{ "info": { "author": "Robert McHardy", "author_email": "robert@robertmchardy.de", "bugtrack_url": null, "classifiers": [ "License :: OSI Approved :: MIT License", "Operating System :: OS Independent", "Programming Language :: Python :: 3", "Programming Language :: Python :: 3.5", "Programming Language :: Python :: 3.6", "Programming Language :: Python :: 3.7", "Programming Language :: Python :: 3.8" ], "description": "# Mindfactory.de Crawler\nThis repository contains a crawler for [Mindfactory](https://www.mindfactory.de), a German ecommerce shop (for computer hardware). The crawler extracts the data contained on every single product page and stores the scraped products and reviews in a SQLite database consisting of two tables. \n\nEach product has the following properties: \n* ID (SQLite identifier)\n* URL\n* Product name\n* Brand name\n* Category (i.e. CPU)\n* EAN\n* SKU\n* Items sold (Count)\n* People watching (Count)\n* RMA quote (in percent)\n* Average rating (from 1.0 to 5.0)\n* Shipping (information on availability)\n* Price (in Euro) \n\nAdditionally, for every product all reviews are collected and stored in a separate SQLite table. An entry in this table has the following properties:\n* Product ID (Reference to the corresponding ID in the product table)\n* Stars (Rating, from 1 to 5)\n* Text\n* Author\n* Date (YYYY-MM-DD)\n* Verified (actually bought the product at Mindfactory)\n\n# Prerequisites \n* Python3\n* scrapy\n* SQLite3\n\n# Run the scraper \n scrapy crawl mindfactory_products\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/RobMcH/mindfactory_crawling", "keywords": "", "license": "", "maintainer": "", "maintainer_email": "", "name": "mindfactory-crawling", "package_url": "https://pypi.org/project/mindfactory-crawling/", "platform": "", "project_url": "https://pypi.org/project/mindfactory-crawling/", "project_urls": { "Homepage": "https://github.com/RobMcH/mindfactory_crawling" }, "release_url": "https://pypi.org/project/mindfactory-crawling/1.0.4/", "requires_dist": [ "scrapy" ], "requires_python": "", "summary": "A crawler for mindfactory.de", "version": "1.0.4" }, "last_serial": 4807462, "releases": { "1.0.3": [ { "comment_text": "", "digests": { "md5": "875e3525ddc71b924f57427a46d4b966", "sha256": "fa6c7611c9d737f0d9e00663a40d0f0fb068ce268292cfb6ef82a743db5c0761" }, "downloads": -1, "filename": "mindfactory_crawling-1.0.3-py3-none-any.whl", "has_sig": false, "md5_digest": "875e3525ddc71b924f57427a46d4b966", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 10638, "upload_time": "2019-02-11T19:15:53", "url": "https://files.pythonhosted.org/packages/8e/08/0f723553239a397b3cb2c737e09e9401ee7a647a2e44db86f387904f5b2d/mindfactory_crawling-1.0.3-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "105b698bfcdb4918944229da612f9938", "sha256": "6ce95fbc61946ea958349b7bf5465e4b4aef6138aa51532163262ec368e6b691" }, "downloads": -1, "filename": "mindfactory_crawling-1.0.3.tar.gz", "has_sig": false, "md5_digest": "105b698bfcdb4918944229da612f9938", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 7186, "upload_time": "2019-02-11T19:15:55", "url": "https://files.pythonhosted.org/packages/f8/3d/a07d3cada49987c382746cc5481b4d99e65068e9aff135d3d5ddfac7b4da/mindfactory_crawling-1.0.3.tar.gz" } ], "1.0.4": [ { "comment_text": "", "digests": { "md5": "7b8a6318a28143d866bf72ea9f84fe93", "sha256": "cf81026e1668d1a487cd09abd3c742626abb63d0d7702eca7607e5be1d6e6934" }, "downloads": -1, "filename": "mindfactory_crawling-1.0.4-py3-none-any.whl", "has_sig": false, "md5_digest": "7b8a6318a28143d866bf72ea9f84fe93", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 10666, "upload_time": "2019-02-11T19:17:15", "url": "https://files.pythonhosted.org/packages/81/47/81f46033cf43c985910fa994fa3069e601d0277834876d6506c1ab61efef/mindfactory_crawling-1.0.4-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "edbfbc7a26353fd8f26c462935614df2", "sha256": "67a18d583b64f9609234e4bd9152d21090df3d8df17d4fb2fa3bf15b0f6ee7e5" }, "downloads": -1, "filename": "mindfactory_crawling-1.0.4.tar.gz", "has_sig": false, "md5_digest": "edbfbc7a26353fd8f26c462935614df2", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 7226, "upload_time": "2019-02-11T19:17:16", "url": "https://files.pythonhosted.org/packages/57/99/278e355ba6e99dae949b6890c6f04fdf3218696c4f932a31b4fd66e66963/mindfactory_crawling-1.0.4.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "7b8a6318a28143d866bf72ea9f84fe93", "sha256": "cf81026e1668d1a487cd09abd3c742626abb63d0d7702eca7607e5be1d6e6934" }, "downloads": -1, "filename": "mindfactory_crawling-1.0.4-py3-none-any.whl", "has_sig": false, "md5_digest": "7b8a6318a28143d866bf72ea9f84fe93", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 10666, "upload_time": "2019-02-11T19:17:15", "url": "https://files.pythonhosted.org/packages/81/47/81f46033cf43c985910fa994fa3069e601d0277834876d6506c1ab61efef/mindfactory_crawling-1.0.4-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "edbfbc7a26353fd8f26c462935614df2", "sha256": "67a18d583b64f9609234e4bd9152d21090df3d8df17d4fb2fa3bf15b0f6ee7e5" }, "downloads": -1, "filename": "mindfactory_crawling-1.0.4.tar.gz", "has_sig": false, "md5_digest": "edbfbc7a26353fd8f26c462935614df2", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 7226, "upload_time": "2019-02-11T19:17:16", "url": "https://files.pythonhosted.org/packages/57/99/278e355ba6e99dae949b6890c6f04fdf3218696c4f932a31b4fd66e66963/mindfactory_crawling-1.0.4.tar.gz" } ] }