{ "info": { "author": "", "author_email": "", "bugtrack_url": null, "classifiers": [], "description": "Skyscraper\n==========\n\nYAML based lightweight crawlers\n\n\nInstallation\n------------\n\n::\n\n pip install skyscraper\n\n\nUsage\n-----\n\n\nEach web crawler is defined in a yml file\n\n::\n\n # the name of the crawler\n name: Python 3.x docs\n # the number of parallel thread workers\n threads: 3\n\n # start urls\n params:\n start_url: https://docs.python.org/3/index.html\n\n # how/where the results are saved\n results:\n type: Json\n file: \"python.json\"\n\n # on each url labeled \"result\", results will be extracted using\n # this scheme\n result_extractor:\n fields:\n - name: title\n rules:\n select: h1\n text: yes\n single: true\n\n\n # the first page is labeled \"start\" and for each extracted url, we label it\n # accordingly. In this example, we extract the results directly from\n # the first page\n steps:\n - name: start\n label: start\n extract:\n - type: ahrefs\n label: result\n rules:\n select: a.biglink\n\n\nTo run the crawler, execute\n\n::\n\n skyscraper run examples/python_docs.yaml\n\n\n", "description_content_type": "text/x-rst", "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://gitlab.com/woning-group/libs/skyscraper", "keywords": "", "license": "", "maintainer": "", "maintainer_email": "", "name": "skyscraper", "package_url": "https://pypi.org/project/skyscraper/", "platform": "", "project_url": "https://pypi.org/project/skyscraper/", "project_urls": { "Homepage": "https://gitlab.com/woning-group/libs/skyscraper" }, "release_url": "https://pypi.org/project/skyscraper/0.0.5/", "requires_dist": [ "woning-wattle", "click", "requests", "beautifulsoup4", "woning-bricks; extra == 'dev'" ], "requires_python": "", "summary": "YAML based lightweight crawlers", "version": "0.0.5" }, "last_serial": 4019798, "releases": { "0.0.1": [ { "comment_text": "", "digests": { "md5": "e9d89dc057da1b7187fe667d507093c9", "sha256": "e5102ddff69e7fa219e82c1502831165ada84ce9e6797b00b537d0fafe3727d1" }, "downloads": -1, "filename": "skyscraper-0.0.1-py3-none-any.whl", "has_sig": false, "md5_digest": "e9d89dc057da1b7187fe667d507093c9", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 5616, "upload_time": "2018-07-01T08:33:49", "url": "https://files.pythonhosted.org/packages/dc/64/adcc2ebccc84d9db08a4e5889891d945c41d1200571c6dd30d76ed10c605/skyscraper-0.0.1-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "75c1f71b66c7a38b1cac3c885e6b52ae", "sha256": "8fd65cfa79ec4bae5a8267a8ca95aa3ab5045128c367ab492844d838315293a2" }, "downloads": -1, "filename": "skyscraper-0.0.1.tar.gz", "has_sig": false, "md5_digest": "75c1f71b66c7a38b1cac3c885e6b52ae", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 3374, "upload_time": "2018-07-01T08:33:50", "url": "https://files.pythonhosted.org/packages/38/2a/c99637469a140b74d3858b3253245d5f63331074a36a59db9382248bee0f/skyscraper-0.0.1.tar.gz" } ], "0.0.2": [ { "comment_text": "", "digests": { "md5": "a8023813bae5d084cc309f6bbeb214ea", "sha256": "b2c73973690a49eb0491fd110ed45a84db8b8e46a2d1357bc058a62ad83ab045" }, "downloads": -1, "filename": "skyscraper-0.0.2-py3-none-any.whl", "has_sig": false, "md5_digest": "a8023813bae5d084cc309f6bbeb214ea", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 5642, "upload_time": "2018-07-01T08:42:56", "url": "https://files.pythonhosted.org/packages/81/12/4d57c0277e520fc5cba1d17a0aee18128b937e16e6262a4dd17064811159/skyscraper-0.0.2-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "b41a3177e863e92c7ee30a9f0b84058c", "sha256": "014c93cbaee16d1ce2700b0c4902f1b6844ac5cdb9ebf350a5a1961d065b95db" }, "downloads": -1, "filename": "skyscraper-0.0.2.tar.gz", "has_sig": false, "md5_digest": "b41a3177e863e92c7ee30a9f0b84058c", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 3942, "upload_time": "2018-07-01T08:42:57", "url": "https://files.pythonhosted.org/packages/15/1f/03456492d3a2b290643522011fe84a986ab6cb5e001e2e7e6f38b4720f09/skyscraper-0.0.2.tar.gz" } ], "0.0.3": [ { "comment_text": "", "digests": { "md5": "7ee72b43c30e3e3eaabe937e433cc9a4", "sha256": "0d673e1f0be9d43c327113474a7bc2c73e1fb065316e045ac1d7832c7505e85e" }, "downloads": -1, "filename": "skyscraper-0.0.3-py3-none-any.whl", "has_sig": false, "md5_digest": "7ee72b43c30e3e3eaabe937e433cc9a4", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 6058, "upload_time": "2018-07-01T08:45:51", "url": "https://files.pythonhosted.org/packages/a1/29/e5b7a99eb11ca5765cd15d7c717b484713133a777854407e9c5b65b1015a/skyscraper-0.0.3-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "66c0e4cf07bc958a6efd5e22379501d6", "sha256": "3121a0c440d5688beb9a9be7a8f5800a279dc8d84fdf0b0a8539f1eeba5dddbb" }, "downloads": -1, "filename": "skyscraper-0.0.3.tar.gz", "has_sig": false, "md5_digest": "66c0e4cf07bc958a6efd5e22379501d6", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4155, "upload_time": "2018-07-01T08:45:52", "url": "https://files.pythonhosted.org/packages/8f/5f/3f1ef52c90108f7e8e1fcc9285ac21f7e26eacc5709b8f1baa5a611b48cd/skyscraper-0.0.3.tar.gz" } ], "0.0.4": [ { "comment_text": "", "digests": { "md5": "6322f9ef3976a8013aae98993944828d", "sha256": "d2ce5cfa275a1a32ae46762bb8e305a44b2e7e642999395a0d7ce27d09f49958" }, "downloads": -1, "filename": "skyscraper-0.0.4-py3-none-any.whl", "has_sig": false, "md5_digest": "6322f9ef3976a8013aae98993944828d", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 6084, "upload_time": "2018-07-01T08:47:29", "url": "https://files.pythonhosted.org/packages/19/7c/36fa3047743027cab5037ca0ace29f2992ef4ee3525ff8cd284de278bb8f/skyscraper-0.0.4-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "3731362babd8d56d8116341d5ae1d1dc", "sha256": "35467b0f34e471ab1892b3db67c9325ffb9fc1a30b326ac315c99f2770212fea" }, "downloads": -1, "filename": "skyscraper-0.0.4.tar.gz", "has_sig": false, "md5_digest": "3731362babd8d56d8116341d5ae1d1dc", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4186, "upload_time": "2018-07-01T08:47:30", "url": "https://files.pythonhosted.org/packages/b8/e9/9cd099f4ce7decde9a22e88869e941a847b9747768235ed59dc1ad66d2c1/skyscraper-0.0.4.tar.gz" } ], "0.0.5": [ { "comment_text": "", "digests": { "md5": "986133cfc77d43187f565c4d11c6be19", "sha256": "cfd51f80d32e4c7e5803c6d9be2def7b2244141798cebda000ab986a1144e33e" }, "downloads": -1, "filename": "skyscraper-0.0.5-py3-none-any.whl", "has_sig": false, "md5_digest": "986133cfc77d43187f565c4d11c6be19", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 6113, "upload_time": "2018-07-01T09:03:47", "url": "https://files.pythonhosted.org/packages/87/21/5939f42b87fb68389b772342468eb0651cba700cc8f69dfa4345a5ad6635/skyscraper-0.0.5-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "ac8c43e72c13c8417c524e030427f1ca", "sha256": "c5fb4f5ef39194a1f566a497da4053de27494c58e537d59afc09203c4e2fc74b" }, "downloads": -1, "filename": "skyscraper-0.0.5.tar.gz", "has_sig": false, "md5_digest": "ac8c43e72c13c8417c524e030427f1ca", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4194, "upload_time": "2018-07-01T09:03:50", "url": "https://files.pythonhosted.org/packages/85/f0/c76e3617212afc8b846f1cabf1a17931d31d128cd88213f92164b2537ca1/skyscraper-0.0.5.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "986133cfc77d43187f565c4d11c6be19", "sha256": "cfd51f80d32e4c7e5803c6d9be2def7b2244141798cebda000ab986a1144e33e" }, "downloads": -1, "filename": "skyscraper-0.0.5-py3-none-any.whl", "has_sig": false, "md5_digest": "986133cfc77d43187f565c4d11c6be19", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 6113, "upload_time": "2018-07-01T09:03:47", "url": "https://files.pythonhosted.org/packages/87/21/5939f42b87fb68389b772342468eb0651cba700cc8f69dfa4345a5ad6635/skyscraper-0.0.5-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "ac8c43e72c13c8417c524e030427f1ca", "sha256": "c5fb4f5ef39194a1f566a497da4053de27494c58e537d59afc09203c4e2fc74b" }, "downloads": -1, "filename": "skyscraper-0.0.5.tar.gz", "has_sig": false, "md5_digest": "ac8c43e72c13c8417c524e030427f1ca", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4194, "upload_time": "2018-07-01T09:03:50", "url": "https://files.pythonhosted.org/packages/85/f0/c76e3617212afc8b846f1cabf1a17931d31d128cd88213f92164b2537ca1/skyscraper-0.0.5.tar.gz" } ] }