{
    "info": {
        "author": "rozap",
        "author_email": "chrisd1891@gmail.com",
        "bugtrack_url": null,
        "classifiers": [],
        "description": "corpcrawl\n=============\n\n# About\nThis is a python scraper for the Securities and Exchange Commission EDGAR database. It looks at the Form 10k\nfilings that publicly held corporations are required to file with the SEC. It then attempts to extract the \nsubsidiary relationships from the 10k exhibit 21.1. \n\nCorpcrawl is a storage agnostic scraper, so you'll need to implement your own storage scheme. \n\n\n# Installation\nYou can get the package from PyPi through Pip. \n    \n    pip install corpcrawl\n    \nFrom a python console you can try\n\n    import corpcrawl\n    \nIf it works, then you can get started\n\n# How to use\n\n## Running it\nFirst import the required pieces\n    \n    from corpcrawl.crawler import CorpCrawl\n    from corpcrawl.backend import Backend\n    \n    def main()\n        my_backend = MyBackend()\n        crawler = CorpCrawl(cache_path = '/an/absolute/path/to/some/dir', backend = my_backend)\n        c.crawl(years = [2011, 2012], quarters = [1, 2, 3, 4])\n    \n    \n    class MyBackend(Backend):\n\n        def get_company(self, name):\n            pass\n\n        def add_company(self, comp):\n            print \"Adding %s\" % str(comp)\n            \n            \n            \n            \n            \n            \nThis is about as simple of a backend as can be. This code will crawl the filings and print out the name of each\ncompany and subsidiary that it finds for all quarters of years 2011 and 2012.\nObviously you will want to hook it up to a database or something.\n\n# Notes\nThe SEC data is very unstructured. As such, there are a lot of errors. This is version 0.0.1, so instead of\nimplementing your own methods to massage the data that it returns, it would be better if you could contribute\nso make the core parser better.",
        "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/chrisd1891/corpcrawl/",
        "keywords": null,
        "license": "MIT",
        "maintainer": null,
        "maintainer_email": null,
        "name": "corpcrawl",
        "package_url": "https://pypi.org/project/corpcrawl/",
        "platform": "any",
        "project_url": "https://pypi.org/project/corpcrawl/",
        "project_urls": {
            "Download": "UNKNOWN",
            "Homepage": "https://github.com/chrisd1891/corpcrawl/"
        },
        "release_url": "https://pypi.org/project/corpcrawl/0.0.37/",
        "requires_dist": null,
        "requires_python": null,
        "summary": "Corpcrawl EDGAR Scraper",
        "version": "0.0.37"
    },
    "last_serial": 788460,
    "releases": {
        "0.0.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "605f62587cc02b14a612aff9f7cc0c90",
                    "sha256": "e6c50701d82cce3b95e91ac28d4eac19805d0e4bbdce152f76760113dfa71f85"
                },
                "downloads": -1,
                "filename": "corpcrawl-0.0.1.tar.gz",
                "has_sig": false,
                "md5_digest": "605f62587cc02b14a612aff9f7cc0c90",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 3526,
                "upload_time": "2013-03-12T03:24:24",
                "url": "https://files.pythonhosted.org/packages/92/1a/9b489fd50effafe66ed78d3e9f8e86ba4819479cc36ece934cb52d72b0af/corpcrawl-0.0.1.tar.gz"
            }
        ],
        "0.0.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "930ecb08429d991c9ee387582206e59e",
                    "sha256": "2a5d2e230f95b2761ff241fdca47350d7f51be0c2e177569992fd8bad4595ae6"
                },
                "downloads": -1,
                "filename": "corpcrawl-0.0.2.tar.gz",
                "has_sig": false,
                "md5_digest": "930ecb08429d991c9ee387582206e59e",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 4148,
                "upload_time": "2013-03-12T04:13:30",
                "url": "https://files.pythonhosted.org/packages/eb/ff/4eda7e225e148bb831959ddf6b5f6529ffed43383b4d93fb9e89f70d2f9c/corpcrawl-0.0.2.tar.gz"
            }
        ],
        "0.0.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "7c87670f3b8c189e6d585a7d22fb4646",
                    "sha256": "751834a41367fdf99380e0e155eea305e748931a6d3be9167f99188bfb330c40"
                },
                "downloads": -1,
                "filename": "corpcrawl-0.0.3.tar.gz",
                "has_sig": false,
                "md5_digest": "7c87670f3b8c189e6d585a7d22fb4646",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 4175,
                "upload_time": "2013-03-14T04:34:38",
                "url": "https://files.pythonhosted.org/packages/50/ec/6e44c00fdfbbe8cfdc088864dd26b18dcc474e21bd27200d149f8f1f0a82/corpcrawl-0.0.3.tar.gz"
            }
        ],
        "0.0.30": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "6e646532f24b4a88ceb11cf68720517d",
                    "sha256": "3e6bbec3c35a2e0d23227e4fabbcdffb8c563372b3030ceba2df0a070f9fe292"
                },
                "downloads": -1,
                "filename": "corpcrawl-0.0.30.tar.gz",
                "has_sig": false,
                "md5_digest": "6e646532f24b4a88ceb11cf68720517d",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 4333,
                "upload_time": "2013-03-14T04:44:59",
                "url": "https://files.pythonhosted.org/packages/af/53/5250f06652e943f1d34a9d1faafd6951a886270e593da2c530dd6b33d309/corpcrawl-0.0.30.tar.gz"
            }
        ],
