{ "info": { "author": "Mikhail Korobov, Terry Peng", "author_email": "kmike84@gmail.com, pengtaoo@gmail.com", "bugtrack_url": null, "classifiers": [ "Development Status :: 3 - Alpha", "Intended Audience :: Developers", "Intended Audience :: Science/Research", "License :: OSI Approved :: MIT License", "Programming Language :: Python :: 2", "Programming Language :: Python :: 2.7", "Programming Language :: Python :: 3", "Programming Language :: Python :: 3.4", "Programming Language :: Python :: 3.5", "Programming Language :: Python :: 3.6", "Topic :: Scientific/Engineering :: Information Analysis", "Topic :: Software Development :: Libraries :: Python Modules", "Topic :: Text Processing :: Linguistic" ], "description": "Webstruct\n=========\n\n.. image:: https://img.shields.io/pypi/v/webstruct.svg\n :target: https://pypi.python.org/pypi/webstruct\n :alt: PyPI Version\n\n.. image:: https://travis-ci.org/scrapinghub/webstruct.svg?branch=master\n :target: https://travis-ci.org/scrapinghub/webstruct\n :alt: Build Status\n\n.. image:: https://codecov.io/gh/scrapinghub/webstruct/branch/master/graph/badge.svg\n :target: https://codecov.io/gh/scrapinghub/webstruct\n :alt: Code Coverage\n\n.. image:: https://readthedocs.org/projects/webstruct/badge/?version=latest\n :target: http://webstruct.readthedocs.io/en/latest/\n :alt: Documentation\n\n\nWebstruct is a library for creating statistical NER_ systems that work\non HTML data, i.e. a library for building tools that extract named\nentities (addresses, organization names, open hours, etc) from webpages.\n\nUnlike most NER systems, webstruct works on HTML data, not only\non text data. This allows to define features that use HTML structure,\nand also to embed annotation results back into HTML.\n\nRead the docs_ for more info.\n\nLicense is MIT.\n\n.. _docs: http://webstruct.readthedocs.io/en/latest/\n.. _NER: http://en.wikipedia.org/wiki/Named-entity_recognition\n\nContributing\n------------\n\n* Source code: https://github.com/scrapinghub/webstruct\n* Bug tracker: https://github.com/scrapinghub/webstruct/issues\n\nTo run tests, make sure tox_ is installed, then run\n``tox`` from the source root.\n\n.. _tox: https://tox.readthedocs.io/en/latest/\n", "description_content_type": null, "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/scrapinghub/webstruct", "keywords": "", "license": "MIT", "maintainer": "", "maintainer_email": "", "name": "webstruct", "package_url": "https://pypi.org/project/webstruct/", "platform": "", "project_url": "https://pypi.org/project/webstruct/", "project_urls": { "Homepage": "https://github.com/scrapinghub/webstruct" }, "release_url": "https://pypi.org/project/webstruct/0.6/", "requires_dist": null, "requires_python": "", "summary": "A library for creating statistical NER systems that work on HTML data", "version": "0.6" }, "last_serial": 4308984, "releases": { "0.2": [ { "comment_text": "", "digests": { "md5": "8ae6e94a3f4c4bbc518a1f3bf0171cad", "sha256": "52c568b3e2460538c7ea5f6339c231398b4e6e891e1277b6bc2e993c519c2bd9" }, "downloads": -1, "filename": "webstruct-0.2.tar.gz", "has_sig": false, "md5_digest": "8ae6e94a3f4c4bbc518a1f3bf0171cad", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 32220, "upload_time": "2014-04-21T22:27:20", "url": "https://files.pythonhosted.org/packages/01/b8/a300513adfaf62abd8223299a59e057d34202725d660e8d798dae2ce5507/webstruct-0.2.tar.gz" } ], "0.3": [ { "comment_text": "", "digests": { "md5": "125cf23eff305384422eddb39b60f088", "sha256": "89a3be6e8d4fb689310c1605e492a70e6f730140be984972e9ef923e7280fc48" }, "downloads": -1, "filename": "webstruct-0.3-py3-none-any.whl", "has_sig": false, "md5_digest": "125cf23eff305384422eddb39b60f088", "packagetype": "bdist_wheel", "python_version": "3.5", "requires_python": null, "size": 51824, "upload_time": "2016-09-19T12:51:57", "url": "https://files.pythonhosted.org/packages/e0/ad/d186214161c1a08a520f3d3efb95b4cf8494bd414dde5ae17d8e61e7a9cf/webstruct-0.3-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "0f384ee6c807347cd9761ff22094fd3e", "sha256": "1a9e06726891d041d662e352a45d0c4e23dc01105ce659bb3b48674c8300e8d4" }, "downloads": -1, "filename": "webstruct-0.3.tar.gz", "has_sig": false, "md5_digest": "0f384ee6c807347cd9761ff22094fd3e", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 40292, "upload_time": "2016-09-19T12:51:47", "url": "https://files.pythonhosted.org/packages/af/b2/b4d7bd1931795c1f10889d39f262e63ca6d422382584a3bb516a69ecc90d/webstruct-0.3.tar.gz" } ], "0.4": [ { "comment_text": "", "digests": { "md5": "cccabd16548c9267b093cd6a8efe0188", "sha256": "c89500610065d1678d1354ed65637cb37227d252eead9f599e766223198b6059" }, "downloads": -1, "filename": "webstruct-0.4-py2.py3-none-any.whl", "has_sig": false, "md5_digest": "cccabd16548c9267b093cd6a8efe0188", "packagetype": "bdist_wheel", "python_version": "3.5", "requires_python": null, "size": 53829, "upload_time": "2016-11-26T00:46:01", "url": "https://files.pythonhosted.org/packages/6b/77/4ef388c00694b9058c8a785edbe2f50d22061addff07d3339250dd980f42/webstruct-0.4-py2.py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "d31d9f300c1971631379694709df0869", "sha256": "2d30a186710a15917b202f7fe1f17c5807f99a091b359bf08bd59e30585340a8" }, "downloads": -1, "filename": "webstruct-0.4.tar.gz", "has_sig": false, "md5_digest": "d31d9f300c1971631379694709df0869", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 40426, "upload_time": "2016-11-26T00:45:52", "url": "https://files.pythonhosted.org/packages/10/22/6fdee7381077cd42b43192b2d77152100855a86117c6d02b96aff7b6cdf9/webstruct-0.4.tar.gz" } ], "0.4.1": [ { "comment_text": "", "digests": { "md5": "29f99a62b2ada4e8fda6248810bf9cac", "sha256": "1fee1794794e82298b782050aeb90ef1482b47a1187fbdb07019cc0ac7cc6ce3" }, "downloads": -1, "filename": "webstruct-0.4.1-py2.py3-none-any.whl", "has_sig": false, "md5_digest": "29f99a62b2ada4e8fda6248810bf9cac", "packagetype": "bdist_wheel", "python_version": "3.5", "requires_python": null, "size": 53866, "upload_time": "2016-11-28T16:00:35", "url": "https://files.pythonhosted.org/packages/f3/2d/6523d8717fec4eca493b55b149123a7af4ec1b511da4cb2f63d133b44445/webstruct-0.4.1-py2.py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "d26c7ce9eaa134aff3bfe87f40a2f73d", "sha256": "af61c40f9d379530dc5b53832aea7dfde4711e15ead08c3bd6c2b1ad371d8863" }, "downloads": -1, "filename": "webstruct-0.4.1.tar.gz", "has_sig": false, "md5_digest": "d26c7ce9eaa134aff3bfe87f40a2f73d", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 40438, "upload_time": "2016-11-28T16:00:24", "url": "https://files.pythonhosted.org/packages/bd/c3/1e602693b6f6a1d8f2e753ebb718b548570b59f7b970f06170ef578c250d/webstruct-0.4.1.tar.gz" } ], "0.5": [ { "comment_text": "", "digests": { "md5": "43e2de233d994d83c7781ad92cd497d6", "sha256": "7513fd32e4ccca73b4074fc06bc8a0e2e5c1350212549ad2caa462be8db71669" }, "downloads": -1, "filename": "webstruct-0.5-py2.py3-none-any.whl", "has_sig": false, "md5_digest": "43e2de233d994d83c7781ad92cd497d6", "packagetype": "bdist_wheel", "python_version": "3.5", "requires_python": null, "size": 56413, "upload_time": "2017-05-10T13:07:22", "url": "https://files.pythonhosted.org/packages/7e/49/2a7f087df7a532e8cc620dc9276278349532353fa78a1c6b83794d1b43b7/webstruct-0.5-py2.py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "e3f36d3477b193666443b16c4de427be", "sha256": "bbf7abd484dc2beb9a19842aeb8cd1777cab7ce71afdbb974e6362a0b3b1b8f4" }, "downloads": -1, "filename": "webstruct-0.5.tar.gz", "has_sig": false, "md5_digest": "e3f36d3477b193666443b16c4de427be", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 42307, "upload_time": "2017-05-10T13:07:13", "url": "https://files.pythonhosted.org/packages/28/f8/9b046f1972415a6355c035f99a6410181d1e4fdc2bf478bfe2708bc39327/webstruct-0.5.tar.gz" } ], "0.6": [ { "comment_text": "", "digests": { "md5": "46f4f7b5da5d9129848b70d941da403c", "sha256": "b482e789bb39291e62b573c9a089ce06a2510f4f967695b5824252010bf4c332" }, "downloads": -1, "filename": "webstruct-0.6-py2.py3-none-any.whl", "has_sig": false, "md5_digest": "46f4f7b5da5d9129848b70d941da403c", "packagetype": "bdist_wheel", "python_version": "3.6", "requires_python": null, "size": 63046, "upload_time": "2017-12-29T17:39:54", "url": "https://files.pythonhosted.org/packages/e7/c4/b0c13f60b24013e4a560a27b23b4547191d0581c67a35d8c64bc57eb83cc/webstruct-0.6-py2.py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "96ebcf483c5dea21a0d2ed5a07679945", "sha256": "839443b4d22c2e3cca58545d3947b752132c640d5753580b5faa2e05374e79cd" }, "downloads": -1, "filename": "webstruct-0.6.tar.gz", "has_sig": false, "md5_digest": "96ebcf483c5dea21a0d2ed5a07679945", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 48307, "upload_time": "2017-12-29T17:39:43", "url": "https://files.pythonhosted.org/packages/42/33/6da21470f8eba9ea2858c394fd806af9f9d191d8f234df8de5d69c9b2f69/webstruct-0.6.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "46f4f7b5da5d9129848b70d941da403c", "sha256": "b482e789bb39291e62b573c9a089ce06a2510f4f967695b5824252010bf4c332" }, "downloads": -1, "filename": "webstruct-0.6-py2.py3-none-any.whl", "has_sig": false, "md5_digest": "46f4f7b5da5d9129848b70d941da403c", "packagetype": "bdist_wheel", "python_version": "3.6", "requires_python": null, "size": 63046, "upload_time": "2017-12-29T17:39:54", "url": "https://files.pythonhosted.org/packages/e7/c4/b0c13f60b24013e4a560a27b23b4547191d0581c67a35d8c64bc57eb83cc/webstruct-0.6-py2.py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "96ebcf483c5dea21a0d2ed5a07679945", "sha256": "839443b4d22c2e3cca58545d3947b752132c640d5753580b5faa2e05374e79cd" }, "downloads": -1, "filename": "webstruct-0.6.tar.gz", "has_sig": false, "md5_digest": "96ebcf483c5dea21a0d2ed5a07679945", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 48307, "upload_time": "2017-12-29T17:39:43", "url": "https://files.pythonhosted.org/packages/42/33/6da21470f8eba9ea2858c394fd806af9f9d191d8f234df8de5d69c9b2f69/webstruct-0.6.tar.gz" } ] }