added support for translating docx and pdf files

deep_translator/base.py

@@ -10,6 +10,8 @@ from deep_translator.exceptions import (
     InvalidSourceOrTargetLanguage,
     LanguageNotSupportedException,
 )
+from pathlib import Path
+from bs4 import BeautifulSoup as bs
 
 
 class BaseTranslator(ABC):
@@ -123,6 +125,17 @@ class BaseTranslator(ABC):
         """
         return NotImplemented("You need to implement the translate method!")
 
+    def _read_docx(self, f: str):
+        import docx2txt
+        return docx2txt.process(f)
+
+    def _read_pdf(self, f: str):
+        import pypdf
+
+        reader = pypdf.PdfReader(f)
+        page = reader.pages[0]
+        return page.extract_text()
+
     def _translate_file(self, path: str, **kwargs) -> str:
         """
         translate directly from file
@@ -131,12 +144,25 @@ class BaseTranslator(ABC):
         @param kwargs: additional args
         @return: str
         """
-        try:
+        if not isinstance(path, Path):
+            path = Path(path)
+
+        if not path.exists():
+            print("Path to the file is wrong!")
+            exit(1)
+
+        ext = path.suffix
+        
+        if ext == '.docx':
+            text = self._read_docx(f=str(path))
+
+        elif ext == '.pdf':
+            text = self._read_pdf(f=str(path))
+        else:
             with open(path, "r", encoding="utf-8") as f:
                 text = f.read().strip()
-            return self.translate(text)
-        except Exception as e:
-            raise e
+
+        return self.translate(text)
 
     def _translate_batch(self, batch: List[str], **kwargs) -> List[str]:
         """

deep_translator/google.py

@@ -121,6 +121,6 @@ class GoogleTranslator(BaseTranslator):
 
 
 if __name__ == "__main__":
-    trans = GoogleTranslator(source="auto", target="zh-CN")
-    res = trans.translate("good")
+    trans = GoogleTranslator(source="auto", target="de")
+    res = trans.translate_file(path='/home/nidhal/Documents/translate.pdf')
     print("translation: ", res)

poetry.lock

@@ -1,10 +1,10 @@
 [[package]]
 name = "alabaster"
-version = "0.7.12"
+version = "0.7.13"
 description = "A configurable sidebar-enabled Sphinx theme"
 category = "dev"
 optional = false
-python-versions = "*"
+python-versions = ">=3.6"
 
 [[package]]
 name = "atomicwrites"
@@ -16,21 +16,23 @@ python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
 
 [[package]]
 name = "attrs"
-version = "22.1.0"
+version = "22.2.0"
 description = "Classes Without Boilerplate"
 category = "dev"
 optional = false
-python-versions = ">=3.5"
+python-versions = ">=3.6"
 
 [package.extras]
-dev = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "mypy (>=0.900,!=0.940)", "pytest-mypy-plugins", "zope.interface", "furo", "sphinx", "sphinx-notfound-page", "pre-commit", "cloudpickle"]
-docs = ["furo", "sphinx", "zope.interface", "sphinx-notfound-page"]
-tests = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "mypy (>=0.900,!=0.940)", "pytest-mypy-plugins", "zope.interface", "cloudpickle"]
-tests_no_zope = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "mypy (>=0.900,!=0.940)", "pytest-mypy-plugins", "cloudpickle"]
+cov = ["attrs", "coverage-enable-subprocess", "coverage[toml] (>=5.3)"]
+dev = ["attrs"]
+docs = ["furo", "sphinx", "myst-parser", "zope.interface", "sphinx-notfound-page", "sphinxcontrib-towncrier", "towncrier"]
+tests = ["attrs", "zope.interface"]
+tests-no-zope = ["hypothesis", "pympler", "pytest (>=4.3.0)", "pytest-xdist", "cloudpickle", "mypy (>=0.971,<0.990)", "pytest-mypy-plugins"]
+tests_no_zope = ["hypothesis", "pympler", "pytest (>=4.3.0)", "pytest-xdist", "cloudpickle", "mypy (>=0.971,<0.990)", "pytest-mypy-plugins"]
 
 [[package]]
 name = "babel"
-version = "2.10.3"
+version = "2.11.0"
 description = "Internationalization utilities"
 category = "dev"
 optional = false
@@ -41,7 +43,7 @@ pytz = ">=2015.7"
 
