pyxtxt 0.0.1__tar.gz

pyxtxt-0.0.1/LICENCSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Giuseppe Levi
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

pyxtxt-0.0.1/PKG-INFO

@@ -0,0 +1,183 @@
+Metadata-Version: 2.4
+Name: pyxtxt
+Version: 0.0.1
+Summary: A Python library for extracting text from different types of files (PDF, DOCX, PPTX, XLSX, ODT, ecc.).
+Author-email: Giuseppe Levi <giuseppe.levi@gmail.com>
+License: MIT License
+        
+        Copyright (c) 2025 Giuseppe Levi
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+Requires-Dist: python-magic; sys_platform != "win32"
+Requires-Dist: python-magic-bin; sys_platform == "win32"
+Provides-Extra: pdf
+Requires-Dist: PyMuPDF; extra == "pdf"
+Provides-Extra: docx
+Requires-Dist: python-docx; extra == "docx"
+Provides-Extra: presentation
+Requires-Dist: python-pptx; extra == "presentation"
+Provides-Extra: spreadsheet
+Requires-Dist: openpyxl; extra == "spreadsheet"
+Requires-Dist: xlrd; extra == "spreadsheet"
+Provides-Extra: odf
+Requires-Dist: odfpy; extra == "odf"
+Provides-Extra: html
+Requires-Dist: beautifulsoup4; extra == "html"
+Requires-Dist: lxml; extra == "html"
+Provides-Extra: doc
+Requires-Dist: textract; extra == "doc"
+Provides-Extra: all
+Requires-Dist: textract; extra == "all"
+Requires-Dist: PyMuPDF; extra == "all"
+Requires-Dist: python-docx; extra == "all"
+Requires-Dist: python-pptx; extra == "all"
+Requires-Dist: openpyxl; extra == "all"
+Requires-Dist: xlrd; extra == "all"
+Requires-Dist: odfpy; extra == "all"
+Requires-Dist: beautifulsoup4; extra == "all"
+Requires-Dist: lxml; extra == "all"
+
+# PyxTxt
+
+[![PyPI version](https://img.shields.io/pypi/v/pyxtxt.svg)](https://pypi.org/project/pyxtxt/)
+[![Python versions](https://img.shields.io/pypi/pyversions/pyxtxt.svg)](https://pypi.org/project/pyxtxt/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+**PyxTxt** is a simple and powerful Python library to extract text from various file formats.  
+It supports PDF, DOCX, XLSX, PPTX, ODT, HTML, XML, TXT, legacy XLS files, and more.
+
+---
+
+## ✨ Features
+
+- Extracts text from both file paths and in-memory buffers (`io.BytesIO`).
+- Supports multiple formats: PDF, DOCX, PPTX, XLSX, ODT, HTML, XML, TXT, legacy Office files (.xls,.ppt).
+- Automatically detects MIME type using `python-magic`.
+- Compatible with modern and legacy formats.
+- Can handle streamed content without saving to disk (with some limitations).
+
+---
+
+## 📦 Installation 
+
+The library i modular so you can install all modules:
+
+```bash
+pip install pyxtxt[all]
+```
+or just the modules you need:
+```bash
+pip install pyxtxt[pdf,odf,docx,presentation,spreadsheet,html]
+```
+Beause needed libraries are common installing the html module will enable also SVG and XML.
+The architecture is designed to be able to grow with new modules to work with other formats as well.
+## ⚠️ Note: You must have libmagic installed on your system (required by python-magic).
+The pyproject.toml file should select the correct version for your system. But if you have any problem you can install it manually.
+
+**On Ubuntu/Debian:**
+
+```bash
+sudo apt install libmagic1
+```
+
+**On Mac (Homebrew):**
+
+```bash
+brew install libmagic
+```
+**On Windows:**
+
+Use python-magic-bin instead of python-magic for easier installation.
+
+## 🛠️ Dependencies
+- PyMuPDF (fitz)
+
+- beautifulsoup4
+
+- python-docx
+
+- python-pptx
+
+- odfpy
+
+- openpyxl
+
+- lxml
+
+- xlrd (<2.0.0)
+
+- python-magic
+
+Dependencies are automatically installed from pyproject.toml.
+
+## 📚 Usage Example
+Extract text from a file path:
+
+```python
+from pyxtxt import xtxt
+
+text = xtxt("document.pdf")
+print(text)
+```
+Extract text from a file-like buffer:
+
+```python
+import io
+
+with open("document.docx", "rb") as f:
+    buffer = io.BytesIO(f.read())
+
+from pyxtxt import xtxt
+text = xtxt(buffer)
+print(text)
+```
+Show available formats:
+from pyxtxt import extxt_available_formats
+```python
+from pyxtxt import extxt_available_formats
+text = extxt_available_formats()
+print(text)
+# For a pretty printing
+text = extxt_available_formats(True)
+print(text)
+```
+## ⚠️ Known Limitations
+When passing a raw stream (io.BytesIO) without a filename, legacy files (.doc, .xls, .ppt) may not be correctly detected.
+
+This is a limitation of libmagic beacuse the signature byte sequence at the start of doc/xls/ppt is exactly the same (b'\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1'),
+not of pyxtxt.
+
+If available, using the original filename is highly recommended.
+
+To extract text from documents in MSWrite's old .doc format, it is necessary to install antiword.
+
+```bash
+sudo apt-get update
+sudo apt-get -y install antiword
+```
+
+## 🔒 License
+Distributed under the MIT License.
+
+The software is provided "as is" without any warranty of any kind.
+
+Pull requests, issues, and feedback are warmly welcome! 🚀

