Version 0.1

Author: Belval

README.md

@@ -1,2 +1,29 @@
 # pdf2image
-A python module that wraps the pdftoppm utility to convert PDF to PPM, JPEG, and PNG
+A python3 module that wraps the pdftoppm utility to convert PDF to the PIL image formatt
+
+## How to install
+
+` pip install pdf2image `
+
+Windows users will have to install (pdftoppm)[https://sourceforge.net/projects/poppler-win32/]
+
+Linux users will have pdftoppm pre-installed with the distro (Tested on Ubuntu and Archlinux)
+
+## How does it work?
+` from pdf2image import convert_from_path, convert_from_bytes `
+
+Then simply do:
+
+` images = convert_from_path('/home/kankroc/example.pdf') `
+
+OR
+
+` images = convert_from_bytes(open('/home/kankroc/example.pdf', 'rb').read()) `
+
+`images` will be a list of PIL Image representing each page of the PDF document.
+
+## Limitations / known issues
+
+- A relatively big PDF will use up all your memory and cause the process to be killed
+- pdftoppm errors are not handled
+- Not Python 2 compatible

pdf2image/__init__.py

@@ -0,0 +1,55 @@
+from subprocess import Popen, PIPE
+from PIL import Image
+from io import BytesIO
+
+def convert_from_path(pdf_path, save_path=None, dpi=200):
+    """
+        Description: Convert PDF to Image
+        Parameters:
+            pdf_path -> Path to the PDF that you want to convert
+            dpi -> Image quality in DPI (default 200)
+    """
+
+    proc = Popen(['pdftoppm', '-r', str(dpi), pdf_path, ], stdout=PIPE)
+
+    data, err = proc.communicate()
+
+    images = []
+    
+    index = 0
+
+    while(index < len(data)):
+        code, size, rgb, _ = tuple(data[index:index + 40].split(b'\n'))
+        size_x, size_y = tuple(size.split(b' '))
+        file_size = len(code) + len(size) + len(rgb) + 3 + int(size_x) * int(size_y) * 3
+        images.append(Image.open(BytesIO(data[index:index + file_size])))
+        index += file_size
+
+    return images
+
+def convert_from_bytes(pdf_file, save_path=None, dpi=200):
+    """
+        Description: Convert PDF to Image
+        Parameters:
+            pdf_file -> Bytes representing the PDF file
+            dpi -> Image quality in DPI
+    """
+
+    proc = Popen(['pdftoppm', '-r', str(dpi), ], stdout=PIPE, stdin=PIPE)
+
+    proc.stdin.write(pdf_file)
+
+    data, err = proc.communicate()
+
+    images = []
+    
+    index = 0
+
+    while(index < len(data)):
+        code, size, rgb, _ = tuple(data[index:index + 40].split(b'\n'))
+        size_x, size_y = tuple(size.split(b' '))
+        file_size = len(code) + len(size) + len(rgb) + 3 + int(size_x) * int(size_y) * 3
+        images.append(Image.open(BytesIO(data[index:index + file_size])))
+        index += file_size
+
+    return images

pdf2image/pdf2image.py

@@ -0,0 +1,2 @@
+[metadata]
+description-file = README.md

setup.cfg

@@ -0,0 +1,45 @@
+# Always prefer setuptools over distutils
+from setuptools import setup, find_packages
+# To use a consistent encoding
+from codecs import open
+from os import path
+
+here = path.abspath(path.dirname(__file__))
+
+setup(
+    name='pdf2image',
+
+    version='0.1.0',
+
+    description='A wrapper around the pdftoppm command line tool to convert pdf to a PIL Image list.',
+
+    url='https://github.com/Kankroc/pdf2image',
+
+    author='Edouard Belval',
+    author_email='[email protected]',
+
+    # Choose your license
+    license='MIT',
+
+    # See https://pypi.python.org/pypi?%3Aaction=list_classifiers
+    classifiers=[
+        #   3 - Alpha
+        #   4 - Beta
+        #   5 - Production/Stable
+        'Development Status :: 3 - Alpha',
+
+        'Intended Audience :: Developers',
+
+        'License :: OSI Approved :: MIT License',
+
+        'Programming Language :: Python :: 3',
+        'Programming Language :: Python :: 3.3',
+        'Programming Language :: Python :: 3.4',
+        'Programming Language :: Python :: 3.5',
+        'Programming Language :: Python :: 3.6',
+    ],
+
+    keywords='pdf image png jpeg jpg convert',
+
+    packages=find_packages(exclude=['contrib', 'docs', 'tests']),
+)