pyxtxt 0.2__tar.gz → 0.2.2__tar.gz

pyxtxt-0.2.2/MANIFEST.in

@@ -0,0 +1,3 @@
+include examples.py
+include README.md
+include LICENCSE

{pyxtxt-0.2/src/pyxtxt.egg-info → pyxtxt-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyxtxt
-Version: 0.2
+Version: 0.2.2
 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
@@ -65,7 +65,7 @@ Requires-Dist: lxml; extra == "all"
 **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 Office files, and more.
 
-**NEW in v0.1.24+**: Enhanced support for web content, byte streams, and requests integration!
+**NEW in v0.2.1+**: Enhanced support for web content, byte streams, and requests integration!
 
 ---
 
@@ -205,13 +205,28 @@ text = xtxt(attachment_bytes)
 
 ## 📖 Full Examples
 
-See [examples.py](https://github.com/dede-amdp/pyxtxt/blob/main/examples.py) for comprehensive usage examples including:
+See [examples.py](./examples.py) for comprehensive usage examples including:
 - Local file processing
 - Memory buffer handling  
 - Web content extraction
 - Error handling patterns
 - All supported formats demonstration
 
+### Accessing Examples After Installation
+After installing PyxTxt from PyPI, you can access the examples file:
+
+```python
+import pkg_resources
+
+# Get path to examples file
+examples_path = pkg_resources.resource_filename('pyxtxt', 'examples.py')
+print(f"Examples file location: {examples_path}")
+
+# Or read the content directly
+examples_content = pkg_resources.resource_string('pyxtxt', 'examples.py').decode('utf-8')
+print(examples_content)
+```
+
 ## 🔒 License
 
 Distributed under the MIT License. See LICENSE file for details.

{pyxtxt-0.2 → pyxtxt-0.2.2}/README.md

@@ -7,7 +7,7 @@
 **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 Office files, and more.
 
-**NEW in v0.1.24+**: Enhanced support for web content, byte streams, and requests integration!
+**NEW in v0.2.1+**: Enhanced support for web content, byte streams, and requests integration!
 
 ---
 
@@ -147,13 +147,28 @@ text = xtxt(attachment_bytes)
 
 ## 📖 Full Examples
 
-See [examples.py](https://github.com/dede-amdp/pyxtxt/blob/main/examples.py) for comprehensive usage examples including:
+See [examples.py](./examples.py) for comprehensive usage examples including:
 - Local file processing
 - Memory buffer handling  
 - Web content extraction
 - Error handling patterns
 - All supported formats demonstration
 
+### Accessing Examples After Installation
+After installing PyxTxt from PyPI, you can access the examples file:
+
+```python
+import pkg_resources
+
+# Get path to examples file
+examples_path = pkg_resources.resource_filename('pyxtxt', 'examples.py')
+print(f"Examples file location: {examples_path}")
+
+# Or read the content directly
+examples_content = pkg_resources.resource_string('pyxtxt', 'examples.py').decode('utf-8')
+print(examples_content)
+```
+
 ## 🔒 License
 
 Distributed under the MIT License. See LICENSE file for details.