pyxtxt-0.0.1/README.md

@@ -0,0 +1,125 @@
+# PyxTxt
+
+[![PyPI version](https://img.shields.io/pypi/v/pyxtxt.svg)](https://pypi.org/project/pyxtxt/)
+[![Python versions](https://img.shields.io/pypi/pyversions/pyxtxt.svg)](https://pypi.org/project/pyxtxt/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+**PyxTxt** is a simple and powerful Python library to extract text from various file formats.  
+It supports PDF, DOCX, XLSX, PPTX, ODT, HTML, XML, TXT, legacy XLS files, and more.
+
+---
+
+## ✨ Features
+
+- Extracts text from both file paths and in-memory buffers (`io.BytesIO`).
+- Supports multiple formats: PDF, DOCX, PPTX, XLSX, ODT, HTML, XML, TXT, legacy Office files (.xls,.ppt).
+- Automatically detects MIME type using `python-magic`.
+- Compatible with modern and legacy formats.
+- Can handle streamed content without saving to disk (with some limitations).
+
+---
+
+## 📦 Installation 
+
+The library i modular so you can install all modules:
+
+```bash
+pip install pyxtxt[all]
+```
+or just the modules you need:
+```bash
+pip install pyxtxt[pdf,odf,docx,presentation,spreadsheet,html]
+```
+Beause needed libraries are common installing the html module will enable also SVG and XML.
+The architecture is designed to be able to grow with new modules to work with other formats as well.
+## ⚠️ Note: You must have libmagic installed on your system (required by python-magic).
+The pyproject.toml file should select the correct version for your system. But if you have any problem you can install it manually.
+
+**On Ubuntu/Debian:**
+
+```bash
+sudo apt install libmagic1
+```
+
+**On Mac (Homebrew):**
+
+```bash
+brew install libmagic
+```
+**On Windows:**
+
+Use python-magic-bin instead of python-magic for easier installation.
+
+## 🛠️ Dependencies
+- PyMuPDF (fitz)
+
+- beautifulsoup4
+
+- python-docx
+
+- python-pptx
+
+- odfpy
+
+- openpyxl
+
+- lxml
+
+- xlrd (<2.0.0)
+
+- python-magic
+
+Dependencies are automatically installed from pyproject.toml.
+
+## 📚 Usage Example
+Extract text from a file path:
+
+```python
+from pyxtxt import xtxt
+
+text = xtxt("document.pdf")
+print(text)
+```
+Extract text from a file-like buffer:
+
+```python
+import io
+
+with open("document.docx", "rb") as f:
+    buffer = io.BytesIO(f.read())
+
+from pyxtxt import xtxt
+text = xtxt(buffer)
+print(text)
+```
+Show available formats:
+from pyxtxt import extxt_available_formats
+```python
+from pyxtxt import extxt_available_formats
+text = extxt_available_formats()
+print(text)
+# For a pretty printing
+text = extxt_available_formats(True)
+print(text)
+```
+## ⚠️ Known Limitations
+When passing a raw stream (io.BytesIO) without a filename, legacy files (.doc, .xls, .ppt) may not be correctly detected.
+
+This is a limitation of libmagic beacuse the signature byte sequence at the start of doc/xls/ppt is exactly the same (b'\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1'),
+not of pyxtxt.
+
+If available, using the original filename is highly recommended.
+
+To extract text from documents in MSWrite's old .doc format, it is necessary to install antiword.
+
+```bash
+sudo apt-get update
+sudo apt-get -y install antiword
+```
+
+## 🔒 License
+Distributed under the MIT License.
+
+The software is provided "as is" without any warranty of any kind.
+
+Pull requests, issues, and feedback are warmly welcome! 🚀