 [[package]]
 name = "beautifulsoup4"
-version = "4.11.1"
+version = "4.11.2"
 description = "Screen-scraping library"
 category = "main"
 optional = false
@@ -56,11 +58,11 @@ lxml = ["lxml"]
 
 [[package]]
 name = "black"
-version = "22.8.0"
+version = "22.12.0"
 description = "The uncompromising code formatter."
 category = "dev"
 optional = false
-python-versions = ">=3.6.2"
+python-versions = ">=3.7"
 
 [package.dependencies]
 click = ">=8.0.0"
@@ -79,7 +81,7 @@ uvloop = ["uvloop (>=0.15.2)"]
 
 [[package]]
 name = "bleach"
-version = "5.0.1"
+version = "6.0.0"
 description = "An easy safelist-based HTML-sanitizing tool."
 category = "dev"
 optional = false
@@ -91,11 +93,10 @@ webencodings = "*"
 
 [package.extras]
 css = ["tinycss2 (>=1.1.0,<1.2)"]
-dev = ["build (==0.8.0)", "flake8 (==4.0.1)", "hashin (==0.17.0)", "pip-tools (==6.6.2)", "pytest (==7.1.2)", "Sphinx (==4.3.2)", "tox (==3.25.0)", "twine (==4.0.1)", "wheel (==0.37.1)", "black (==22.3.0)", "mypy (==0.961)"]
 
 [[package]]
 name = "certifi"
-version = "2022.9.14"
+version = "2022.12.7"
 description = "Python package for providing Mozilla's CA Bundle."
 category = "main"
 optional = false
@@ -114,14 +115,11 @@ pycparser = "*"
 
 [[package]]
 name = "charset-normalizer"
-version = "2.1.1"
+version = "3.0.1"
 description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
 category = "main"
 optional = false
-python-versions = ">=3.6.0"
-
-[package.extras]
-unicode_backport = ["unicodedata2"]
+python-versions = "*"
 
 [[package]]
 name = "click"
@@ -148,11 +146,11 @@ click = "*"
 
 [[package]]
 name = "colorama"
-version = "0.4.5"
+version = "0.4.6"
 description = "Cross-platform colored terminal text."
 category = "dev"
 optional = false
-python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
 
 [[package]]
 name = "coverage"
@@ -167,7 +165,7 @@ toml = ["toml"]
 
 [[package]]
 name = "cryptography"
-version = "38.0.1"
+version = "39.0.0"
 description = "cryptography is a package which provides cryptographic recipes and primitives to Python developers."
 category = "dev"
 optional = false
@@ -177,9 +175,9 @@ python-versions = ">=3.6"
 cffi = ">=1.12"
 
 [package.extras]
-docs = ["sphinx (>=1.6.5,!=1.8.0,!=3.1.0,!=3.1.1)", "sphinx-rtd-theme"]
+docs = ["sphinx (>=1.6.5,!=1.8.0,!=3.1.0,!=3.1.1,!=5.2.0,!=5.2.0.post0)", "sphinx-rtd-theme"]
 docstest = ["pyenchant (>=1.6.11)", "twine (>=1.12.0)", "sphinxcontrib-spelling (>=4.0.1)"]
-pep8test = ["black", "flake8", "flake8-import-order", "pep8-naming"]
+pep8test = ["black", "ruff"]
 sdist = ["setuptools-rust (>=0.11.4)"]
 ssh = ["bcrypt (>=3.1.5)"]
 test = ["pytest (>=6.2.0)", "pytest-benchmark", "pytest-cov", "pytest-subtests", "pytest-xdist", "pretend", "iso8601", "pytz", "hypothesis (>=1.11.4,!=3.79.2)"]
@@ -192,6 +190,14 @@ category = "dev"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
 
+[[package]]
+name = "docx2txt"
+version = "0.8"
+description = "A pure python-based utility to extract text and images from docx files."
+category = "main"
+optional = false
+python-versions = "*"
+
 [[package]]
 name = "dotty-dict"
 version = "1.3.1"
@@ -202,18 +208,18 @@ python-versions = ">=3.5,<4.0"
 
 [[package]]
 name = "gitdb"
-version = "4.0.9"
+version = "4.0.10"
 description = "Git Object Database"
 category = "dev"
 optional = false
-python-versions = ">=3.6"
+python-versions = ">=3.7"
 
 [package.dependencies]
 smmap = ">=3.0.1,<6"
 
