{ "info": { "author": "Yuri Baburov", "author_email": "burchik@gmail.com", "bugtrack_url": null, "classifiers": [ "Environment :: Web Environment", "Intended Audience :: Developers", "Operating System :: OS Independent", "Programming Language :: Python", "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", "Programming Language :: Python :: 3.7", "Topic :: Internet", "Topic :: Software Development :: Libraries :: Python Modules", "Topic :: Text Processing :: Indexing", "Topic :: Utilities" ], "description": ".. image:: https://travis-ci.org/buriy/python-readability.svg?branch=master\n :target: https://travis-ci.org/buriy/python-readability\n\n\npython-readability\n==================\n\nGiven a html document, it pulls out the main body text and cleans it up.\n\nThis is a python port of a ruby port of `arc90's readability\nproject `__.\n\nInstallation\n------------\n\nIt's easy using ``pip``, just run:\n\n::\n\n $ pip install readability-lxml\n\nUsage\n-----\n\n::\n\n >> import requests\n >> from readability import Document\n >>\n >> response = requests.get('http://example.com')\n >> doc = Document(response.text)\n >> doc.title()\n >> 'Example Domain'\n >> doc.summary()\n >> u'
\\n
\\n

Example Domain

\\n\n

This domain is established to be used for illustrative examples in documents. You may\n use this\\n domain in examples without prior coordination or asking for permission.

\n \\n

More information...

\\n
\n \\n\\n
'\n\nChange Log\n----------\n\n- 0.7.1 Support for Python 3.7 . Fixed a slowdown when processing documents with lots of spaces.\n- 0.7 Improved HTML5 tags handling. Fixed stripping unwanted HTML nodes (only first matching node was removed before).\n- 0.6 Finally a release which supports Python versions 2.6, 2.7, 3.3 - 3.6\n- 0.5 Preparing a release to support Python versions 2.6, 2.7, 3.3 and 3.4\n- 0.4 Added Videos loading and allowed more images per paragraph\n- 0.3 Added Document.encoding, positive\\_keywords and negative\\_keywords\n\nLicensing\n=========\n\nThis code is under `the Apache License\n2.0 `__ license.\n\nThanks to\n---------\n\n- Latest `readability.js `__\n- Ruby port by starrhorne and iterationlabs\n- `Python port `__ by gfxmonk\n- `Decruft effort ` to move to lxml\n- \"BR to P\" fix from readability.js which improves quality for smaller texts\n- Github users contributions.\n", "description_content_type": "", "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "http://github.com/buriy/python-readability", "keywords": "", "license": "Apache License 2.0", "maintainer": "", "maintainer_email": "", "name": "readability-lxml", "package_url": "https://pypi.org/project/readability-lxml/", "platform": "", "project_url": "https://pypi.org/project/readability-lxml/", "project_urls": { "Homepage": "http://github.com/buriy/python-readability" }, "release_url": "https://pypi.org/project/readability-lxml/0.7.1/", "requires_dist": null, "requires_python": "", "summary": "fast html to text parser (article readability tool) with python3 support", "version": "0.7.1" }, "last_serial": 5203897, "releases": { "0.2": [ { "comment_text": "", "digests": { "md5": "d0066b2c96f58aeb8b6253997f509e83", "sha256": "8c877972386031d4269342ba37d6940ae1de22a6f0bbe1e51c3f5820201aaf03" }, "downloads": -1, "filename": "readability-lxml-0.2.tar.gz", "has_sig": false, "md5_digest": "d0066b2c96f58aeb8b6253997f509e83", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 9285, "upload_time": "2011-06-30T07:29:02", "url": "https://files.pythonhosted.org/packages/fc/1c/bd9beed4126f27f463fe3479e76a328baf8a8938f39a943d08832fdea8e1/readability-lxml-0.2.tar.gz" } ], "0.2.1": [ { "comment_text": "", "digests": { "md5": "6be4137f67619fcf7e0e60b749688561", "sha256": "f36c00469b30bc0260c36fef267a65bf8ef37690b14cc2a4f30c923156b26a9e" }, "downloads": -1, "filename": "readability-lxml-0.2.1.zip", "has_sig": false, "md5_digest": "6be4137f67619fcf7e0e60b749688561", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 13515, "upload_time": "2011-07-01T19:24:36", "url": "https://files.pythonhosted.org/packages/ac/eb/f50632e2801176789380322d7cdce6a5c6b4c0bcc5b82dbba0acb275c0c7/readability-lxml-0.2.1.zip" } ], "0.2.2": [ { "comment_text": "", "digests": { "md5": "40a583ee57485c02b5feb0eb6f05fff2", "sha256": "41259a306fda066b2305fdb3573ef704b1527d96ee646039f37372aa90e63e0b" }, "downloads": -1, "filename": "readability-lxml-0.2.2.zip", "has_sig": false, "md5_digest": "40a583ee57485c02b5feb0eb6f05fff2", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 13602, "upload_time": "2011-07-26T08:44:22", "url": "https://files.pythonhosted.org/packages/06/3e/68426e5a09c72688f99642f852ca71c220129c0a93becc6f9588bbeb3b68/readability-lxml-0.2.2.zip" } ], "0.2.3": [ { "comment_text": "", "digests": { "md5": "0b5274f2aa00b8e85f03c487b2b7510a", "sha256": "f432cb4c717355e71c3bf56e6f4ca856a31eaee8881cbd583febc73e9e873b82" }, "downloads": -1, "filename": "readability-lxml-0.2.3.zip", "has_sig": false, "md5_digest": "0b5274f2aa00b8e85f03c487b2b7510a", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 13593, "upload_time": "2011-07-26T21:06:05", "url": "https://files.pythonhosted.org/packages/b4/48/fc3bcfceebe8cdea0243f2a6494b9d56692e769ee516cc72b01e9f819e32/readability-lxml-0.2.3.zip" } ], "0.2.5": [ { "comment_text": "", "digests": { "md5": "a7615ee319f26320ce2414b5bd414541", "sha256": "fa013226a4f2f01d160fe173200d4a1984d931f5d0a38c4868b9598d41a18beb" }, "downloads": -1, "filename": "readability-lxml-0.2.5.zip", "has_sig": false, "md5_digest": "a7615ee319f26320ce2414b5bd414541", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 15660, "upload_time": "2012-04-19T20:25:04", "url": "https://files.pythonhosted.org/packages/ba/fd/80f04050a06a46426402cd98ba5596831ef8c0e08ace714661e3def48e8e/readability-lxml-0.2.5.zip" } ], "0.2.6": [ { "comment_text": "", "digests": { "md5": "1c96df20299b2a295db5e01f5bc095a7", "sha256": "3553cbefbf919816e718256bfbe9a637f00d2765e97ac3dcf4871c25ff86621a" }, "downloads": -1, "filename": "readability-lxml-0.2.6.tar.gz", "has_sig": false, "md5_digest": "1c96df20299b2a295db5e01f5bc095a7", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 11522, "upload_time": "2012-06-21T17:04:38", "url": "https://files.pythonhosted.org/packages/ac/82/062f80a0a406c3e4d182e4d2462d5abf9725cb3914606151dad8709e7536/readability-lxml-0.2.6.tar.gz" } ], "0.2.6.1": [ { "comment_text": "", "digests": { "md5": "655c5856b34321064cc0bfd4ebe75165", "sha256": "ebc1b04bfa0c3e8fd20c4edf479b21725e6a5e7a35882c165c993b64486c9dcc" }, "downloads": -1, "filename": "readability-lxml-0.2.6.1.tar.gz", "has_sig": false, "md5_digest": "655c5856b34321064cc0bfd4ebe75165", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 11577, "upload_time": "2012-07-17T14:36:22", "url": "https://files.pythonhosted.org/packages/d6/d8/16b38b246777176e16812043d8cf11b2359239df8f4eb8f5d54ea1211cd6/readability-lxml-0.2.6.1.tar.gz" } ], "0.3": [ { "comment_text": "", "digests": { "md5": "eddfc596b9196cb8e4fa970dbb2f5e67", "sha256": "94eb1211a1beee5821bfbb7d78345a3b0dfdcf5c145216c82d3d10104c2ff23c" }, "downloads": -1, "filename": "readability_lxml-0.3-py2.7.egg", "has_sig": false, "md5_digest": "eddfc596b9196cb8e4fa970dbb2f5e67", "packagetype": "bdist_egg", "python_version": "2.7", "requires_python": null, "size": 