pyxtxt-0.0.1/pyproject.toml

@@ -0,0 +1,58 @@
+[project]
+name = "pyxtxt"
+version = "0.0.1"
+description = "A Python library for extracting text from different types of files (PDF, DOCX, PPTX, XLSX, ODT, ecc.)."
+readme = "README.md"
+requires-python = ">=3.7"
+license = { file = "LICENCSE" }
+authors = [
+  { name = "Giuseppe Levi", email = "giuseppe.levi@gmail.com" }
+]
+dependencies = [
+  "python-magic; sys_platform != 'win32'",
+  "python-magic-bin; sys_platform == 'win32'"
+]
+[project.optional-dependencies]
+pdf = [
+  "PyMuPDF",
+]
+docx = [
+  "python-docx",
+]
+presentation = [
+  "python-pptx",
+]
+spreadsheet = [
+  "openpyxl",
+  "xlrd",
+]
+odf = [
+  "odfpy",
+]
+html = [
+  "beautifulsoup4",
+  "lxml",
+]
+doc = [
+"textract",
+]
+all = [
+  "textract",
+  "PyMuPDF",
+  "python-docx",
+  "python-pptx",
+  "openpyxl",
+  "xlrd",
+  "odfpy",
+  "beautifulsoup4",
+  "lxml",
+]
+
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+
+[tool.setuptools.packages.find]
+where = ["src"]
+

pyxtxt-0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

pyxtxt-0.0.1/src/pyxtxt/__init__.py

@@ -0,0 +1 @@
+from .core import xtxt, extxt_available_formats

pyxtxt-0.0.1/src/pyxtxt/core.py

@@ -0,0 +1,71 @@
+from .estrattori import estrattori
+from functools import singledispatch
+import io
+import magic
+
+@singledispatch
+def xtxt(file_input):
+    raise NotImplementedError(f"Type not supported : {type(file_input)}")
+
+# Caso 1: file path (str)
+@xtxt.register
+def _(file_input: str):
+    try:
+        with open(file_input, "rb") as f:
+            data = f.read()
+        buffer = io.BytesIO(data)
+        buffer.name=file_input
+        buffer.mimeType=magic.Magic(mime=True).from_file(file_input)
+        return xtxt(buffer)
+    except Exception as e:
+        print(f"⚠️ File opening error'{file_input}': {e}")
+        return None
+
+# Caso 2: buffer (BytesIO)
+@xtxt.register
+def _(file_input: io.BytesIO):
+    try:
+
+
+        # Mappa dei MIME Type gestiti dagli estrattori
+        # estrattori = {
+            # "application/pdf": xtxt_pdf,
+            # "application/vnd.openxmlformats-officedocument.wordprocessingml.document": xtxt_docx,
+            # "application/vnd.openxmlformats-officedocument.presentationml.presentation": xtxt_pptx,
+            # "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": xtxt_xlsx,
+            # "application/vnd.ms-excel": xtxt_xls,
+            # "text/plain": xtxt_txt,
+            # "application/vnd.oasis.opendocument.text": xtxt_odt,
+            # "text/html": xtxt_html,
+# #            "text/rtf": xtxt_rtf,
+            # "application/xml": xtxt_xml,
+            # "text/xml": xtxt_xml,
+        # }
+        if hasattr(file_input,'mimeType'):
+            mime_type=file_input.mimeType
+        else:
+            mime_type = magic.Magic(mime=True).from_buffer(file_input.read(2048))
+            file_input.name='IO_buffer'
+            file_input.seek(0)
+        print(mime_type)
+        if mime_type.startswith("text/"):
+            if (mime_type != "text/html") and (mime_type != "text/xml") and (mime_type != "text/plain"):
+               print(f"📄 File recognized as text type: {mime_type}, treated as text/plain")
+               mime_type = "text/plain"
+        if mime_type not in estrattori:
+            print(f"⚠️ MIME type not supported {mime_type} ({file_input.name}) ignored.")
+            return None
+
+
+        # Estrai il testo
+        testo = estrattori[mime_type](file_input)
+        return f"{testo}"
+    except  Exception as e:
+        print(f"❌ Error while reading: {e}")
+        return None
+def extxt_available_formats(pretty=False):
+    if pretty:
+        from .estrattori import pretty_names
+        return sorted({pretty_names.get(mime, mime) for mime in estrattori.keys()})
+    else:
+        return sorted(estrattori.keys())

