Python zipfile.BadZipfile() Examples

def check_read_with_bad_crc(self, compression):
        """Tests that files with bad CRCs raise a BadZipfile exception when read."""
        zipdata = self.zips_with_bad_crc[compression]

        # Using ZipFile.read()
        with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf:
            self.assertRaises(zipfile.BadZipfile, zipf.read, 'afile')

        # Using ZipExtFile.read()
        with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf:
            with zipf.open('afile', 'r') as corrupt_file:
                self.assertRaises(zipfile.BadZipfile, corrupt_file.read)

        # Same with small reads (in order to exercise the buffering logic)
        with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf:
            with zipf.open('afile', 'r') as corrupt_file:
                corrupt_file.MIN_READ_SIZE = 2
                with self.assertRaises(zipfile.BadZipfile):
                    while corrupt_file.read(2):
                        pass 

def _extract(self, filename, password):
        archive_path = _prepare_archive_at_path(filename)
        if not archive_path:
            return None
        # Extraction.
        extract_path = environ.get("TEMP", "/tmp")
        with ZipFile(archive_path, "r") as archive:
            try:
                archive.extractall(path=extract_path, pwd=password)
            except BadZipfile:
                raise Exception("Invalid Zip file")
            # Try to extract it again, but with a default password
            except RuntimeError:
                try:
                    archive.extractall(path=extract_path, pwd="infected")
                except RuntimeError as err:
                    raise Exception("Unable to extract Zip file: %s" % err)
            finally:
                self._extract_nested_archives(archive, extract_path, password)
        return archive.namelist() 

def _prepare_archive_at_path(filename):
    """ Verifies that there's a readable zip archive at the given path.

    This function returns a new name for the archive (for most cases it's
    the same as the original one; but if an archive named "foo.zip" contains
    a file named "foo" this archive will be renamed to avoid being overwrite.
    """
    # Verify that the archive is actually readable
    try:
        with ZipFile(filename, "r") as archive:
            archive.close()
    except BadZipfile:
        return None
    # Test if zip file contains a file named as itself
    if _is_overwritten(filename):
        log.debug("ZIP file contains a file with the same name, original is \
        going to be overwrite")
        # In this case we just change the file name
        new_zip_path = filename + _random_extension()
        move(filename, new_zip_path)
        filename = new_zip_path
    return filename 

def _extract(self, filename, password):
        archive_path = _prepare_archive_at_path(filename)
        if not archive_path:
            return None
        # Extraction.
        extract_path = environ.get("TEMP", "/tmp")
        with ZipFile(archive_path, "r") as archive:
            try:
                archive.extractall(path=extract_path, pwd=password)
            except BadZipfile:
                raise Exception("Invalid Zip file")
            # Try to extract it again, but with a default password
            except RuntimeError:
                try:
                    archive.extractall(path=extract_path, pwd="infected")
                except RuntimeError as err:
                    raise Exception("Unable to extract Zip file: %s" % err)
            finally:
                self._extract_nested_archives(archive, extract_path, password)
        return archive.namelist() 

def _prepare_archive_at_path(filename):
    """ Verifies that there's a readable zip archive at the given path.

    This function returns a new name for the archive (for most cases it's
    the same as the original one; but if an archive named "foo.zip" contains
    a file named "foo" this archive will be renamed to avoid being overwrite.
    """
    # Verify that the archive is actually readable
    try:
        with ZipFile(filename, "r") as archive:
            archive.close()
    except BadZipfile:
        return None
    # Test if zip file contains a file named as itself
    if _is_overwritten(filename):
        log.debug("ZIP file contains a file with the same name, original is \
        going to be overwrite")
        # In this case we just change the file name
        new_zip_path = filename + _random_extension()
        move(filename, new_zip_path)
        filename = new_zip_path
    return filename 

def _ParseRelationshipsXMLFile(self, xml_data):
    """Parses the relationships XML file (_rels/.rels).

    Args:
      xml_data (bytes): data of a _rels/.rels XML file.

    Returns:
      list[str]: property file paths. The path is relative to the root of
          the ZIP file.