 [[package]]
 name = "gitpython"
-version = "3.1.27"
+version = "3.1.30"
 description = "GitPython is a python library used to interact with Git repositories"
 category = "dev"
 optional = false
@@ -241,7 +247,7 @@ python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
 
 [[package]]
 name = "importlib-metadata"
-version = "4.12.0"
+version = "6.0.0"
 description = "Read metadata from Python packages"
 category = "dev"
 optional = false
@@ -252,21 +258,36 @@ typing-extensions = {version = ">=3.6.4", markers = "python_version < \"3.8\""}
 zipp = ">=0.5"
 
 [package.extras]
-docs = ["sphinx", "jaraco.packaging (>=9)", "rst.linker (>=1.9)"]
+docs = ["sphinx (>=3.5)", "jaraco.packaging (>=9)", "rst.linker (>=1.9)", "furo", "sphinx-lint", "jaraco.tidelift (>=1.4)"]
 perf = ["ipython"]
-testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytest-cov", "pytest-enabler (>=1.3)", "packaging", "pyfakefs", "flufl.flake8", "pytest-perf (>=0.9.2)", "pytest-black (>=0.3.7)", "pytest-mypy (>=0.9.1)", "importlib-resources (>=1.3)"]
+testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "flake8 (<5)", "pytest-cov", "pytest-enabler (>=1.3)", "packaging", "pyfakefs", "flufl.flake8", "pytest-perf (>=0.9.2)", "pytest-black (>=0.3.7)", "pytest-mypy (>=0.9.1)", "pytest-flake8", "importlib-resources (>=1.3)"]
+
+[[package]]
+name = "importlib-resources"
+version = "5.10.2"
+description = "Read resources from Python packages"
+category = "dev"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+zipp = {version = ">=3.1.0", markers = "python_version < \"3.10\""}
+
+[package.extras]
+docs = ["sphinx (>=3.5)", "jaraco.packaging (>=9)", "rst.linker (>=1.9)", "furo", "sphinx-lint", "jaraco.tidelift (>=1.4)"]
+testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "flake8 (<5)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-black (>=0.3.7)", "pytest-mypy (>=0.9.1)", "pytest-flake8"]
 
 [[package]]
 name = "iniconfig"
-version = "1.1.1"
-description = "iniconfig: brain-dead simple config-ini parsing"
+version = "2.0.0"
+description = "brain-dead simple config-ini parsing"
 category = "dev"
 optional = false
-python-versions = "*"
+python-versions = ">=3.7"
 
 [[package]]
 name = "invoke"
-version = "1.7.1"
+version = "1.7.3"
 description = "Pythonic task execution"
 category = "dev"
 optional = false
@@ -274,21 +295,21 @@ python-versions = "*"
 
 [[package]]
 name = "isort"
-version = "5.10.1"
+version = "5.11.5"
 description = "A Python utility / library to sort Python imports."
 category = "dev"
 optional = false
-python-versions = ">=3.6.1,<4.0"
+python-versions = ">=3.7.0"
 
 [package.extras]
-pipfile_deprecated_finder = ["pipreqs", "requirementslib"]
-requirements_deprecated_finder = ["pipreqs", "pip-api"]
+pipfile-deprecated-finder = ["pipreqs", "requirementslib", "pip-shims (>=0.5.2)"]
+requirements-deprecated-finder = ["pipreqs", "pip-api"]
 colors = ["colorama (>=0.4.3,<0.5.0)"]
 plugins = ["setuptools"]
 
 [[package]]
 name = "jaraco.classes"
-version = "3.2.2"
+version = "3.2.3"
 description = "Utility functions for Python class constructs"
 category = "dev"
 optional = false
@@ -298,8 +319,8 @@ python-versions = ">=3.7"
 more-itertools = "*"
 
 [package.extras]
-docs = ["sphinx", "jaraco.packaging (>=9)", "rst.linker (>=1.9)", "jaraco.tidelift (>=1.4)"]
-testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-black (>=0.3.7)", "pytest-mypy (>=0.9.1)"]
+docs = ["sphinx (>=3.5)", "jaraco.packaging (>=9)", "rst.linker (>=1.9)", "jaraco.tidelift (>=1.4)"]
+testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "flake8 (<5)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-black (>=0.3.7)", "pytest-mypy (>=0.9.1)"]
 