25376, "upload_time": "2013-10-09T19:40:44", "url": "https://files.pythonhosted.org/packages/0e/a1/f2e871c2994c01ab357ea5eb7a123f2555466fd3968c90a4bda70c3a05c9/readability_lxml-0.3-py2.7.egg" }, { "comment_text": "", "digests": { "md5": "31eb639ea43f46e32f7a1a94f7377c6e", "sha256": "20dbbe0613092519b8a58b1c932f36fb154884053df80ed208ad9b67dae1d00f" }, "downloads": -1, "filename": "readability-lxml-0.3.tar.gz", "has_sig": false, "md5_digest": "31eb639ea43f46e32f7a1a94f7377c6e", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 12266, "upload_time": "2013-10-09T19:38:00", "url": "https://files.pythonhosted.org/packages/b7/c8/d80abc0f80a495a1f674ca091afe5fa0f414221afbf3967155f5604b7a34/readability-lxml-0.3.tar.gz" } ], "0.3.0.1": [ { "comment_text": "", "digests": { "md5": "f3f688654866608530ec71526f57779d", "sha256": "99ce6cf83e06ac8ec1382210ee48c5117bff0a8765ba59b2e3a1318a03dc42a8" }, "downloads": -1, "filename": "readability_lxml-0.3.0.1-py2.7.egg", "has_sig": false, "md5_digest": "f3f688654866608530ec71526f57779d", "packagetype": "bdist_egg", "python_version": "2.7", "requires_python": null, "size": 25250, "upload_time": "2013-10-09T19:58:45", "url": "https://files.pythonhosted.org/packages/0c/f0/43200a64a4e0fc1a8c4ecadcaad9b3ab211aa268aeca2b46b9e4af9660af/readability_lxml-0.3.0.1-py2.7.egg" }, { "comment_text": "", "digests": { "md5": "9961bd647804f4ec707e420d9907c446", "sha256": "83ec8c63bd17155083a5a3d3b5b012032eb0234bee5a91842ec13e15697a2bc8" }, "downloads": -1, "filename": "readability-lxml-0.3.0.1.tar.gz", "has_sig": false, "md5_digest": "9961bd647804f4ec707e420d9907c446", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 12210, "upload_time": "2013-10-09T19:58:41", "url": "https://files.pythonhosted.org/packages/09/df/a7e4f7744d5becf6b13dd6cfca768c6dcd5beae4d49d0fd452c921a1887f/readability-lxml-0.3.0.1.tar.gz" } ], "0.3.0.2": [ { "comment_text": "", "digests": { "md5": "9b46fff271f01a1901a24f9dbd0e9bbf", "sha256": "1e972a64879590e5520efb0e87f5e9d185991532692605e10797df29669f1060" }, "downloads": -1, "filename": "readability_lxml-0.3.0.2-py2.7.egg", "has_sig": false, "md5_digest": "9b46fff271f01a1901a24f9dbd0e9bbf", "packagetype": "bdist_egg", "python_version": "2.7", "requires_python": null, "size": 25251, "upload_time": "2013-10-10T06:49:04", "url": "https://files.pythonhosted.org/packages/3e/6b/f19f1ea29902c08085ad3e44709a2a39b653325f86543b8521b693801e00/readability_lxml-0.3.0.2-py2.7.egg" }, { "comment_text": "", "digests": { "md5": "197f1ed2460e36309a1a55aaf27fc252", "sha256": "955984fc8589502c5001f2c4f37340785a7aa06e346530295ccf8c01c7772b9d" }, "downloads": -1, "filename": "readability-lxml-0.3.0.2.tar.gz", "has_sig": false, "md5_digest": "197f1ed2460e36309a1a55aaf27fc252", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 12216, "upload_time": "2013-10-10T06:48:59", "url": "https://files.pythonhosted.org/packages/36/31/510be4fc63e48e7755c63198b3ffe0d9287b4fcb0e6ab093b83d7c654fc7/readability-lxml-0.3.0.2.tar.gz" } ], "0.3.0.3": [ { "comment_text": "", "digests": { "md5": "fc4d7f1c352466924588a4db5057bd8d", "sha256": "6f491bb285278e4beb2e2ae195540b6d91c6a0b76f09f27e2e85c8dbac68792d" }, "downloads": -1, "filename": "readability_lxml-0.3.0.3-py2.7.egg", "has_sig": false, "md5_digest": "fc4d7f1c352466924588a4db5057bd8d", "packagetype": "bdist_egg", "python_version": "2.7", "requires_python": null, "size": 