{ "info": { "author": "Ankush Shah, Yalei Du", "author_email": "yaleidu@163.com", "bugtrack_url": null, "classifiers": [ "Programming Language :: Python :: 2.7", "Programming Language :: Python :: 3.3", "Programming Language :: Python :: 3.4", "Programming Language :: Python :: 3.5" ], "description": "docxpy\n======\n\n|image0| |PyPI|\n\nThis project is forked from\n`ankushshah89/python-docx2txt `__.\nA new feature is added: extract the hyperlinks and its corresponding\ntexts.\n\nIt is a pure python-based utility to extract text from docx files. The\ncode is taken and adapted from\n`python-docx `__. It can\nhowever also extract **text** from header, footer and **hyperlinks**. It\ncan now also extract **images**.\n\nHow to install?\n---------------\n\n.. code:: bash\n\n pip install docxpy\n\nHow to run?\n-----------\n\na. From command line:\n\n.. code:: bash\n\n # extract text\n docx2txt file.docx\n # extract text and images\n docx2txt -i /tmp/img_dir file.docx\n\nb. From python:\n\n.. code:: python\n\n import docxpy\n\n file = 'file.docx'\n\n # extract text\n text = docxpy.process(file)\n\n # extract text and write images in /tmp/img_dir\n text = docxpy.process(file, \"/tmp/img_dir\")\n\n\n # if you want the hyperlinks\n doc = docxpy.DOCReader(file)\n doc.process() # process file\n hyperlinks = doc.data['links']\n\n.. |image0| image:: https://travis-ci.org/badbye/docxpy.svg?branch=master\n.. |PyPI| image:: https://img.shields.io/pypi/pyversions/scrapy-corenlp.svg?style=flat-square", "description_content_type": null, "docs_url": null, "download_url": "UNKNOWN", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/badbye/docxpy", "keywords": "python,docx,text,links,images,extract", "license": "UNKNOWN", "maintainer": null, "maintainer_email": null, "name": "docxpy", "package_url": "https://pypi.org/project/docxpy/", "platform": "UNKNOWN", "project_url": "https://pypi.org/project/docxpy/", "project_urls": { "Download": "UNKNOWN", "Homepage": "https://github.com/badbye/docxpy" }, "release_url": "https://pypi.org/project/docxpy/0.8.5/", "requires_dist": null, "requires_python": null, "summary": "A pure python-based utility to extract text, hyperlinks and imagesfrom docx files.", "version": "0.8.5" }, "last_serial": 2889870, "releases": { "0.1": [ { "comment_text": "", "digests": { "md5": "28d164e4c4a752d9ee832ff5dcd4bf47", "sha256": "98fe8607674372335d9a921ced4cc1b93379520191304bcc2fd21f559007a34b" }, "downloads": -1, "filename": "docxpy-0.1.tar.gz", "has_sig": false, "md5_digest": "28d164e4c4a752d9ee832ff5dcd4bf47", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 3338, "upload_time": "2017-03-05T15:09:34", "url": "https://files.pythonhosted.org/packages/e8/30/f988fcf2cbe114b5818d0c1618ff2ef98b5a93108e6007264cb5321b3d45/docxpy-0.1.tar.gz" } ], "0.7": [ { "comment_text": "", "digests": { "md5": "d8b55c09394e42156d92745238b80879", "sha256": "eb618ddf7b9d09ad040e444d669167facf0099b4621f3da2ee4cbd99fc0cc92b" }, "downloads": -1, "filename": "docxpy-0.7.tar.gz", "has_sig": false, "md5_digest": "d8b55c09394e42156d92745238b80879", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 3302, "upload_time": "2017-03-05T14:49:27", "url": "https://files.pythonhosted.org/packages/b6/db/fd3e42fc0a11e22d62ec3ac6cdf457a242f6847bbef4f63bb779e3e03185/docxpy-0.7.tar.gz" } ], "0.8": [ { "comment_text": "", "digests": { "md5": "93c17773016538d9805f27f2ca64920f", "sha256": "396d3de03e98642bd1aa228274cce5806558424886c0cee8a48aacc680438a08" }, "downloads": -1, "filename": "docxpy-0.8.tar.gz", "has_sig": false, "md5_digest": "93c17773016538d9805f27f2ca64920f", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 