pyxtxt-0.0.1/src/pyxtxt/estrattori/__init__.py

@@ -0,0 +1,18 @@
+import os
+import importlib
+
+# Qui vengono registrati gli estrattori disponibili
+estrattori = {}
+pretty_names = {}
+
+def register_extractor(mime_type, func, name=None):
+    estrattori[mime_type] = func
+    if name:
+        pretty_names[mime_type] = name
+
+# Carica automaticamente tutti i moduli presenti
+current_dir = os.path.dirname(__file__)
+for filename in os.listdir(current_dir):
+    if filename.endswith(".py") and filename != "__init__.py":
+        module_name = f"{__name__}.{filename[:-3]}"
+        importlib.import_module(module_name)

pyxtxt-0.0.1/src/pyxtxt/estrattori/doc.py

@@ -0,0 +1,26 @@
+
+from . import register_extractor
+import shutil
+try:
+    import textract
+except ImportError:
+    Lib = None
+if Lib:
+def xtxt_doc(file_buffer):
+
+    if shutil.which("antiword") is None:
+       print("⚠️ 'antiword' is not installed or is not in the system PATH.")
+       return None
+    try:
+        file_buffer.seek(0)
+        data = file_buffer.read()
+        testo = textract.process("temp.doc", input_data=data)
+        return testo.decode("utf-8").strip()
+    except Exception as e:
+        print(f"⚠️  Error during extraction from DOC: {e}")
+        return None
+register_extractor(
+     "application/msword",
+     xtxt__doc,
+    name="DOC"
+)

pyxtxt-0.0.1/src/pyxtxt/estrattori/docx.py

@@ -0,0 +1,35 @@
+from . import register_extractor
+import io
+import zipfile
+try:
+    from docx import Document
+except ImportError:
+    Lib = None
+
+if Lib:
+def xtxt_docx(file_buffer) -> str:
+    try:
+        # Copia del buffer per poterlo riutilizzare
+        file_buffer.seek(0)
+        data = file_buffer.read()
+        buffer_copy = io.BytesIO(data)
+
+        if not zipfile.is_zipfile(buffer_copy):
+            print("⚠️ Invalid DOCX (not a ZIP file)")
+            return ""
+
+        buffer_copy.seek(0)
+        doc = Document(buffer_copy)
+
+        text = "\n".join(p.text for p in doc.paragraphs)
+        return text
+
+    except Exception as e:
+        print(f"⚠️  Error during extraction DOCX: {e}")
+        return ""
+
+register_extractor(
+    "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+    xtxt_docx,
+    name="DOCX"
+)

pyxtxt-0.0.1/src/pyxtxt/estrattori/html.py

@@ -0,0 +1,15 @@
+from . import register_extractor
+try:
+    from bs4 import BeautifulSoup
+except ImportError:
+    BeautifulSoup = None
+
+if BeautifulSoup:
+def xtxt_html(file_buffer):
+    soup = BeautifulSoup(file_buffer.read(), "html.parser")
+    return soup.get_text(separator="\n")
+register_extractor(
+    "text/html",
+    xtxt_html,
+    name="HTML"
+)