25254, "upload_time": "2014-04-02T08:06:42", "url": "https://files.pythonhosted.org/packages/2b/ef/e9e8b872193e3419d84bed231620e730e8fbde6fca2593e4b9a64252a714/readability_lxml-0.3.0.3-py2.7.egg" }, { "comment_text": "", "digests": { "md5": "21b78d85ff036885dbad6a1d3c26e964", "sha256": "4e1402f4851294664980b8da98cb754962076884db8a5d2f904450455ac5da2a" }, "downloads": -1, "filename": "readability-lxml-0.3.0.3.tar.gz", "has_sig": false, "md5_digest": "21b78d85ff036885dbad6a1d3c26e964", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 12296, "upload_time": "2014-04-02T08:06:38", "url": "https://files.pythonhosted.org/packages/c8/4e/6d140a623fa2d4718cb139e855a6d820fcf2df8b6cfd278cb9c85e7fef19/readability-lxml-0.3.0.3.tar.gz" } ], "0.3.0.5": [ { "comment_text": "", "digests": { "md5": "2c42729bd9fb4b4b571b82cdcb818786", "sha256": "521cc8a17d76affc9fc4967d231227e37fad083c0c393b0ae6b65eb4b1442a0f" }, "downloads": -1, "filename": "readability-lxml-0.3.0.5.tar.gz", "has_sig": false, "md5_digest": "2c42729bd9fb4b4b571b82cdcb818786", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 12577, "upload_time": "2014-09-22T08:36:24", "url": "https://files.pythonhosted.org/packages/c7/28/193a891f7ff350d0bce6e070c2b483e329b5b8bc12afdd0d1cca89295fc5/readability-lxml-0.3.0.5.tar.gz" } ], "0.3.0.6": [ { "comment_text": "", "digests": { "md5": "b6e32514da82302707a7b8d03b30a9eb", "sha256": "2a8d26e81e4508ab173aae138e29f3aa552fa8ad4634e282bee643ef33e4c830" }, "downloads": -1, "filename": "readability-lxml-0.3.0.6.tar.gz", "has_sig": false, "md5_digest": "b6e32514da82302707a7b8d03b30a9eb", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 11736, "upload_time": "2015-03-16T16:44:46", "url": "https://files.pythonhosted.org/packages/47/01/6a216fa1eae199e78ad6ea353d78e1a0dd3a0853e7ddba84580524741392/readability-lxml-0.3.0.6.tar.gz" } ], "0.5": [ { "comment_text": "", "digests": { "md5": "ce5d47580de0dc0c4d3071e6f33ec1f6", "sha256": "3b537faca57054f240bb9cf3bd0964861e891d981d7b4d8086f81db040a146b8" }, "downloads": -1, "filename": "readability-lxml-0.5.tar.gz", "has_sig": false, "md5_digest": "ce5d47580de0dc0c4d3071e6f33ec1f6", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 12730, "upload_time": "2015-04-27T09:56:40", "url": "https://files.pythonhosted.org/packages/c1/45/bfd6167b5faa692459d9e8d7d893c640a6f7f7e0c40149098613d1596554/readability-lxml-0.5.tar.gz" } ], "0.5.1": [ { "comment_text": "", "digests": { "md5": "b476f2590eae47f4ebea411ac27ace68", "sha256": "039b0709534e9f168ba1ad5517849583805dc5ef8572942a109ac4e43b5730e6" }, "downloads": -1, "filename": "readability-lxml-0.5.1.tar.gz", "has_sig": false, "md5_digest": "b476f2590eae47f4ebea411ac27ace68", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 11879, "upload_time": "2015-05-06T08:34:35", "url": "https://files.pythonhosted.org/packages/c5/64/aa1b8f98112d1b12e270fa1292b9ecb650ff37134be700ed95edaad8ea78/readability-lxml-0.5.1.tar.gz" } ], "0.6.0.3": [ { "comment_text": "", "digests": { "md5": "f007f1613cf8314d91407bbf9206ba18", "sha256": "6c03052c2dfbfc931651a878f2a6f8b29a0e1efdb087fa87d0103dc7f367eb63" }, "downloads": -1, "filename": "readability-lxml-0.6.0.3.tar.gz", "has_sig": false, "md5_digest": "f007f1613cf8314d91407bbf9206ba18", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 13523, "upload_time": "2015-07-26T18:50:43", "url": "https://files.pythonhosted.org/packages/8a/98/70591d99461c6a61253933f29b1bd4a5096052f92b2a42284984133c68f6/readability-lxml-0.6.0.3.tar.gz" } ], "0.6.0.4": [ { "comment_text": "", "digests": { "md5": "34614d7b05224924d96f1fc8ad7e0f3e", "sha256": "cfb074e23dbc7ac75e96155780146105a2b3e778f4b43e39b800f44cea653a78" }, "downloads": -1, "filename": "readability-lxml-0.6.0.4.tar.gz", "has_sig": false, "md5_digest": "34614d7b05224924d96f1fc8ad7e0f3e", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 