    Raises:
      zipfile.BadZipfile: if the relationship XML file cannot be read.
    """
    xml_root = ElementTree.fromstring(xml_data)

    property_files = []
    for xml_element in xml_root.iter():
      type_attribute = xml_element.get('Type')
      if 'properties' in repr(type_attribute):
        target_attribute = xml_element.get('Target')
        property_files.append(target_attribute)

    return property_files 

def _create_cbz_(dirpath, archivename):
        """
        Create a Comic Book Archive in .cbz and .cbr format (Tar Compression)

        :param dirpath: Directory location to save the the book archive.
        :param archivename: Name of the archive.
        """
        currdir = os.getcwd()
        try:
            import zlib

            compression = zipfile.ZIP_DEFLATED
        except ImportError:
            logging.warning("zlib library not available. Using ZIP_STORED compression.")
            compression = zipfile.ZIP_STORED
        try:
            with zipfile.ZipFile(archivename, "w", compression) as zf:
                os.chdir(os.path.abspath(os.path.join(dirpath, os.pardir)))
                name = os.path.basename(dirpath)
                for file in os.listdir(name):
                    zf.write(os.path.join(name, file))
        except zipfile.BadZipfile:
            logging.error("Unable to compile CBR file ")
        os.chdir(currdir) 

def test_unsupportedCompression(self):
        """
        A zipfile which describes an unsupported compression mechanism should
        raise BadZipfile.
        """
        fn = self.mktemp()
        with zipfile.ZipFile(fn, "w") as zf:
            zi = zipfile.ZipInfo("0")
            zf.writestr(zi, "some data")
            # Mangle its compression type in the central directory; can't do
            # this before the writestr call or zipfile will (correctly) tell us
            # not to pass bad compression types :)
            zi.compress_type = 1234

        with zipstream.ChunkingZipFile(fn) as czf:
            self.assertRaises(zipfile.BadZipfile, czf.readfile, "0") 

def main():
    """
    Read input zip file, minhash the documents in it and put them in buckets
    The zip file should have been created with data_prep/prepare_blobstore_zips
    """
    try:
        filename = os.path.abspath(sys.argv[1])
    except IndexError:
        print 'filename not provided'
        exit(1)
    try:
        zip_reader = zipfile.ZipFile(filename)
    except IOError:
        print 'unable to read file {file}'.format(file = filename)
        exit(1)
    except zipfile.BadZipfile:
        print 'file {file} is not a zip file'.format(file = filename)
        exit(1)

    lsh_zipfile(PeerbeltLine, zip_reader, 'bash', filename) 

def test_filenameMismatch(self):
        """
        A zipfile entry with a different filename than is found in the central
        directory should raise BadZipfile.
        """
        fn = self.makeZipFile([b"test contents",
                               b"more contents"])
        with zipfile.ZipFile(fn, "r") as zf:
            info = zf.getinfo("0")
            info.filename = "not zero"
        with open(fn, "r+b") as scribble:
            scribble.seek(info.header_offset, 0)
            scribble.write(info.FileHeader())

        with zipstream.ChunkingZipFile(fn) as czf:
            self.assertRaises(zipfile.BadZipfile, czf.readfile, "0")
            with czf.readfile("1") as zfe:
                self.assertEqual(zfe.read(), b"more contents") 

def test_invalidHeader(self):
        """
        A zipfile entry with the wrong magic number should raise BadZipfile for
        readfile(), but that should not affect other files in the archive.
        """
        fn = self.makeZipFile(["test contents",
                               "more contents"])
        with zipfile.ZipFile(fn, "r") as zf:
            zeroOffset = zf.getinfo("0").header_offset
        # Zero out just the one header.
        with open(fn, "r+b") as scribble:
            scribble.seek(zeroOffset, 0)
            scribble.write(b'0' * 4)
        with zipstream.ChunkingZipFile(fn) as czf:
            self.assertRaises(zipfile.BadZipfile, czf.readfile, "0")
            with czf.readfile("1") as zfe:
                self.assertEqual(zfe.read(), b"more contents") 

def check_read_with_bad_crc(self, compression):
        """Tests that files with bad CRCs raise a BadZipfile exception when read."""
        zipdata = self.zips_with_bad_crc[compression]

        # Using ZipFile.read()
        with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf:
            self.assertRaises(zipfile.BadZipfile, zipf.read, 'afile')