 [[package]]
 name = "jeepney"
@@ -329,26 +350,28 @@ i18n = ["Babel (>=2.7)"]
 
 [[package]]
 name = "keyring"
-version = "23.9.3"
+version = "23.13.1"
 description = "Store and access your passwords safely."
 category = "dev"
 optional = false
 python-versions = ">=3.7"
 
 [package.dependencies]
-importlib-metadata = {version = ">=3.6", markers = "python_version < \"3.10\""}
+importlib-metadata = {version = ">=4.11.4", markers = "python_version < \"3.12\""}
+importlib-resources = {version = "*", markers = "python_version < \"3.9\""}
 "jaraco.classes" = "*"
 jeepney = {version = ">=0.4.2", markers = "sys_platform == \"linux\""}
-pywin32-ctypes = {version = "<0.1.0 || >0.1.0,<0.1.1 || >0.1.1", markers = "sys_platform == \"win32\""}
+pywin32-ctypes = {version = ">=0.2.0", markers = "sys_platform == \"win32\""}
 SecretStorage = {version = ">=3.2", markers = "sys_platform == \"linux\""}
 
 [package.extras]
-docs = ["sphinx", "jaraco.packaging (>=9)", "rst.linker (>=1.9)", "jaraco.tidelift (>=1.4)"]
-testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "flake8 (<5)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-black (>=0.3.7)", "pytest-mypy (>=0.9.1)"]
+completion = ["shtab"]
+docs = ["sphinx (>=3.5)", "jaraco.packaging (>=9)", "rst.linker (>=1.9)", "furo", "jaraco.tidelift (>=1.4)"]
+testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "flake8 (<5)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-black (>=0.3.7)", "pytest-mypy (>=0.9.1)", "pytest-flake8"]
 
 [[package]]
 name = "markupsafe"
-version = "2.1.1"
+version = "2.1.2"
 description = "Safely add untrusted strings to HTML/XML markup."
 category = "dev"
 optional = false
@@ -356,34 +379,31 @@ python-versions = ">=3.7"
 
 [[package]]
 name = "more-itertools"
-version = "8.14.0"
+version = "9.0.0"
 description = "More routines for operating on iterables, beyond itertools"
 category = "dev"
 optional = false
-python-versions = ">=3.5"
+python-versions = ">=3.7"
 
 [[package]]
 name = "mypy-extensions"
-version = "0.4.3"
-description = "Experimental type system extensions for programs checked with the mypy typechecker."
+version = "1.0.0"
+description = "Type system extensions for programs checked with the mypy type checker."
 category = "dev"
 optional = false
-python-versions = "*"
+python-versions = ">=3.5"
 
 [[package]]
 name = "packaging"
-version = "21.3"
+version = "23.0"
 description = "Core utilities for Python packages"
 category = "dev"
 optional = false
-python-versions = ">=3.6"
-
-[package.dependencies]
-pyparsing = ">=2.0.2,<3.0.5 || >3.0.5"
+python-versions = ">=3.7"
 
 [[package]]
 name = "pathspec"
-version = "0.10.1"
+version = "0.11.0"
 description = "Utility library for gitignore style pattern matching of file paths."
 category = "dev"
 optional = false
@@ -391,26 +411,29 @@ python-versions = ">=3.7"
 
 [[package]]
 name = "pkginfo"
-version = "1.8.3"
-description = "Query metadatdata from sdists / bdists / installed packages."
+version = "1.9.6"
+description = "Query metadata from sdists / bdists / installed packages."
 category = "dev"
 optional = false
-python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*"
+python-versions = ">=3.6"
 
 [package.extras]
-testing = ["coverage", "nose"]
+testing = ["pytest", "pytest-cov"]
 
 [[package]]
 name = "platformdirs"
-version = "2.5.2"
-description = "A small Python module for determining appropriate platform-specific dirs, e.g. a \"user data dir\"."
+version = "2.6.2"
+description = "A small Python package for determining appropriate platform-specific dirs, e.g. a \"user data dir\"."
 category = "dev"
 optional = false
 python-versions = ">=3.7"
 