pyxtxt-0.2.2/examples.py

@@ -0,0 +1,179 @@
+#!/usr/bin/env python3
+"""
+PyxTxt - Usage Examples
+=======================
+
+This file shows how to use the PyxTxt library to extract text
+from different file types and data streams.
+"""
+
+import io
+from pyxtxt import xtxt, extxt_available_formats, xtxt_from_url
+
+def example_basic():
+    """Example 1: Extraction from local file"""
+    print("=== EXAMPLE 1: Local file ====")
+    
+    # Extract text from a local PDF file
+    try:
+        text = xtxt("test.pdf")
+        if text:
+            print(f"Extracted text: {text[:100]}...")
+        else:
+            print("No text extracted or file not found")
+    except Exception as e:
+        print(f"Error: {e}")
+
+def example_buffer():
+    """Example 2: Extraction from memory buffer"""
+    print("\n=== EXAMPLE 2: Memory buffer ====")
+    
+    # Read file into memory and process
+    try:
+        with open("test.txt", "rb") as f:
+            buffer = io.BytesIO(f.read())
+            text = xtxt(buffer)
+            print(f"From buffer: {text}")
+    except FileNotFoundError:
+        print("File test.txt not found - creating example...")
+        # Create a sample text buffer
+        sample_text = "This is sample text for PyxTxt!"
+        buffer = io.BytesIO(sample_text.encode('utf-8'))
+        text = xtxt(buffer)
+        print(f"From sample buffer: {text}")
+
+def example_bytes():
+    """Example 3: Extraction from bytes object (NEW!)"""
+    print("\n=== EXAMPLE 3: Bytes object ====")
+    
+    # Simulate downloaded content
+    sample_content = b"This is sample text content downloaded from web"
+    text = xtxt(sample_content)
+    print(f"From bytes: {text}")
+    
+    # Example with simulated PDF content (won't work but shows usage)
+    try:
+        with open("test.pdf", "rb") as f:
+            pdf_bytes = f.read()
+            text = xtxt(pdf_bytes)
+            if text:
+                print(f"PDF from bytes: {text[:100]}...")
+    except FileNotFoundError:
+        print("File test.pdf not found for bytes example")
+
+def example_requests():
+    """Example 4: Extraction from requests.Response (NEW!)"""
+    print("\n=== EXAMPLE 4: requests.Response ====")
+    
+    try:
+        import requests
+        
+        # Download a text file
+        url = "https://raw.githubusercontent.com/python/cpython/main/README.rst"
+        response = requests.get(url)
+        
+        if response.status_code == 200:
+            # Method 1: Pass response object directly
+            text1 = xtxt(response)
+            if text1:
+                print(f"From Response object: {text1[:100]}...")
+            
+            # Method 2: Pass response.content (bytes)
+            text2 = xtxt(response.content) 
+            if text2:
+                print(f"From response.content: {text2[:100]}...")
+        
+    except ImportError:
+        print("requests not installed. Install with: pip install requests")
+    except Exception as e:
+        print(f"Download error: {e}")
+
+def example_url_helper():
+    """Example 5: URL helper function (NEW!)"""
+    print("\n=== EXAMPLE 5: xtxt_from_url helper ====")
+    
+    # Download directly from URL
+    url = "https://raw.githubusercontent.com/python/cpython/main/README.rst"
+    text = xtxt_from_url(url)
+    
+    if text:
+        print(f"Downloaded from URL: {text[:100]}...")
+    else:
+        print("Download or parsing error")
+    
+    # With additional parameters for requests
+    text_with_headers = xtxt_from_url(
+        url,
+        headers={'User-Agent': 'PyxTxt-Example/1.0'},
+        timeout=10
+    )
+    if text_with_headers:
+        print("Download with custom headers successful")
+
+def example_supported_formats():
+    """Example 6: Display supported formats"""
+    print("\n=== EXAMPLE 6: Supported formats ====")
+    
+    print("Supported MIME types:")
+    formats = extxt_available_formats()
+    for fmt in formats:
+        print(f"  - {fmt}")
+    
+    print("\nPretty format names:")
+    pretty_formats = extxt_available_formats(pretty=True)
+    for fmt in pretty_formats:
+        print(f"  - {fmt}")
+
+def example_web_use_cases():
+    """Example 7: Common use cases for web content"""
+    print("\n=== EXAMPLE 7: Web use cases =====")
+    
+    # Case 1: API that returns a document
+    try:
+        import requests
+        
+        # Simulate API call that returns PDF
+        print("Example API call...")
+        # api_response = requests.post("https://api.example.com/generate-pdf", 
+        #                            json={"type": "report"})
+        # text = xtxt(api_response.content)
+        
+        # Case 2: File download from form upload
+        print("Example file upload processing...")
+        # uploaded_file_content = request.files['document'].read()  # Flask example
+        # text = xtxt(uploaded_file_content)
+        
+        # Case 3: Email attachments processing
+        print("Example email attachment...")
+        # attachment_bytes = email_message.get_payload(decode=True)
+        # text = xtxt(attachment_bytes)
+        
+        print("See code comments for detailed examples")
+        
+    except ImportError:
+        print("requests not available - examples commented out")
+
+def main():
+    """Run all examples"""
+    print("PyxTxt - Usage Examples")
+    print("=" * 40)
+    
+    example_basic()
+    example_buffer() 
+    example_bytes()
+    example_requests()
+    example_url_helper()
+    example_supported_formats()
+    example_web_use_cases()
+    
+    print("\n" + "=" * 40)
+    print("Examples completed!")
+    print("\nNew features added:")
+    print("✅ bytes object support")
+    print("✅ requests.Response support")
+    print("✅ xtxt_from_url() helper function")
+    print("✅ Better error handling")
+    print("✅ Type hints")
+
+if __name__ == "__main__":
+    main()

{pyxtxt-0.2 → pyxtxt-0.2.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pyxtxt"
-version = "0.2"
+version = "0.2.2"
 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"
@@ -56,3 +56,9 @@ build-backend = "setuptools.build_meta"
 [tool.setuptools.packages.find]
 where = ["src"]
 
+[tool.setuptools]
+include-package-data = true
+
+[tool.setuptools.package-data]
+"*" = ["examples.py"]
+

