{ "info": { "author": "Elad Kehat", "author_email": "eladkehat@gmail.com", "bugtrack_url": null, "classifiers": [ "Development Status :: 5 - Production/Stable", "Environment :: Console", "Intended Audience :: Developers", "Intended Audience :: Science/Research", "License :: OSI Approved :: MIT License", "Operating System :: OS Independent", "Programming Language :: Python :: 3.7", "Topic :: Text Processing" ], "description": "# yapdfminer (Yet Another PDFMiner fork)\n\nPDFMiner is a great Python tool that had apparently been abandoned by its original author\n[Yusuke Shinyama](https://github.com/euske) in 2016.\nEver since, it got forked and re-forked time and time again but never maintained for long.\n\n## Goals\n\nI created this fork in order to better service the requirements of my own project from PDF analysis:\n1. Apply multiple pull requests that languish on the original repository, that **solve some bugs** that I ran into.\n1. Target **Python 3.7**.\nThere will be no attempt to maintain backwards compatibility to older versions of Python.\n1. Generate a **smaller distribution package** (I'm running on AWS Lambda, where RAM is at a premium),\nat the cost of **dropping support for Chinese, Japanese and Korean** PDFs.\n\nIf you require Asian language support, it should be simple enough to re-enable it by building with the resource\nfiles in `cmaprsrc`.\n\nOther than the issues mentioned above, I do strive to make this library drop-in compatible with the original PDFMiner,\nincluding for example the package name (which pdfminer3 had changed).\n\n\n**Lineage:**\n- This is a fork of [gwk/pdfminer3](https://github.com/gwk/pdfminer3/).\n- gwk/pdfminer3 was forked from [pdfminer/pdfminer.six](https://github.com/pdfminer/pdfminer.six)\n- pdfminer.six was forked from the original [pdfminer](https://github.com/euske/pdfminer)\n\n\n## About\n\nPDFMiner is a pure Python tool for extracting information from PDF documents.\n\nIts focus is on PDF content retrieval and analysis.\n\nPlease refer to the original repo for more information: https://github.com/euske\n\n\n", "description_content_type": "text/markdown", "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/eladkehat/yapdfminer", "keywords": "pdf,pdf parser,pdf converter,layout analysis,text mining", "license": "MIT", "maintainer": "", "maintainer_email": "", "name": "yapdfminer", "package_url": "https://pypi.org/project/yapdfminer/", "platform": "", "project_url": "https://pypi.org/project/yapdfminer/", "project_urls": { "Homepage": "https://github.com/eladkehat/yapdfminer" }, "release_url": "https://pypi.org/project/yapdfminer/1.2.2/", "requires_dist": [ "chardet (~=3.0)", "Pillow (~=6.0)", "pycryptodome (~=3.8)", "sortedcontainers (~=2.1)" ], "requires_python": ">=3.7", "summary": "PDF parser and analyzer", "version": "1.2.2" }, "last_serial": 5649348, "releases": { "1.0.0": [ { "comment_text": "", "digests": { "md5": "63ece395707b7099e1805817b8499c12", "sha256": "a3fd3735c17ad5124ae2345ead95ecea2607747502cd1dcb74e983a45768217b" }, "downloads": -1, "filename": "yapdfminer-1.0.0-py3-none-any.whl", "has_sig": false, "md5_digest": "63ece395707b7099e1805817b8499c12", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.7", "size": 136402, "upload_time": "2019-05-03T08:54:01", "url": "https://files.pythonhosted.org/packages/55/a3/be55e93fb09c50eebd0202f134a126f12002050f904e7f6f5237498c6bef/yapdfminer-1.0.0-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "0b6047ece84c80a32b83adc1f8421fb5", "sha256": "a99d97837520815f08300feac03192d17fc4238ad124c5ebe1c43137370941ff" }, "downloads": -1, "filename": "yapdfminer-1.0.0.tar.gz", "has_sig": false, "md5_digest": "0b6047ece84c80a32b83adc1f8421fb5", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.7", "size": 121003, "upload_time": "2019-05-03T08:54:04", "url": "https://files.pythonhosted.org/packages/84/ef/87611e58f5636c5a9495a677a06e587dee84961b19be04adcffc69d670a6/yapdfminer-1.0.0.tar.gz" } ], "1.0.1": [ { "comment_text": "", "digests": { "md5": "786acbaa70d7a5220801216ab08f14b3", "sha256": "09ebda1ef10f166484af938f8d96acdf294792457ceed17466be71b1eefe3923" }, "downloads": -1, "filename": "yapdfminer-1.0.1-py3-none-any.whl", "has_sig": false, "md5_digest": "786acbaa70d7a5220801216ab08f14b3", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.7", "size": 