{
    "info": {
        "author": "Andrea Capitanelli",
        "author_email": "andrea.capitanelli@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha",
            "License :: OSI Approved :: MIT License",
            "Operating System :: POSIX :: Linux",
            "Programming Language :: Python :: 3",
            "Topic :: Office/Business :: News/Diary"
        ],
        "description": "\n# Newsman\n\nA tool for scraping news from web.\n\nThere is no AI here, just good old-fashioned if-else rules.\n\n# Usage\n\nBasic usage:\n\n```\nimport newsman\n\n# start reading\nsrc = 'https://www.bbc.com'\nnews = newsman.read(src)\n\n# show articles\nfor article in news:\n    print(f'Url: {article.url.url}')\n    print(f'Title: {article.title}')\n    print(f'Text: {article.text}')\n    print(f'Main image: {article.main_image}')\n```\n\nCustomizing configuration:\n\n```\nimport newsman\n\n# get configuration\nconfig = newsman.get_config()\n\n# add a proxy for connection\nconfig['proxies'] = proxies\n\n# update accepted/rejected domains\nconfig['accepted_domains'] = ['a-good-site.com', 'the-best-one.org']\nconfig['rejected_domains'] += ['bad.com', 'very.bad.biz']\n\n# override default values for web retrieval\nconfig['link_depth'] = 2            # crawling depth level\nconfig['scan_limit'] = 10           # max. number of scanned sites\n\n# set pipes\npipes = ['byte2html', 'html2text', 'text2title', 'html2image']\nnews = newsman.News(config, pipes)\n\nsrc = 'https://www.bbc.com'\npages = news(src)\n```\n\nProxy information is formatted according to [Requests format](https://requests.kennethreitz.org/en/master/user/advanced/#proxies).\n\n# Installation\n\n` pip install newsman `\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/acapitanelli/newsman",
        "keywords": "press articles text extraction",
        "license": "MIT",
        "maintainer": "Andrea Capitanelli",
        "maintainer_email": "andrea.capitanelli@gmail.com",
        "name": "newsman",
        "package_url": "https://pypi.org/project/newsman/",
        "platform": "",
        "project_url": "https://pypi.org/project/newsman/",
        "project_urls": {
            "Homepage": "https://github.com/acapitanelli/newsman"
        },
        "release_url": "https://pypi.org/project/newsman/1.1.0/",
        "requires_dist": [
            "chardet",
            "requests"
        ],
        "requires_python": ">=3.6.0",
        "summary": "A tool for web news scraping.",
        "version": "1.1.0",
        "yanked": false,
        "yanked_reason": null
    },
    "last_serial": 6129232,
    "releases": {
        "1.0.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "6241340d0b48635dee4658556daf900a",
                    "sha256": "7f7a754985c777a8481e6cf8aca999b4863f716432fa3e34f59ba6a0cf25299e"
                },
                "downloads": -1,
                "filename": "newsman-1.0.0-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "6241340d0b48635dee4658556daf900a",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": ">=3.6.0",
                "size": 20260,
                "upload_time": "2019-10-30T13:29:07",
                "upload_time_iso_8601": "2019-10-30T13:29:07.638836Z",
                "url": "https://files.pythonhosted.org/packages/68/77/da1a17a4a6c8b99ddfb877c17855026a7881716abe8cf636570a1901c4eb/newsman-1.0.0-py3-none-any.whl",
                "yanked": false,
                "yanked_reason": null
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "dd509637af983cdf325c8a409b2d8590",
                    "sha256": "3f93058dd9368730949c74d20144cdaa9bfb0604230cf5a33759a89a3f7aa639"
                },
                "downloads": -1,
                "filename": "newsman-1.0.0.tar.gz",
                "has_sig": false,
                "md5_digest": "dd509637af983cdf325c8a409b2d8590",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=3.6.0",
                "size": 13721,
                "upload_time": "2019-10-30T13:29:10",
                "upload_time_iso_8601": "2019-10-30T13:29:10.070923Z",
                "url": "https://files.pythonhosted.org/packages/10/c2/a2116523bbda2ab309ef4a6a62c68607345e79c74257bea1d565ab01a603/newsman-1.0.0.tar.gz",
                "yanked": false,
                "yanked_reason": null
            }
        ],
        "1.1.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "af8aa9e0b4d1049e7e37058c7b671711",
                    "sha256": "cbe1b49fefa255349926b9ee0854905799311309a8ea5227c5c9e98e9e985b0d"
                },
                "downloads": -1,
                "filename": "newsman-1.1.0-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "af8aa9e0b4d1049e7e37058c7b671711",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": ">=3.6.0",
                "size": 19719,
                "upload_time": "2019-11-13T10:51:10",
                "upload_time_iso_8601": "2019-11-13T10:51:10.477228Z",
                "url": "https://files.pythonhosted.org/packages/08/a4/35836b3fa9679d6776cea459eb9b7ab9f5a2c10e193f9baf009357b82b42/newsman-1.1.0-py3-none-any.whl",
                "yanked": false,
                "yanked_reason": null
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "40e1030f877cb6c7c1f30543d29650b6",
                    "sha256": "8829be60ae71d9045b276c5b88e73472e5f2b205c9968b8be5581ca6097baee4"
                },
                "downloads": -1,
                "filename": "newsman-1.1.0.tar.gz",
                "has_sig": false,
                "md5_digest": "40e1030f877cb6c7c1f30543d29650b6",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=3.6.0",
                "size": 13078,
                "upload_time": "2019-11-13T10:51:12",
                "upload_time_iso_8601": "2019-11-13T10:51:12.195741Z",
                "url": "https://files.pythonhosted.org/packages/89/ba/f5e57abc5d602528f268d72bd2e74dc8d6e4477beb3711a880ffe36c721b/newsman-1.1.0.tar.gz",
                "yanked": false,
                "yanked_reason": null
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "af8aa9e0b4d1049e7e37058c7b671711",
                "sha256": "cbe1b49fefa255349926b9ee0854905799311309a8ea5227c5c9e98e9e985b0d"
            },
            "downloads": -1,
            "filename": "newsman-1.1.0-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "af8aa9e0b4d1049e7e37058c7b671711",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.6.0",
            "size": 19719,
            "upload_time": "2019-11-13T10:51:10",
            "upload_time_iso_8601": "2019-11-13T10:51:10.477228Z",
            "url": "https://files.pythonhosted.org/packages/08/a4/35836b3fa9679d6776cea459eb9b7ab9f5a2c10e193f9baf009357b82b42/newsman-1.1.0-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "40e1030f877cb6c7c1f30543d29650b6",
                "sha256": "8829be60ae71d9045b276c5b88e73472e5f2b205c9968b8be5581ca6097baee4"
            },
            "downloads": -1,
            "filename": "newsman-1.1.0.tar.gz",
            "has_sig": false,
            "md5_digest": "40e1030f877cb6c7c1f30543d29650b6",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.6.0",
            "size": 13078,
            "upload_time": "2019-11-13T10:51:12",
            "upload_time_iso_8601": "2019-11-13T10:51:12.195741Z",
            "url": "https://files.pythonhosted.org/packages/89/ba/f5e57abc5d602528f268d72bd2e74dc8d6e4477beb3711a880ffe36c721b/newsman-1.1.0.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "vulnerabilities": []
}