{pyxtxt-0.2 → pyxtxt-0.2.2}/src/pyxtxt/estrattori/doc.py

@@ -10,15 +10,20 @@ def xtxt_doc(file_buffer):
         try:
             file_buffer.seek(0)
             data = file_buffer.read()
-            with tempfile.NamedTemporaryFile(suffix=".doc") as temp_file:
+            with tempfile.NamedTemporaryFile(suffix=".doc", delete=False) as temp_file:
                 temp_file.write(data)
                 temp_file.flush()
                 temp_path = temp_file.name
-            result = subprocess.run(["antiword", temp_path],capture_output=True,text=True)
-            if result.returncode != 0:
-                print(f"⚠️ antiword failed: {result.stderr}")
-                return None
-            return result.stdout.strip()
+            
+            try:
+                result = subprocess.run(["antiword", temp_path], capture_output=True, text=True)
+                if result.returncode != 0:
+                    print(f"⚠️ antiword failed: {result.stderr}")
+                    return None
+                return result.stdout.strip()
+            finally:
+                import os
+                os.unlink(temp_path)
         except Exception as e:
             print(f"⚠️ Error during extraction from DOC: {e}")
             return None

pyxtxt-0.2.2/src/pyxtxt/estrattori/eml.py

@@ -0,0 +1,44 @@
+from . import register_extractor
+
+try:
+    import email
+    from email import policy
+    from bs4 import BeautifulSoup
+except ImportError:
+    email = None
+
+if email:
+    def xtxt_eml(file_buffer):
+        content = file_buffer.read()
+        if isinstance(content, bytes):
+            msg = email.message_from_bytes(content, policy=policy.default)
+        else:
+            msg = email.message_from_string(content, policy=policy.default)
+
+        parts = []
+
+        if msg.is_multipart():
+            for part in msg.walk():
+                content_type = part.get_content_type()
+                if content_type == "text/plain":
+                    parts.append(part.get_content())
+                elif content_type == "text/html":
+                    html = part.get_content()
+                    soup = BeautifulSoup(html, "html.parser")
+                    parts.append(soup.get_text(separator="\n"))
+        else:
+            content_type = msg.get_content_type()
+            payload = msg.get_content()
+            if content_type == "text/html":
+                soup = BeautifulSoup(payload, "html.parser")
+                parts.append(soup.get_text(separator="\n"))
+            else:
+                parts.append(payload)
+
+        return "\n\n".join(part.strip() for part in parts if part)
+
+    register_extractor(
+        "message/rfc822",
+        xtxt_eml,
+        name="EML"
+    )

pyxtxt-0.2.2/src/pyxtxt/estrattori/epub.py

@@ -0,0 +1,28 @@
+from . import register_extractor
+
+try:
+    from ebooklib import epub
+    from bs4 import BeautifulSoup
+except ImportError:
+    epub = None
+
+if epub:
+    def xtxt_epub(file_buffer):
+        book = epub.read_epub(file_buffer)
+
+        testo = []
+
+        for item in book.get_items():
+            if item.get_type() == epub.ITEM_DOCUMENT:
+                soup = BeautifulSoup(item.get_body_content(), 'html.parser')
+                estratto = soup.get_text(separator='\n', strip=True)
+                if estratto:
+                    testo.append(estratto)
+
+        return "\n\n".join(testo)
+
+    register_extractor(
+        "application/epub+zip",
+        xtxt_epub,
+        name="EPUB"
+    )

pyxtxt-0.2.2/src/pyxtxt/estrattori/md.py

@@ -0,0 +1,27 @@
+from . import register_extractor
+
+try:
+    import markdown
+    from bs4 import BeautifulSoup
+except ImportError:
+    markdown = None
+
+if markdown:
+    def xtxt_md(file_buffer):
+        # Legge il file come testo
+        content = file_buffer.read()
+        if isinstance(content, bytes):
+            content = content.decode("utf-8", errors="ignore")
+
+        # Converte Markdown in HTML
+        html = markdown.markdown(content)
+
+        # Estrae il testo dall'HTML
+        soup = BeautifulSoup(html, "html.parser")
+        return soup.get_text(separator="\n")
+
+    register_extractor(
+        "text/markdown",
+        xtxt_md,
+        name="Markdown"
+    )

pyxtxt-0.2.2/src/pyxtxt/estrattori/msg.py

@@ -0,0 +1,41 @@
+from . import register_extractor
+import tempfile
+
+try:
+    import extract_msg
+    from bs4 import BeautifulSoup
+except ImportError:
+    extract_msg = None
+
+if extract_msg:
+    def xtxt_msg(file_buffer):
+        # Salva su file temporaneo perché extract_msg lavora su path
+        content = file_buffer.read()
+        
+        with tempfile.NamedTemporaryFile(suffix=".msg", delete=False) as tmp:
+            tmp.write(content)
+            tmp.flush()
+            
+            try:
+                msg = extract_msg.Message(tmp.name)
+                msg.extract()  # Decodifica i contenuti
+                
+                parts = []
+                
+                if msg.body:
+                    parts.append(msg.body)
+                
+                if msg.htmlBody:
+                    soup = BeautifulSoup(msg.htmlBody, "html.parser")
+                    parts.append(soup.get_text(separator="\n"))
+                
+                return "\n\n".join(part.strip() for part in parts if part)
+            finally:
+                import os
+                os.unlink(tmp.name)
+
+    register_extractor(
+        "application/vnd.ms-outlook",
+        xtxt_msg,
+        name="MSG"
+    )