pyxtxt-0.0.1/src/pyxtxt/estrattori/odt.py

@@ -0,0 +1,27 @@
+from . import register_extractor
+try:
+    from odf.opendocument import load
+    from odf.text import P
+except ImportError:
+    Lib = None
+
+if Lib:
+def xtxt_odt(file_buffer):
+    odt_doc = load(file_buffer)
+    paragraphs = odt_doc.getElementsByType(P)
+    
+    testo = []
+    for p in paragraphs:
+        contenuto = []
+        for n in p.childNodes:
+            if n.nodeType == 3:  # TEXT_NODE
+                contenuto.append(n.data)
+        if contenuto:
+            testo.append("".join(contenuto))
+    
+    return "\n".join(testo)
+register_extractor(
+     "application/vnd.oasis.opendocument.text",
+     xtxt_odt,
+    name="ODT"
+)

pyxtxt-0.0.1/src/pyxtxt/estrattori/pdf.py

@@ -0,0 +1,32 @@
+from . import register_extractor
+try:
+    import fitz  # PyMuPDF
+except ImportError:
+    Lib = None
+
+if Lib:
+def xtxt_pdf(file_buffer):
+    try:
+        raw_data = file_buffer.read()
+        if not raw_data:
+            print("⚠️  PDF blank or not read correctly")
+            return None
+
+        doc = fitz.open(stream=raw_data, filetype="pdf")
+        return "\n".join(page.get_text() for page in doc)
+
+    except fitz.EmptyFileError:
+        print("⚠️ Error: PDF is blank or unreadable")
+        return None
+    except Exception as e:
+        print(f"⚠️  Error during PDF extraction: {e}")
+        return None
+
+
+
+
+register_extractor(
+    "application/pdf",
+    xtxt_pdf,
+    name="PDF"
+)

pyxtxt-0.0.1/src/pyxtxt/estrattori/pptx.py

@@ -0,0 +1,40 @@
+from . import register_extractor
+import io
+import zipfile
+try:
+    from pptx import Presentation
+except ImportError:
+    Lib = None
+
+if Lib:
+def xtxt_pptx(file_buffer) -> str:
+    try:
+        # Convertiamo il file_buffer (che è già un BytesIO o simile) in modo da poterlo riusare
+        file_buffer.seek(0)
+        data = file_buffer.read()
+        buffer_copy = io.BytesIO(data)
+
+        if not zipfile.is_zipfile(buffer_copy):
+            print("⚠️  Invalid PPTX (not a ZIP file)" )
+            return ""
+
+        # Se è un file zip valido, possiamo ripassare i dati a Presentation
+        buffer_copy.seek(0)
+        prs = Presentation(buffer_copy)
+
+        text = "\n".join(
+            shape.text
+            for slide in prs.slides
+            for shape in slide.shapes
+            if hasattr(shape, "text")
+        )
+        return text
+
+    except Exception as e:
+        print(f"⚠️ Error during PPTX extraction: {e}")
+        return ""
+register_extractor(
+    "application/vnd.openxmlformats-officedocument.presentationml.presentation" ,
+    xtxt_pptx,
+    name="PPTX"
+)

pyxtxt-0.0.1/src/pyxtxt/estrattori/svg.py

@@ -0,0 +1,23 @@
+from . import register_extractor
+try:
+    from lxml import etree
+except ImportError:
+    Lib = None
+
+if Lib:
+def xtxt_svg(file_buffer):
+     try:
+         tree = etree.parse(file_buffer)
+         root = tree.getroot()
+
+        # Estrai tutto il testo dai tag <text>
+         texts = [element.text for element in root.findall('.//{http://www.w3.org/2000/svg}text')]
+         return "\n".join(texts)
+     except Exception as e:
+         print(f"⚠️ Error while extracting SVG: {e}")
+         return ""
+register_extractor(
+     "image/svg+xml",
+     xtxt_svg,
+     name="SVG"
+ )