3331, "upload_time": "2017-03-05T15:15:54", "url": "https://files.pythonhosted.org/packages/b4/a9/98a532332421246ff7edcb25f20471771fdb81a11ba8fe2664a096049888/docxpy-0.8.tar.gz" } ], "0.8.1": [ { "comment_text": "", "digests": { "md5": "6b6384a0e48350642545069be6c4caaa", "sha256": "a52f28626e3161c74b73ad67a99b44bc8afb9cd851258e77cbf34833f46d2e8d" }, "downloads": -1, "filename": "docxpy-0.8.1.tar.gz", "has_sig": false, "md5_digest": "6b6384a0e48350642545069be6c4caaa", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 3890, "upload_time": "2017-03-07T06:55:56", "url": "https://files.pythonhosted.org/packages/f3/cc/74e1d889e6a324187b37daf0f9369d5ec6b59f68a82c38b427f9c31c04da/docxpy-0.8.1.tar.gz" } ], "0.8.2": [ { "comment_text": "", "digests": { "md5": "9200edcc9220384a7b5b52a436dd6e43", "sha256": "39222e9ffadec9873c7b93013cbcf4dff1aaea6cac611130484794e4dfb39a9e" }, "downloads": -1, "filename": "docxpy-0.8.2.tar.gz", "has_sig": false, "md5_digest": "9200edcc9220384a7b5b52a436dd6e43", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 3916, "upload_time": "2017-03-07T07:00:13", "url": "https://files.pythonhosted.org/packages/97/42/0f61f6f6e4641f02d5049fbf961b45c95e0929aead320b0ecc2c53ef7069/docxpy-0.8.2.tar.gz" } ], "0.8.3": [ { "comment_text": "", "digests": { "md5": "ae23688edbfe915aa1b5a002048c995d", "sha256": "c2baead3c7ccdb282c23234c3e8c284e5c3d9bfb97ad0a61d77827f512b2bafe" }, "downloads": -1, "filename": "docxpy-0.8.3.tar.gz", "has_sig": false, "md5_digest": "ae23688edbfe915aa1b5a002048c995d", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 3913, "upload_time": "2017-03-08T06:04:35", "url": "https://files.pythonhosted.org/packages/d7/4a/02e7ae45326f21c2f149896ca27d2e64fa328fa824915d8a0f30f96e0509/docxpy-0.8.3.tar.gz" } ], "0.8.4": [ { "comment_text": "", "digests": { "md5": "70dba792c460ef17cc65443aa8b72f01", "sha256": "e47e0dc16aca2e65b81d29657069585c709fec0721e08281572c0add7ecf3d09" }, "downloads": -1, "filename": "docxpy-0.8.4.tar.gz", "has_sig": false, "md5_digest": "70dba792c460ef17cc65443aa8b72f01", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 3913, "upload_time": "2017-03-08T06:06:57", "url": "https://files.pythonhosted.org/packages/51/5b/87f12e326ee8f48afc8a6f6c13053b9c7ed793cfccca74697227a2c828af/docxpy-0.8.4.tar.gz" } ], "0.8.5": [ { "comment_text": "", "digests": { "md5": "da1711806e41ee9410186f5eac99d43c", "sha256": "7949c5b8f6a1b749d1449f4590a3ddc6a3c16d62944b548df2efba52bad3d857" }, "downloads": -1, "filename": "docxpy-0.8.5.tar.gz", "has_sig": false, "md5_digest": "da1711806e41ee9410186f5eac99d43c", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4062, "upload_time": "2017-05-22T04:01:45", "url": "https://files.pythonhosted.org/packages/de/39/d3c28e3ef0637237356306d3e7916cf9d4deddc2c7517b16765b4bdb7b13/docxpy-0.8.5.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "da1711806e41ee9410186f5eac99d43c", "sha256": "7949c5b8f6a1b749d1449f4590a3ddc6a3c16d62944b548df2efba52bad3d857" }, "downloads": -1, "filename": "docxpy-0.8.5.tar.gz", "has_sig": false, "md5_digest": "da1711806e41ee9410186f5eac99d43c", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4062, "upload_time": "2017-05-22T04:01:45", "url": "https://files.pythonhosted.org/packages/de/39/d3c28e3ef0637237356306d3e7916cf9d4deddc2c7517b16765b4bdb7b13/docxpy-0.8.5.tar.gz" } ] }