        # Using ZipExtFile.read()
        with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf:
            with zipf.open('afile', 'r') as corrupt_file:
                self.assertRaises(zipfile.BadZipfile, corrupt_file.read)

        # Same with small reads (in order to exercise the buffering logic)
        with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf:
            with zipf.open('afile', 'r') as corrupt_file:
                corrupt_file.MIN_READ_SIZE = 2
                with self.assertRaises(zipfile.BadZipfile):
                    while corrupt_file.read(2):
                        pass 

def check_read_with_bad_crc(self, compression):
        """Tests that files with bad CRCs raise a BadZipfile exception when read."""
        zipdata = self.zips_with_bad_crc[compression]

        # Using ZipFile.read()
        with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf:
            self.assertRaises(zipfile.BadZipfile, zipf.read, 'afile')

        # Using ZipExtFile.read()
        with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf:
            with zipf.open('afile', 'r') as corrupt_file:
                self.assertRaises(zipfile.BadZipfile, corrupt_file.read)

        # Same with small reads (in order to exercise the buffering logic)
        with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf:
            with zipf.open('afile', 'r') as corrupt_file:
                corrupt_file.MIN_READ_SIZE = 2
                with self.assertRaises(zipfile.BadZipfile):
                    while corrupt_file.read(2):
                        pass 

def test_invalidHeader(self):
        """
        A zipfile entry with the wrong magic number should raise BadZipfile for
        readfile(), but that should not affect other files in the archive.
        """
        fn = self.makeZipFile(["test contents",
                               "more contents"])
        with zipfile.ZipFile(fn, "r") as zf:
            zeroOffset = zf.getinfo("0").header_offset
        # Zero out just the one header.
        with open(fn, "r+b") as scribble:
            scribble.seek(zeroOffset, 0)
            scribble.write(b'0' * 4)
        with zipstream.ChunkingZipFile(fn) as czf:
            self.assertRaises(zipfile.BadZipfile, czf.readfile, "0")
            with czf.readfile("1") as zfe:
                self.assertEqual(zfe.read(), b"more contents") 

def test_filenameMismatch(self):
        """
        A zipfile entry with a different filename than is found in the central
        directory should raise BadZipfile.
        """
        fn = self.makeZipFile([b"test contents",
                               b"more contents"])
        with zipfile.ZipFile(fn, "r") as zf:
            info = zf.getinfo("0")
            info.filename = "not zero"
        with open(fn, "r+b") as scribble:
            scribble.seek(info.header_offset, 0)
            scribble.write(info.FileHeader())

        with zipstream.ChunkingZipFile(fn) as czf:
            self.assertRaises(zipfile.BadZipfile, czf.readfile, "0")
            with czf.readfile("1") as zfe:
                self.assertEqual(zfe.read(), b"more contents") 

def test_unsupportedCompression(self):
        """
        A zipfile which describes an unsupported compression mechanism should
        raise BadZipfile.
        """
        fn = self.mktemp()
        with zipfile.ZipFile(fn, "w") as zf:
            zi = zipfile.ZipInfo("0")
            zf.writestr(zi, "some data")
            # Mangle its compression type in the central directory; can't do
            # this before the writestr call or zipfile will (correctly) tell us
            # not to pass bad compression types :)
            zi.compress_type = 1234

        with zipstream.ChunkingZipFile(fn) as czf:
            self.assertRaises(zipfile.BadZipfile, czf.readfile, "0") 

def read_sheets(self):
        try:
            self.workbook = openpyxl.load_workbook(self.input_name, data_only=True)
        except BadZipFile as e:  # noqa
            # TODO when we have python3 only add 'from e' to show exception chain
            raise BadXLSXZipFile(
                "The supplied file has extension .xlsx but isn't an XLSX file."
            )

        self.sheet_names_map = OrderedDict(
            (sheet_name, sheet_name) for sheet_name in self.workbook.sheetnames
        )
        if self.include_sheets:
            for sheet in list(self.sheet_names_map):
                if sheet not in self.include_sheets:
                    self.sheet_names_map.pop(sheet)
        for sheet in self.exclude_sheets or []:
            self.sheet_names_map.pop(sheet, None)

        sheet_names = list(sheet for sheet in self.sheet_names_map.keys())
        self.sub_sheet_names = sheet_names
        self.configure_sheets() 

def _makeArchive(self, buffer: "io.BytesIO", root_path: str) -> Optional[ZipFile]:
        """Make a full archive from the given root path with the given name.