136398, "upload_time": "2019-05-04T20:28:30", "url": "https://files.pythonhosted.org/packages/b9/39/9a96b425d3fbbd325292b5912f70ba977a61fbe114d45af4df0177779516/yapdfminer-1.0.1-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "3b10caf7543c4222bef9cbbdc9c0392d", "sha256": "ef7f8bd6234132e03826d25a284cd6b670fdf9ba8099352c7b967225c522b947" }, "downloads": -1, "filename": "yapdfminer-1.0.1.tar.gz", "has_sig": false, "md5_digest": "3b10caf7543c4222bef9cbbdc9c0392d", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.7", "size": 121000, "upload_time": "2019-05-04T20:28:32", "url": "https://files.pythonhosted.org/packages/c6/b1/0b7dee6e8c2711a8b7b6763413af3672b23b5939b687d09a744109576e96/yapdfminer-1.0.1.tar.gz" } ], "1.1.0": [ { "comment_text": "", "digests": { "md5": "4a6fae6b049b356af920466065328bad", "sha256": "e346ad80d6430ff8de15df4708e12c4451787c24feee58762af30d4deb2550ef" }, "downloads": -1, "filename": "yapdfminer-1.1.0-py3-none-any.whl", "has_sig": false, "md5_digest": "4a6fae6b049b356af920466065328bad", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.7", "size": 139143, "upload_time": "2019-05-04T21:02:40", "url": "https://files.pythonhosted.org/packages/06/d1/bef979e9bdd868cba2059593c0fa96a3b732c141355ab74e69edd978c4c3/yapdfminer-1.1.0-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "6b0ccda95b479e6cf7f8012ca3fc7c74", "sha256": "2d84daa9c3f51709e335304ca02eeed6607ae84b948d2ba7f3f91ff55ccb0cfc" }, "downloads": -1, "filename": "yapdfminer-1.1.0.tar.gz", "has_sig": false, "md5_digest": "6b0ccda95b479e6cf7f8012ca3fc7c74", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.7", "size": 123574, "upload_time": "2019-05-04T21:02:43", "url": "https://files.pythonhosted.org/packages/9f/33/1e86642f1871b8db9e7a2c67275434e516873cb8b9cbebb69f5973a948f8/yapdfminer-1.1.0.tar.gz" } ], "1.1.1": [ { "comment_text": "", "digests": { "md5": "75d1e0db62eb535a3620ba3d3da94af0", "sha256": "821a98bb6d86af4721bee3b3c79424145537f5f585843103709ee5eab051973b" }, "downloads": -1, "filename": "yapdfminer-1.1.1-py3-none-any.whl", "has_sig": false, "md5_digest": "75d1e0db62eb535a3620ba3d3da94af0", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.7", "size": 139138, "upload_time": "2019-05-05T08:27:41", "url": "https://files.pythonhosted.org/packages/15/20/d7af141d5b5403b7ce05d88a8748c1b2befa66833c20aee23028473cdd15/yapdfminer-1.1.1-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "41e094353ce6120b376c325b0f9ec74e", "sha256": "9d99bacb88f70cc4ca68df529524f01386ff7749a6af28e40e72687c815807fc" }, "downloads": -1, "filename": "yapdfminer-1.1.1.tar.gz", "has_sig": false, "md5_digest": "41e094353ce6120b376c325b0f9ec74e", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.7", "size": 123577, "upload_time": "2019-05-05T08:27:44", "url": "https://files.pythonhosted.org/packages/5e/21/182855ee8f0370c875484c48f18076574f132031650fa8a9d609189f57bf/yapdfminer-1.1.1.tar.gz" } ], "1.1.3": [ { "comment_text": "", "digests": { "md5": "da203ccccee375f1ac5c6a6ab9815d51", "sha256": "a02ede9e78c5b82a017bbde798aeba44b5f15b69a53a7743bb31372a26de10a1" }, "downloads": -1, "filename": "yapdfminer-1.1.3-py3-none-any.whl", "has_sig": false, "md5_digest": "da203ccccee375f1ac5c6a6ab9815d51", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.7", "size": 139152, "upload_time": "2019-05-19T11:36:27", "url": "https://files.pythonhosted.org/packages/7b/12/9e02bb91880ae49dd941ff8e360dfbce86be053fd16eff4bbebe57f1dedb/yapdfminer-1.1.3-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "602fc3af5e702bf16be112e268abd1e9", "sha256": "1be7bd69fd166fce5c7694f994f012265d74da1155775a42dbe84c1e3aef96e5" }, "downloads": -1, "filename": "yapdfminer-1.1.3.tar.gz", "has_sig": false, "md5_digest": "602fc3af5e702bf16be112e268abd1e9", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.7", "size": 123598, "upload_time": "2019-05-19T11:36:30", "url": "https://files.pythonhosted.org/packages/e4/d3/54c0443f916c91a2c96cce2bb3414472e801f1eb32751b65485cf72b31a3/yapdfminer-1.1.3.tar.gz" } ], "1.2.0": [ { "comment_text": "", "digests": { "md5": "c1a7fda3349ff3befc318c2880e6baa4", "sha256": "f8845bdcf425877cf76e0c49e13818afb1c9495e6feb805a7122bab6a8f9b88b" }, "downloads": -1, "filename": "yapdfminer-1.2.0-py3-none-any.whl", "has_sig": false, "md5_digest": "c1a7fda3349ff3befc318c2880e6baa4", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.7", "size": 139164, "upload_time": "2019-05-19T12:36:51", "url": "https://files.pythonhosted.org/packages/10/ad/8b4f167de00442b9483d29ed8010a870d82d472f9cf4542a5c05327c771a/yapdfminer-1.2.0-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "68429968e72c46b0f36acfd8e719d0b7", "sha256": "ef0695ee2dcdacb41dfe35d0ac082d79f21d5b08a71c9721e2630b141d9b2e1b" }, "downloads": -1, "filename": "yapdfminer-1.2.0.tar.gz", "has_sig": false, "md5_digest": "68429968e72c46b0f36acfd8e719d0b7", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.7", "size": 123614, "upload_time": "2019-05-19T12:36:53", "url": "https://files.pythonhosted.org/packages/a2/06/5367a99536a49521d73870b5239d22a75df67501d102ab0ce35a93bc497d/yapdfminer-1.2.0.tar.gz" } ], "1.2.1": [ { "comment_text": "", "digests": { "md5": "9a54d87033a81d06338e5a0ae0b00695", "sha256": "cf74b3f275942ac73793ec7ec8d7e4d74d9c0b40e736ba37f634574d6bcae57a" }, "downloads": -1, "filename": "yapdfminer-1.2.1-py3-none-any.whl", "has_sig": false, "md5_digest": "9a54d87033a81d06338e5a0ae0b00695", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.7", "size": 139182, "upload_time": "2019-08-08T08:23:45", "url": "https://files.pythonhosted.org/packages/a4/d5/a13de9da541517423e27d9f0091c041a848e6739f08d96d0d4d698fc009e/yapdfminer-1.2.1-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "2c3a201cd65e8ca693dab7859e88095d", "sha256": "a55ad84a17ca8d60f6fb4b919adec9f0d2d573ce7208f24a66379daf7912aa54" }, "downloads": -1, "filename": "yapdfminer-1.2.1.tar.gz", "has_sig": false, "md5_digest": "2c3a201cd65e8ca693dab7859e88095d", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.7", "size": 123662, "upload_time": "2019-08-08T08:23:48", "url": "https://files.pythonhosted.org/packages/66/d5/15b08d5dd30c9559effb3fa01a1c38144853cd059206b9a671f192b7934c/yapdfminer-1.2.1.tar.gz" } ], "1.2.2": [ { "comment_text": "", "digests": { "md5": "cac2022a066afba55f91423fa9489e11", "sha256": "2398504813aee4a5e3c645741726038912e4cb0f74a0a552a6ac4717d174076a" }, "downloads": -1, "filename": "yapdfminer-1.2.2-py3-none-any.whl", "has_sig": false, "md5_digest": "cac2022a066afba55f91423fa9489e11", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.7", "size": 139189, "upload_time": "2019-08-08T10:13:19", "url": "https://files.pythonhosted.org/packages/08/c4/bb77287fb10f4485d4c0c426fc9b63e3c26c4e6b6cde3f97a9d9022526c3/yapdfminer-1.2.2-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "dae755eba000f27d81ac13fc9e1fd53e", "sha256": "d92d023a7af1df2a03c729fb6c0c3abde6020a4c57ff2a47eaa2f5f0e1e96cad" }, "downloads": -1, "filename": "yapdfminer-1.2.2.tar.gz", "has_sig": false, "md5_digest": "dae755eba000f27d81ac13fc9e1fd53e", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.7", "size": 123669, "upload_time": "2019-08-08T10:13:22", "url": "https://files.pythonhosted.org/packages/6b/da/02fc886c16fdd8f841fecd7c889d4eea30824e03ab0e406f8d3fb6079c48/yapdfminer-1.2.2.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "cac2022a066afba55f91423fa9489e11", "sha256": "2398504813aee4a5e3c645741726038912e4cb0f74a0a552a6ac4717d174076a" }, "downloads": -1, "filename": "yapdfminer-1.2.2-py3-none-any.whl", "has_sig": false, "md5_digest": "cac2022a066afba55f91423fa9489e11", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.7", "size": 139189, "upload_time": "2019-08-08T10:13:19", "url": "https://files.pythonhosted.org/packages/08/c4/bb77287fb10f4485d4c0c426fc9b63e3c26c4e6b6cde3f97a9d9022526c3/yapdfminer-1.2.2-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "dae755eba000f27d81ac13fc9e1fd53e", "sha256": "d92d023a7af1df2a03c729fb6c0c3abde6020a4c57ff2a47eaa2f5f0e1e96cad" }, "downloads": -1, "filename": "yapdfminer-1.2.2.tar.gz", "has_sig": false, "md5_digest": "dae755eba000f27d81ac13fc9e1fd53e", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.7", "size": 123669, "upload_time": "2019-08-08T10:13:22", "url": "https://files.pythonhosted.org/packages/6b/da/02fc886c16fdd8f841fecd7c889d4eea30824e03ab0e406f8d3fb6079c48/yapdfminer-1.2.2.tar.gz" } ] }