        "0.0.31": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "baba1cace7d0222cf8acb9c0816b67a6",
                    "sha256": "38f61e03df8cb1301e811672a3cc0384484676eb749ff2076df2bdfa15aac8b4"
                },
                "downloads": -1,
                "filename": "corpcrawl-0.0.31.tar.gz",
                "has_sig": false,
                "md5_digest": "baba1cace7d0222cf8acb9c0816b67a6",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 4331,
                "upload_time": "2013-03-14T05:01:25",
                "url": "https://files.pythonhosted.org/packages/34/31/c998fb4b78bb7c5eb52f5acec94dc11fdb5200fb59f2346cfe84418259ec/corpcrawl-0.0.31.tar.gz"
            }
        ],
        "0.0.32": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "fcb0fb136dda9a463c9b538cc4cf99e6",
                    "sha256": "29cbf54de7c669fdc555e06c14b29c7393d2708f911d94b89adab92158adec5b"
                },
                "downloads": -1,
                "filename": "corpcrawl-0.0.32.tar.gz",
                "has_sig": false,
                "md5_digest": "fcb0fb136dda9a463c9b538cc4cf99e6",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 4450,
                "upload_time": "2013-03-14T05:11:15",
                "url": "https://files.pythonhosted.org/packages/c7/c4/b9e83c7bf61ce70a94beb0e9b957a5b6be6bde821dd5cdd14497560bc75a/corpcrawl-0.0.32.tar.gz"
            }
        ],
        "0.0.33": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "5bc8edae406360d7a5a4da3f33cb68a2",
                    "sha256": "2da6f33bc4e3b52c0645ad2b23e8446ecfc5b388141aa1920806ae412eb93144"
                },
                "downloads": -1,
                "filename": "corpcrawl-0.0.33.tar.gz",
                "has_sig": false,
                "md5_digest": "5bc8edae406360d7a5a4da3f33cb68a2",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 16148,
                "upload_time": "2013-03-14T05:16:18",
                "url": "https://files.pythonhosted.org/packages/a1/c7/20f655b7e588e8186f519f06dcdfe3acbadce230376b0116e09aeebc8289/corpcrawl-0.0.33.tar.gz"
            }
        ],
        "0.0.34": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "505b4f3b7041e1f6a5f33ac09f9c40e7",
                    "sha256": "1c0bf8b0f8baa248109fc6ad470b6c096ff24f001af4ff544ad49756119e3fd6"
                },
                "downloads": -1,
                "filename": "corpcrawl-0.0.34.tar.gz",
                "has_sig": false,
                "md5_digest": "505b4f3b7041e1f6a5f33ac09f9c40e7",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 16077,
                "upload_time": "2013-03-14T05:32:51",
                "url": "https://files.pythonhosted.org/packages/4d/ac/137a2f88c138787d5784d49be5ce9a01f68a6d4f6979992653597c6a7087/corpcrawl-0.0.34.tar.gz"
            }
        ],
        "0.0.35": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "0146a30e69797c396618a737e41c4dcb",
                    "sha256": "71136fda16e836134363162385ba97d8beb86d04cc700bce8b0770b766c28eb7"
                },
                "downloads": -1,
                "filename": "corpcrawl-0.0.35.tar.gz",
                "has_sig": false,
                "md5_digest": "0146a30e69797c396618a737e41c4dcb",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 16082,
                "upload_time": "2013-03-14T05:42:38",
                "url": "https://files.pythonhosted.org/packages/4f/5a/e61bd273f97a5b6de26c5228011a54b65ef3432b23b019fd41c7e30297a3/corpcrawl-0.0.35.tar.gz"
            }
        ],
        "0.0.36": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "d3bc16b7b22ea9809eb6b09c4e6df72d",
                    "sha256": "90f16b6d3a68abc588464414fef0933a97b6703320bf3a891cc25abd1ba4bd32"
                },
                "downloads": -1,
                "filename": "corpcrawl-0.0.36.tar.gz",
                "has_sig": false,
                "md5_digest": "d3bc16b7b22ea9809eb6b09c4e6df72d",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 16176,
                "upload_time": "2013-03-14T06:13:29",
                "url": "https://files.pythonhosted.org/packages/ce/71/dd6fecf99bd340fcfdc32d7204fdf702f4fb0d2bc053febbe3bee03019ba/corpcrawl-0.0.36.tar.gz"
            }
        ],
        "0.0.37": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "7110980ed14a0735f4e984547a14bb7f",
                    "sha256": "c29bca0e249d24286f01dd7630eabe953b4498615a6b9de26c2de563d7803214"
                },
                "downloads": -1,
                "filename": "corpcrawl-0.0.37.tar.gz",
                "has_sig": false,
                "md5_digest": "7110980ed14a0735f4e984547a14bb7f",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 16586,
                "upload_time": "2013-03-14T06:38:02",
                "url": "https://files.pythonhosted.org/packages/1b/11/2d93c6021fc0bd1bcc54b08fb80b304299057a12e554cfff1d9316274dff/corpcrawl-0.0.37.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "7110980ed14a0735f4e984547a14bb7f",
                "sha256": "c29bca0e249d24286f01dd7630eabe953b4498615a6b9de26c2de563d7803214"
            },
            "downloads": -1,
            "filename": "corpcrawl-0.0.37.tar.gz",
            "has_sig": false,
            "md5_digest": "7110980ed14a0735f4e984547a14bb7f",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 16586,
            "upload_time": "2013-03-14T06:38:02",
            "url": "https://files.pythonhosted.org/packages/1b/11/2d93c6021fc0bd1bcc54b08fb80b304299057a12e554cfff1d9316274dff/corpcrawl-0.0.37.tar.gz"
        }
    ]
}