        :param root_path: The root directory to archive recursively.
        :return: The archive as bytes.
        """

        ignore_string = re.compile("|".join(self.IGNORED_FILES))
        try:
            archive = ZipFile(buffer, "w", ZIP_DEFLATED)
            for root, folders, files in os.walk(root_path):
                for item_name in folders + files:
                    absolute_path = os.path.join(root, item_name)
                    if ignore_string.search(absolute_path):
                        continue
                    archive.write(absolute_path, absolute_path[len(root_path) + len(os.sep):])
            archive.close()
            return archive
        except (IOError, OSError, BadZipfile) as error:
            Logger.log("e", "Could not create archive from user data directory: %s", error)
            self._showMessage(
                self.catalog.i18nc("@info:backup_failed",
                                   "Could not create archive from user data directory: {}".format(error)))
            return None 

def Run(self):
    try:
      zip_file = self._args[0]
      out_path = self._args[1]
    except IndexError:
      raise ActionError('Unable to determine desired paths from %s.' %
                        str(self._args))

    try:
      file_util.CreateDirectories(out_path)
    except file_util.Error:
      raise ActionError('Unable to create output path %s.' % out_path)

    try:
      zf = zipfile.ZipFile(zip_file)
      zf.extractall(out_path)
    except (IOError, zipfile.BadZipfile) as e:
      raise ActionError('Bad zip file given as input.  %s' % e) 

def retrieve(url):
    sess = requests.Session()
    print("Getting %s" % urlsplit(url).path.split("/")[-1])
    retrieved = sess.get(url, stream=True)
    # don't continue if something's wrong
    retrieved.raise_for_status()
    try:
        raw_zip = zipfile.ZipFile(io.BytesIO(retrieved.content))
        raw_zip.extractall(path)
    except zipfile.BadZipfile:
        # it's a tar
        tar = tarfile.open(mode="r:gz", fileobj=io.BytesIO(retrieved.content))
        tar.extractall(path) 

def _should_contain_zip_content(value):
    if not isinstance(value, bytes):
        # If it's not bytes it's basically impossible for
        # this to be valid zip content, but we'll at least
        # still try to load the contents as a zip file
        # to be absolutely sure.
        value = value.encode('utf-8')
    fileobj = six.BytesIO(value)
    try:
        with closing(zipfile.ZipFile(fileobj)) as f:
            f.infolist()
    except zipfile.BadZipfile:
        raise ValueError(ERROR_MSG) 

def _is_zip(self, response):
        archive = BytesIO(response.body)
        try:
            zip_file = zipfile.ZipFile(archive)
        except zipfile.BadZipfile:
            return

        namelist = zip_file.namelist()
        body = zip_file.read(namelist[0])
        respcls = responsetypes.from_args(filename=namelist[0], body=body)
        return response.replace(body=body, cls=respcls) 

def _load_zip(path):
    try:
        z = ZipFile(path, 'r')
    except (BadZipfile, LargeZipFile):
        raise BadZipfile('%s: %s' % (path, sys.exc_info()[1]))
    else:
        return z 

def read_wheel_metadata_file(source, path):
    # type: (ZipFile, str) -> bytes
    try:
        return source.read(path)
        # BadZipFile for general corruption, KeyError for missing entry,
        # and RuntimeError for password-protected files
    except (BadZipFile, KeyError, RuntimeError) as e:
        raise UnsupportedWheel(
            "could not read {!r} file: {!r}".format(path, e)
        ) 

def archive_context(filename):
    """
    Unzip filename to a temporary directory, set to the cwd.