+[package.dependencies]
+typing-extensions = {version = ">=4.4", markers = "python_version < \"3.8\""}
+
 [package.extras]
-docs = ["furo (>=2021.7.5b38)", "proselint (>=0.10.2)", "sphinx-autodoc-typehints (>=1.12)", "sphinx (>=4)"]
-test = ["appdirs (==1.4.4)", "pytest-cov (>=2.7)", "pytest-mock (>=3.6)", "pytest (>=6)"]
+docs = ["furo (>=2022.12.7)", "proselint (>=0.13)", "sphinx-autodoc-typehints (>=1.19.5)", "sphinx (>=5.3)"]
+test = ["appdirs (==1.4.4)", "covdefaults (>=2.2.2)", "pytest-cov (>=4)", "pytest-mock (>=3.10)", "pytest (>=7.2)"]
 
 [[package]]
 name = "pluggy"
@@ -445,7 +468,7 @@ python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
 
 [[package]]
 name = "pygments"
-version = "2.13.0"
+version = "2.14.0"
 description = "Pygments is a syntax highlighting package written in Python."
 category = "dev"
 optional = false
@@ -455,15 +478,22 @@ python-versions = ">=3.6"
 plugins = ["importlib-metadata"]
 
 [[package]]
-name = "pyparsing"
-version = "3.0.9"
-description = "pyparsing module - Classes and methods to define and execute parsing grammars"
-category = "dev"
+name = "pypdf"
+version = "3.3.0"
+description = "A pure-python PDF library capable of splitting, merging, cropping, and transforming PDF files"
+category = "main"
 optional = false
-python-versions = ">=3.6.8"
+python-versions = ">=3.6"
+
+[package.dependencies]
+typing_extensions = {version = ">=3.10.0.0", markers = "python_version < \"3.10\""}
 
 [package.extras]
-diagrams = ["railroad-diagrams", "jinja2"]
+crypto = ["pycryptodome"]
+dev = ["black", "pip-tools", "pre-commit (<2.18.0)", "pytest-cov", "flit", "wheel"]
+docs = ["sphinx", "sphinx-rtd-theme", "myst-parser"]
+full = ["pycryptodome", "pillow"]
+image = ["pillow"]
 
 [[package]]
 name = "pytest"
@@ -501,7 +531,7 @@ testing = ["pytest (>=4.6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytes
 
 [[package]]
 name = "python-gitlab"
-version = "3.9.0"
+version = "3.13.0"
 description = "Interact with GitLab API"
 category = "dev"
 optional = false
@@ -509,7 +539,7 @@ python-versions = ">=3.7.0"
 
 [package.dependencies]
 requests = ">=2.25.0"
-requests-toolbelt = ">=0.9.1"
+requests-toolbelt = ">=0.10.1"
 
 [package.extras]
 autocompletion = ["argcomplete (>=1.10.0,<3)"]
@@ -517,7 +547,7 @@ yaml = ["PyYaml (>=5.2)"]
 
 [[package]]
 name = "python-semantic-release"
-version = "7.31.4"
+version = "7.33.1"
 description = "Automatic Semantic Versioning for Python projects"
 category = "dev"
 optional = false
@@ -540,11 +570,11 @@ twine = ">=3,<4"
 dev = ["tox", "isort", "black"]
 docs = ["Sphinx (==1.3.6)", "Jinja2 (==3.0.3)"]
 mypy = ["mypy", "types-requests"]
-test = ["coverage (>=5,<6)", "pytest (>=5,<6)", "pytest-xdist (>=1,<2)", "pytest-mock (>=2,<3)", "responses (==0.13.3)", "mock (==1.3.0)"]
+test = ["coverage (>=5,<6)", "pytest (>=7,<8)", "pytest-xdist (>=1,<2)", "pytest-mock (>=2,<3)", "responses (==0.13.3)", "mock (==1.3.0)"]
 
 [[package]]
 name = "pytz"
-version = "2022.2.1"
+version = "2022.7.1"
 description = "World timezone definitions, modern and historical"
 category = "dev"
 optional = false
@@ -560,7 +590,7 @@ python-versions = "*"
 
 [[package]]
 name = "readme-renderer"
-version = "37.1"
+version = "37.3"
 description = "readme_renderer is a library for rendering \"readme\" descriptions for Warehouse"
 category = "dev"
 optional = false
@@ -576,7 +606,7 @@ md = ["cmarkgfm (>=0.8.0)"]
 
 [[package]]
 name = "requests"
-version = "2.28.1"
+version = "2.28.2"
 description = "Python HTTP for Humans."
 category = "main"
 optional = false
@@ -584,7 +614,7 @@ python-versions = ">=3.7, <4"
 