13697, "upload_time": "2015-07-27T04:07:55", "url": "https://files.pythonhosted.org/packages/d3/bd/8183adf6b3e6513555c2dd692fa3a3dcdf6f4b9baa2dbd3cea13e14f185e/readability-lxml-0.6.0.4.tar.gz" } ], "0.6.0.5": [ { "comment_text": "", "digests": { "md5": "f193b320e03dc4d27595588d633908fa", "sha256": "7531a0fa1adb72db3ee94cf919d92d87d9157fea677ba825c8bee227b5aa2423" }, "downloads": -1, "filename": "readability-lxml-0.6.0.5.tar.gz", "has_sig": false, "md5_digest": "f193b320e03dc4d27595588d633908fa", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 13737, "upload_time": "2015-07-27T06:01:26", "url": "https://files.pythonhosted.org/packages/be/aa/5932f336386621d59e95efa9c0c76dc20abc697d01da3b659a9d077e4f20/readability-lxml-0.6.0.5.tar.gz" } ], "0.6.1": [ { "comment_text": "", "digests": { "md5": "ba7bd3b90f2689472df0b10cc87ad5f2", "sha256": "bb7509960350d42c86bdb4a8cbacd462f16e4012dd809e2f867f7dc9c15f3ffe" }, "downloads": -1, "filename": "readability-lxml-0.6.1.tar.gz", "has_sig": false, "md5_digest": "ba7bd3b90f2689472df0b10cc87ad5f2", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 13741, "upload_time": "2015-08-26T10:15:42", "url": "https://files.pythonhosted.org/packages/06/d0/4f405b3f53f514ba6f70f6f992e47acb8c955f124f235703083b068fed8e/readability-lxml-0.6.1.tar.gz" } ], "0.6.2": [ { "comment_text": "", "digests": { "md5": "cb7d4cada8f90acf9e1db7d3b98a044d", "sha256": "ac3b88747bf4ee1093124a1e7370f345fb69e5673eb7e96f97c761427074e426" }, "downloads": -1, "filename": "readability-lxml-0.6.2.tar.gz", "has_sig": false, "md5_digest": "cb7d4cada8f90acf9e1db7d3b98a044d", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 13938, "upload_time": "2016-04-11T05:50:10", "url": "https://files.pythonhosted.org/packages/50/09/62b202b26787770d09ab86de2958a1515428ebb527740bcd5dd756c39ba3/readability-lxml-0.6.2.tar.gz" } ], "0.7": [ { "comment_text": "", "digests": { "md5": "a096ccc23a6af3e5570bd360c3e3d417", "sha256": "b6b30684e302802cdab490dc5093555bfebba663eb569814225939c6b0dead3f" }, "downloads": -1, "filename": "readability-lxml-0.7.tar.gz", "has_sig": false, "md5_digest": "a096ccc23a6af3e5570bd360c3e3d417", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 14811, "upload_time": "2018-05-07T13:09:46", "url": "https://files.pythonhosted.org/packages/b0/7c/807b783c1e7f9c2e3f86573f644771112813e9ee94c1d610811c7acc7562/readability-lxml-0.7.tar.gz" } ], "0.7.1": [ { "comment_text": "", "digests": { "md5": "d204b53ecf1f2d4d51ceabdf273030aa", "sha256": "87cb722e53a4a5749effe37fb1236abc52a856ce71113324d06b25d96b48147b" }, "downloads": -1, "filename": "readability-lxml-0.7.1.tar.gz", "has_sig": false, "md5_digest": "d204b53ecf1f2d4d51ceabdf273030aa", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 15705, "upload_time": "2019-04-29T16:09:50", "url": "https://files.pythonhosted.org/packages/af/a7/8ea52b2d3de4a95c3ed8255077618435546386e35af8969744c0fa82d0d6/readability-lxml-0.7.1.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "d204b53ecf1f2d4d51ceabdf273030aa", "sha256": "87cb722e53a4a5749effe37fb1236abc52a856ce71113324d06b25d96b48147b" }, "downloads": -1, "filename": "readability-lxml-0.7.1.tar.gz", "has_sig": false, "md5_digest": "d204b53ecf1f2d4d51ceabdf273030aa", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 15705, "upload_time": "2019-04-29T16:09:50", "url": "https://files.pythonhosted.org/packages/af/a7/8ea52b2d3de4a95c3ed8255077618435546386e35af8969744c0fa82d0d6/readability-lxml-0.7.1.tar.gz" } ] }