    The unzipped target is cleaned up after.
    """
    tmpdir = tempfile.mkdtemp()
    log.warn('Extracting in %s', tmpdir)
    old_wd = os.getcwd()
    try:
        os.chdir(tmpdir)
        try:
            with ContextualZipFile(filename) as archive:
                archive.extractall()
        except zipfile.BadZipfile as err:
            if not err.args:
                err.args = ('', )
            err.args = err.args + (
                MEANINGFUL_INVALID_ZIP_ERR_MSG.format(filename),
            )
            raise

        # going in the directory
        subdir = os.path.join(tmpdir, os.listdir(tmpdir)[0])
        os.chdir(subdir)
        log.warn('Now working in %s', subdir)
        yield

    finally:
        os.chdir(old_wd)
        shutil.rmtree(tmpdir) 

def handle_application_zip(self, msg):
        self.log.info("Opening a ZIP attachment")
        data = yield msg.get_payload(decode=True)
        try:
            zip = zipfile.ZipFile(StringIO(data))
        except zipfile.BadZipfile as error:
            self.log.error("ZIP handling failed ({0})".format(error))
            idiokit.stop(False)

        for filename in zip.namelist():
            csv_data = zip.open(filename)

            self.log.info("Parsing CSV data from the ZIP attachment")
            result = yield self.parse_csv(filename, csv_data)
            idiokit.stop(result) 

def _ParsePropertiesXMLFile(self, xml_data):
    """Parses a properties XML file.

    Args:
      xml_data (bytes): data of a _rels/.rels XML file.

    Returns:
      dict[str, object]: properties.

    Raises:
      zipfile.BadZipfile: if the properties XML file cannot be read.
    """
    xml_root = ElementTree.fromstring(xml_data)

    properties = {}
    for xml_element in xml_root.iter():
      if not xml_element.text:
        continue

      # The property name is formatted as: {URL}name
      # For example: {http://purl.org/dc/terms/}modified
      _, _, name = xml_element.tag.partition('}')

      # Do not including the 'lpstr' attribute because it is very verbose.
      if name == 'lpstr':
        continue

      property_name = self._PROPERTY_NAMES.get(name, None)
      if not property_name:
        property_name = self._FormatPropertyName(name)

      properties[property_name] = xml_element.text

    return properties 

def ParseFileObject(self, parser_mediator, file_object):
    """Parses a compound ZIP file-like object.

    Args:
      parser_mediator (ParserMediator): mediates interactions between parsers
          and other components, such as storage and dfvfs.
      file_object (dfvfs.FileIO): a file-like object.

    Raises:
      UnableToParseFile: when the file cannot be parsed.
    """
    display_name = parser_mediator.GetDisplayName()

    if not zipfile.is_zipfile(file_object):
      raise errors.UnableToParseFile(
          '[{0:s}] unable to parse file: {1:s} with error: {2:s}'.format(
              self.NAME, display_name, 'Not a Zip file.'))

    try:
      zip_file = zipfile.ZipFile(file_object, 'r', allowZip64=True)
      self._ProcessZipFileWithPlugins(parser_mediator, zip_file)
      zip_file.close()

    # Some non-ZIP files return true for is_zipfile but will fail with a
    # negative seek (IOError) or another error.
    except (zipfile.BadZipfile, struct.error) as exception:
      raise errors.UnableToParseFile(
          '[{0:s}] unable to parse file: {1:s} with error: {2!s}'.format(
              self.NAME, display_name, exception)) 

def handle_application_zip(self, headers, fileobj):
        self.log.info("Opening a ZIP attachment")
        fileobj = self._decode(headers, fileobj)
        try:
            zip = zipfile.ZipFile(fileobj)
        except zipfile.BadZipfile as error:
            self.log.error("ZIP handling failed ({0})".format(error))
            idiokit.stop(False)

        for filename in zip.namelist():
            csv_data = StringIO(zip.read(filename))

            self.log.info("Parsing CSV data from the ZIP attachment")
            result = yield self.parse_csv(headers, filename, csv_data)
            idiokit.stop(result) 

def _resolve_archive_files(self):
        if self.config.archive:
            archive_path = os.path.join(self.root_dir, self.config.archive)
            if not os.path.exists(archive_path):
                raise InvalidInitException('archive file "%s" does not exist' % archive_path)
            try:
                archive = zipfile.ZipFile(archive_path, 'r')
            except zipfile.BadZipfile:
                raise InvalidInitException('bad archive: "%s"' % archive_path)
            return archive
        return None