{ "info": { "author": "Anand Chitipothu, Noufal Ibrahim, Ryan Chartier, Jan Pieter Bruins Slot, Almer S. Tigelaar, Willian Zhang", "author_email": "info@archive.org", "bugtrack_url": null, "classifiers": [ "Development Status :: 4 - Beta", "Environment :: Web Environment", "Intended Audience :: Developers", "License :: OSI Approved :: GNU General Public License v2 (GPLv2)", "Operating System :: OS Independent", "Programming Language :: Python" ], "description": "warc3-wet: Python3 library to work with WARC and WET files\n==============================================\n\nNote: This is a fork of the original (now dead) warc repository.\n\nWARC (Web ARChive) is a file format for storing web crawls.\n\nhttp://bibnum.bnf.fr/WARC/ \n\nThis `warc` library makes it very easy to work with WARC files.::\n\n import warc\n with warc.open(\"test.warc\") as f:\n for record in f:\n print(record['WARC-Target-URI'], record['Content-Length'])\n\nAnd WET files.::\n\n import warc\n with warc.open(\"test.warc.wet\") as f:\n for record in f:\n print(record['WARC-Target-URI'], record['Content-Length'])\n\nDocumentation\n-------------\n\nThe documentation of the warc library is available at http://warc.readthedocs.org/.\n\nApart from the install from pip, which will not work for this warc3 version, the\ninterface as described there is unchanged.\n\t\nLicense\n-------\n\nThis software is licensed under GPL v2. See LICENSE_ file for details.\n\n.. LICENSE: http://github.com/internetarchive/warc/blob/master/LICENSE\n\nAuthors\n-------\n\nOriginal Python2 Versions:\n\n* Anand Chitipothu\n* Noufal Ibrahim\n\nPython3 Port:\n\n* Ryan Chartier \n* Jan Pieter Bruins Slot\n* Almer S. Tigelaar\n\nModification\n* Willian Zhang\n\nChange Log\n-------\n0.2.3\nSupport seeking in WARC/WET\n\n0.2.2\nAllow WET parse\n\nolder...\nsee https://github.com/internetarchive/warc", "description_content_type": null, "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/Willian-Zhang/warc3", "keywords": "", "license": "GPLv2", "maintainer": "", "maintainer_email": "", "name": "warc3-wet", "package_url": "https://pypi.org/project/warc3-wet/", "platform": "any", "project_url": "https://pypi.org/project/warc3-wet/", "project_urls": { "Homepage": "https://github.com/Willian-Zhang/warc3" }, "release_url": "https://pypi.org/project/warc3-wet/0.2.3/", "requires_dist": null, "requires_python": "", "summary": "Python library to work with ARC and WARC files", "version": "0.2.3" }, "last_serial": 3282805, "releases": { "0.2.2": [ { "comment_text": "", "digests": { "md5": "110682f500cb38cd997283e8239ed4d2", "sha256": "79794cf170e691ca67fdd0a8ae4886ddff904c59694598597d5f70c1f35b97ac" }, "downloads": -1, "filename": "warc3_wet-0.2.2-py3-none-any.whl", "has_sig": false, "md5_digest": "110682f500cb38cd997283e8239ed4d2", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 13000, "upload_time": "2017-10-14T08:09:21", "url": "https://files.pythonhosted.org/packages/0a/39/7398d2e792bc91e6141035bfc74ab5244a3ef7f3ce3217a7c8fa444b1e56/warc3_wet-0.2.2-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "d6e8849041ebc3712c01cde3ac253acb", "sha256": "3b6e3c9fbd7eb1744e8a077b8c9e86a937782b2e388f2c22b84f26b704fb5b27" }, "downloads": -1, "filename": "warc3-wet-0.2.2.tar.gz", "has_sig": false, "md5_digest": "d6e8849041ebc3712c01cde3ac253acb", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 16921, "upload_time": "2017-10-14T08:09:22", "url": "https://files.pythonhosted.org/packages/2a/0d/ec9680f0d7fa3dcf970376d6b961d0d86d800096e011768a41ab46c3bd31/warc3-wet-0.2.2.tar.gz" } ], "0.2.3": [ { "comment_text": "", "digests": { "md5": "a7da4faf9e644d8a33536ebaf563f677", "sha256": "f47ec2826806db6fe640c18b299e05678d8346f2a9a574ce698c53e49ac5b456" }, "downloads": -1, "filename": "warc3_wet-0.2.3-py3-none-any.whl", "has_sig": false, "md5_digest": "a7da4faf9e644d8a33536ebaf563f677", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 13207, "upload_time": "2017-10-27T05:36:22", "url": "https://files.pythonhosted.org/packages/78/de/017a6bc2e3ba1ad912a08501f58414dd9e8503da1d6239aad548631777ad/warc3_wet-0.2.3-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "4bce95a13ff1f12dc53530344c763a2f", "sha256": "d43724f372edbbc7990b9c384a493fb60818c7c9ae629d8ec31c29cbbccd01b9" }, "downloads": -1, "filename": "warc3-wet-0.2.3.tar.gz", "has_sig": false, "md5_digest": "4bce95a13ff1f12dc53530344c763a2f", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 17169, "upload_time": "2017-10-27T05:34:08", "url": "https://files.pythonhosted.org/packages/6d/24/5abaafd7d653994ae7694d32ad41d9c6125c53992a4c631eeba8b88e0cda/warc3-wet-0.2.3.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "a7da4faf9e644d8a33536ebaf563f677", "sha256": "f47ec2826806db6fe640c18b299e05678d8346f2a9a574ce698c53e49ac5b456" }, "downloads": -1, "filename": "warc3_wet-0.2.3-py3-none-any.whl", "has_sig": false, "md5_digest": "a7da4faf9e644d8a33536ebaf563f677", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 13207, "upload_time": "2017-10-27T05:36:22", "url": "https://files.pythonhosted.org/packages/78/de/017a6bc2e3ba1ad912a08501f58414dd9e8503da1d6239aad548631777ad/warc3_wet-0.2.3-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "4bce95a13ff1f12dc53530344c763a2f", "sha256": "d43724f372edbbc7990b9c384a493fb60818c7c9ae629d8ec31c29cbbccd01b9" }, "downloads": -1, "filename": "warc3-wet-0.2.3.tar.gz", "has_sig": false, "md5_digest": "4bce95a13ff1f12dc53530344c763a2f", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 17169, "upload_time": "2017-10-27T05:34:08", "url": "https://files.pythonhosted.org/packages/6d/24/5abaafd7d653994ae7694d32ad41d9c6125c53992a4c631eeba8b88e0cda/warc3-wet-0.2.3.tar.gz" } ] }