pyxtxt-0.2.2/src/pyxtxt/estrattori/rtf.py

@@ -0,0 +1,20 @@
+from . import register_extractor
+
+try:
+    from striprtf.striprtf import rtf_to_text
+except ImportError:
+    rtf_to_text = None
+
+if rtf_to_text:
+    def xtxt_rtf(file_buffer):
+        content = file_buffer.read()
+        if isinstance(content, bytes):
+            content = content.decode("utf-8", errors="ignore")
+
+        return rtf_to_text(content)
+
+    register_extractor(
+        "application/rtf",
+        xtxt_rtf,
+        name="RTF"
+    )

pyxtxt-0.2.2/src/pyxtxt/estrattori/tex.py

@@ -0,0 +1,21 @@
+from . import register_extractor
+
+try:
+    from pylatexenc.latex2text import LatexNodes2Text
+except ImportError:
+    LatexNodes2Text = None
+
+if LatexNodes2Text:
+    def xtxt_tex(file_buffer):
+        content = file_buffer.read()
+        if isinstance(content, bytes):
+            content = content.decode("utf-8", errors="ignore")
+
+        text = LatexNodes2Text().latex_to_text(content)
+        return text.strip()
+
+    register_extractor(
+        "application/x-tex",
+        xtxt_tex,
+        name="LaTeX"
+    )

{pyxtxt-0.2 → pyxtxt-0.2.2/src/pyxtxt.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyxtxt
-Version: 0.2
+Version: 0.2.2
 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
@@ -65,7 +65,7 @@ Requires-Dist: lxml; extra == "all"
 **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 Office files, and more.
 
-**NEW in v0.1.24+**: Enhanced support for web content, byte streams, and requests integration!
+**NEW in v0.2.1+**: Enhanced support for web content, byte streams, and requests integration!
 
 ---
 
@@ -205,13 +205,28 @@ text = xtxt(attachment_bytes)
 
 ## 📖 Full Examples
 
-See [examples.py](https://github.com/dede-amdp/pyxtxt/blob/main/examples.py) for comprehensive usage examples including:
+See [examples.py](./examples.py) for comprehensive usage examples including:
 - Local file processing
 - Memory buffer handling  
 - Web content extraction
 - Error handling patterns
 - All supported formats demonstration
 
+### Accessing Examples After Installation
+After installing PyxTxt from PyPI, you can access the examples file:
+
+```python
+import pkg_resources
+
+# Get path to examples file
+examples_path = pkg_resources.resource_filename('pyxtxt', 'examples.py')
+print(f"Examples file location: {examples_path}")
+
+# Or read the content directly
+examples_content = pkg_resources.resource_string('pyxtxt', 'examples.py').decode('utf-8')
+print(examples_content)
+```
+
 ## 🔒 License
 
 Distributed under the MIT License. See LICENSE file for details.

{pyxtxt-0.2 → pyxtxt-0.2.2}/src/pyxtxt.egg-info/SOURCES.txt

@@ -1,5 +1,7 @@
 LICENCSE
+MANIFEST.in
 README.md
+examples.py
 pyproject.toml
 src/pyxtxt/__init__.py
 src/pyxtxt/core.py
@@ -12,11 +14,17 @@ src/pyxtxt.egg-info/top_level.txt
 src/pyxtxt/estrattori/__init__.py
 src/pyxtxt/estrattori/doc.py
 src/pyxtxt/estrattori/docx.py
+src/pyxtxt/estrattori/eml.py
+src/pyxtxt/estrattori/epub.py
 src/pyxtxt/estrattori/html.py
+src/pyxtxt/estrattori/md.py
+src/pyxtxt/estrattori/msg.py
 src/pyxtxt/estrattori/odt.py
 src/pyxtxt/estrattori/pdf.py
 src/pyxtxt/estrattori/pptx.py
+src/pyxtxt/estrattori/rtf.py
 src/pyxtxt/estrattori/svg.py
+src/pyxtxt/estrattori/tex.py
 src/pyxtxt/estrattori/txt.py
 src/pyxtxt/estrattori/xls.py
 src/pyxtxt/estrattori/xlsx.py