 [package.dependencies]
 certifi = ">=2017.4.17"
-charset-normalizer = ">=2,<3"
+charset-normalizer = ">=2,<4"
 idna = ">=2.5,<4"
 urllib3 = ">=1.21.1,<1.27"
 
@@ -594,11 +624,11 @@ use_chardet_on_py3 = ["chardet (>=3.0.2,<6)"]
 
 [[package]]
 name = "requests-toolbelt"
-version = "0.9.1"
+version = "0.10.1"
 description = "A utility belt for advanced users of python-requests"
 category = "dev"
 optional = false
-python-versions = "*"
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
 
 [package.dependencies]
 requests = ">=2.0.1,<3.0.0"
@@ -787,11 +817,11 @@ python-versions = ">=3.7"
 
 [[package]]
 name = "tomlkit"
-version = "0.11.4"
+version = "0.11.6"
 description = "Style preserving TOML library"
 category = "dev"
 optional = false
-python-versions = ">=3.6,<4.0"
+python-versions = ">=3.6"
 
 [[package]]
 name = "tqdm"
@@ -840,19 +870,19 @@ python-versions = ">=3.6"
 
 [[package]]
 name = "typing-extensions"
-version = "4.3.0"
+version = "4.4.0"
 description = "Backported and Experimental Type Hints for Python 3.7+"
-category = "dev"
+category = "main"
 optional = false
 python-versions = ">=3.7"
 
 [[package]]
 name = "urllib3"
-version = "1.26.12"
+version = "1.26.14"
 description = "HTTP library with thread-safe connection pooling, file post, and more."
 category = "main"
 optional = false
-python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*, <4"
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*"
 
 [package.extras]
 brotli = ["brotlicffi (>=0.8.0)", "brotli (>=1.0.9)", "brotlipy (>=0.6.0)"]
@@ -869,20 +899,20 @@ python-versions = "*"
 
 [[package]]
 name = "zipp"
-version = "3.8.1"
+version = "3.12.0"
 description = "Backport of pathlib-compatible object wrapper for zip files"
 category = "dev"
 optional = false
 python-versions = ">=3.7"
 
 [package.extras]
-docs = ["sphinx", "jaraco.packaging (>=9)", "rst.linker (>=1.9)", "jaraco.tidelift (>=1.4)"]
-testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytest-cov", "pytest-enabler (>=1.3)", "jaraco.itertools", "func-timeout", "pytest-black (>=0.3.7)", "pytest-mypy (>=0.9.1)"]
+docs = ["sphinx (>=3.5)", "jaraco.packaging (>=9)", "rst.linker (>=1.9)", "furo", "sphinx-lint", "jaraco.tidelift (>=1.4)"]
+testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "flake8 (<5)", "pytest-cov", "pytest-enabler (>=1.3)", "jaraco.itertools", "func-timeout", "jaraco.functools", "more-itertools", "pytest-black (>=0.3.7)", "pytest-mypy (>=0.9.1)", "pytest-flake8"]
 
 [metadata]
 lock-version = "1.1"
 python-versions = "^3.7"
-content-hash = "054ce1ccb3c4971456c37b9161434ede7867a152627dd1fd40a2b7b7b83d3bf2"
+content-hash = "cd34af7874c97d88a33945a0bdd55f8094141ff27937a19a1a08e6b232f6ecea"
 
 [metadata.files]
 alabaster = []
@@ -901,12 +931,14 @@ colorama = []
 coverage = []
 cryptography = []
 docutils = []
+docx2txt = []
 dotty-dict = []
 gitdb = []
 gitpython = []
 idna = []
 imagesize = []
 importlib-metadata = []
+importlib-resources = []
 iniconfig = []
 invoke = []
 isort = []
@@ -925,7 +957,7 @@ pluggy = []
 py = []
 pycparser = []
 pygments = []
-pyparsing = []
+pypdf = []
 pytest = []
 pytest-runner = []
 python-gitlab = []

pyproject.toml

@@ -31,6 +31,8 @@ dt = 'deep_translator.__main__:main'
 python = "^3.7"
 beautifulsoup4 = "^4.9.1"
 requests = "^2.23.0"
+docx2txt = {version = "^0.8", extras = ["docx"]}
+pypdf = {version = "^3.3.0", extras = ["pdf"]}
 
 [tool.poetry.dev-dependencies]
 wheel = "^0.38.4"