={
            "pptConfig": {
                "macros": "disallow",
            },
            "wordConfig": {
                "internal_hyperlinks": "allow",
                "external_hyperlinks": "allow",
                "macros": "disallow",
            }
        }
    )
)

import os

import glasswall


# Load the Glasswall Editor library
editor = glasswall.Editor(r"C:\gwpw\libraries\10.0")

input_directory = r"C:\gwpw\input"
output_directory = r"C:\gwpw\output\editor\protect_directory_file_format"

# Iterate relative file paths from input_directory
for relative_file in glasswall.utils.list_file_paths(input_directory, absolute=False):
    # Construct absolute paths
    input_file = os.path.join(input_directory, relative_file)
    output_file = os.path.join(output_directory, relative_file)

    # Get the file type of the file
    file_type = editor.determine_file_type(
        input_file=input_file,
        as_string=True,
        raise_unsupported=False
    )

    # Protect only doc and docx files
    if file_type in ["doc", "docx"]:
        editor.protect_file(input_file, output_file)

import glasswall


# Load the Glasswall Editor library
editor = glasswall.Editor(r"C:\gwpw\libraries\10.0")

# Use the default policy to analyse a file, writing the analysis report to a new path
editor.analyse_file(
    input_file=r"C:\gwpw\input\TestFile_11.doc",
    output_file=r"C:\gwpw\output\editor\analyse_f2f\TestFile_11.doc.xml",
)

import glasswall


# Load the Glasswall Editor library
editor = glasswall.Editor(r"C:\gwpw\libraries\10.0")

# Use the default policy to analyse a file
analysis_report = editor.analyse_file(
    input_file=r"C:\gwpw\input\TestFile_11.doc",
)

assert analysis_report[:500] == b'<?xml version="1.0" encoding="utf-8"?>\n<gw:GWallInfo xsi:schemaLocation="http://glasswall.com/namespace/gwallInfo.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:gw="http://glasswall.com/namespace">\n\t<gw:DocumentStatistics>\n\t\t<gw:DocumentSummary>\n\t\t\t<gw:TotalSizeInBytes>35840</gw:TotalSizeInBytes>\n\t\t\t<gw:FileType>doc</gw:FileType>\n\t\t\t<gw:Version>Not Applicable</gw:Version>\n\t\t\t<gw:InputSHA256>9FDE85B8800C1019D2865FA298A7F75873E09870B71F9825827E354B865686A6</gw:InputSHA256>\n\t\t\t<gw'

import glasswall


# Load the Glasswall Editor library
editor = glasswall.Editor(r"C:\gwpw\libraries\10.0")

# Read file from disk to memory
with open(r"C:\gwpw\input\TestFile_11.doc", "rb") as f:
    input_bytes = f.read()

# Use the default policy to analyse a file
analysis_report = editor.analyse_file(
    input_file=input_bytes,
)

assert analysis_report[:500] == b'<?xml version="1.0" encoding="utf-8"?>\n<gw:GWallInfo xsi:schemaLocation="http://glasswall.com/namespace/gwallInfo.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:gw="http://glasswall.com/namespace">\n\t<gw:DocumentStatistics>\n\t\t<gw:DocumentSummary>\n\t\t\t<gw:TotalSizeInBytes>35840</gw:TotalSizeInBytes>\n\t\t\t<gw:FileType>doc</gw:FileType>\n\t\t\t<gw:Version>Not Applicable</gw:Version>\n\t\t\t<gw:InputSHA256>9FDE85B8800C1019D2865FA298A7F75873E09870B71F9825827E354B865686A6</gw:InputSHA256>\n\t\t\t<gw'

import glasswall


# Load the Glasswall Editor library
editor = glasswall.Editor(r"C:\gwpw\libraries\10.0")

# Use the default policy to analyse a directory of files, writing the analysis reports to a new directory.
editor.analyse_directory(
    input_directory=r"C:\gwpw\input",
    output_directory=r"C:\gwpw\output\editor\analyse_directory"
)

import glasswall


# Load the Glasswall Editor library
editor = glasswall.Editor(r"C:\gwpw\libraries\10.0")

# Use the default policy to analyse a directory of files, writing the analysis reports to a new directory.
editor.analyse_directory(
    input_directory=r"C:\gwpw\input_with_unsupported_file_types",
    output_directory=r"C:\gwpw\output\editor\analyse_directory_unsupported",
    raise_unsupported=False
)

import glasswall


# Load the Glasswall Editor library
editor = glasswall.Editor(r"C:\gwpw\libraries\10.0")

# Use a custom Editor policy to analyse all files in the input directory
# and write them to analyse_directory_custom directory. If macros are
# present in ppt or word files, a GeneralFail exception will be raised if the
# raise_unsupported argument is left at its default value of False, but the
# analysis report will still be written to file and will contain IssueItems.
# If internal or external hyperlinks are present in word files they will not
# be sanitised, and will remain in the regenerated document.
editor.analyse_directory(
    input_directory=r"C:\gwpw\input",
    output_directory=r"C:\gwpw\output\editor\analyse_directory_custom",
    content_management_policy=glasswall.content_management.policies.Editor(
        default="sanitise",
        config={
            "pptConfig": {
                "macros": "disallow",
            },
            "wordConfig": {
                "internal_hyperlinks": "allow",
                "external_hyperlinks": "allow",
                "macros": "disallow",
            }
        }
    ),
    raise_unsupported=False
)

import os

import glasswall


# Load the Glasswall Editor library
editor = glasswall.Editor(r"C:\gwpw\libraries\10.0")

input_directory = r"C:\gwpw\input"
output_directory = r"C:\gwpw\output\editor\analyse_directory_file_format"

# Iterate relative file paths from input_directory
for relative_file in glasswall.utils.list_file_paths(input_directory, absolute=False):
    # Construct absolute paths
    input_file = os.path.join(input_directory, relative_file)
    output_file = os.path.join(output_directory, relative_file + ".xml")

    # Get the file type of the file
    file_type = editor.determine_file_type(
        input_file=input_file,
        as_string=True,
        raise_unsupported=False
    )

    # Analyse only doc and docx files
    if file_type in ["doc", "docx"]:
        editor.analyse_file(input_file, output_file)