{
    "info": {
        "author": "Phil Gooch and Kyle Cronan",
        "author_email": "philgooch@users.noreply.github.com",
        "bugtrack_url": null,
        "classifiers": [
            "License :: OSI Approved :: GNU General Public License (GPL)",
            "Natural Language :: English",
            "Operating System :: OS Independent",
            "Programming Language :: Python",
            "Topic :: Office/Business",
            "Topic :: Software Development :: Libraries",
            "Topic :: Text Processing"
        ],
        "description": "\n  This is a Python 3 module and command line utility that analyzes XML output from the\n    program `pdftohtml` in order to extract tables from PDF files and output the data as CSV.\n    \n    For example:\n    \n        pdftohtml -xml -stdout file.pdf | pdftable -f file%d.csv\n    \n    See also `pdftable -h` and http://sourceforge.net/projects/pdftable\n    \n    Original author: (c) 2009 Kyle Cronan <kyle@pbx.org>\n    \n    This Python 3 implementation: (c) 2017 Phil Gooch\n    \n    As per Kyle's code, this version is licensed under GPLv3. See LICENSE file.\n    \n    # Installation\n    \n    Install `pdftohtml` via `poppler-utils` (Linux) or `poppler` (Mac OSX)\n    \n    Then install the module\n    \n        python setup.py install\n        \n    or\n        pip install pdftablr\n        \n    ## Command line usage\n    \n        pdftohtml -xml -stdout file.pdf | pdftable -f file%d.csv\n        \n    ## Module usage\n        \n        from pdftablr.table_extractor import Extractor\n    \n        # XML file created from pdftohtml\n        input_path = '/path/to/file.xml'\n        \n        # Output CSV file\n        output_path = '/path/to/output.csv'\n        \n        with open(output_path, 'w') as output_file:\n            table_extractor = Extractor(output_file=output_file)\n        \n            with open(input_path) as f:\n                table_extractor.read_file(f)\n            \n            tables = table_extractor.extract()\n            for table in tables:\n                table.output(writer=None)\n    \n  ",
        "description_content_type": null,
        "docs_url": null,
        "download_url": "https://github.com/philgooch/pdftable/archive/v0.1.0.tar.gz",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/philgooch/pdftable",
        "keywords": "python3",
        "license": "GPLv3",
        "maintainer": "",
        "maintainer_email": "",
        "name": "pdftablr",
        "package_url": "https://pypi.org/project/pdftablr/",
        "platform": "",
        "project_url": "https://pypi.org/project/pdftablr/",
        "project_urls": {
            "Download": "https://github.com/philgooch/pdftable/archive/v0.1.0.tar.gz",
            "Homepage": "https://github.com/philgooch/pdftable"
        },
        "release_url": "https://pypi.org/project/pdftablr/0.1.0/",
        "requires_dist": null,
        "requires_python": "",
        "summary": "Python3 implementation of Kyle Cronan's pdftable module, with unit tests",
        "version": "0.1.0"
    },
    "last_serial": 3296579,
    "releases": {
        "0.1.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "cd004355619ecbf2883360170ad71dfe",
                    "sha256": "485c4ce1df97176231ff6269eaaab3c1c58f578b5cea395c645ebb4f5e662a1f"
                },
                "downloads": -1,
                "filename": "pdftablr-0.1.0.tar.gz",
                "has_sig": false,
                "md5_digest": "cd004355619ecbf2883360170ad71dfe",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7356,
                "upload_time": "2017-11-01T09:29:13",
                "url": "https://files.pythonhosted.org/packages/2f/b6/e9c613e989f7e95d21e83d988fd27141e52460b1d973a4f6a74051d0af5a/pdftablr-0.1.0.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "cd004355619ecbf2883360170ad71dfe",
                "sha256": "485c4ce1df97176231ff6269eaaab3c1c58f578b5cea395c645ebb4f5e662a1f"
            },
            "downloads": -1,
            "filename": "pdftablr-0.1.0.tar.gz",
            "has_sig": false,
            "md5_digest": "cd004355619ecbf2883360170ad71dfe",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 7356,
            "upload_time": "2017-11-01T09:29:13",
            "url": "https://files.pythonhosted.org/packages/2f/b6/e9c613e989f7e95d21e83d988fd27141e52460b1d973a4f6a74051d0af5a/pdftablr-0.1.0.tar.gz"
        }
    ]
}