{ "info": { "author": "Ray", "author_email": "miuyin@126.com", "bugtrack_url": null, "classifiers": [ "Intended Audience :: Developers", "License :: OSI Approved :: MIT License", "Operating System :: OS Independent", "Programming Language :: Python" ], "description": "##Example.py\n\n# -*- coding: utf-8 -*-\nfrom pyquery import PyQuery as pq\n\nfrom newspider.interfaces import *\nfrom newspider.spider import Newspider\n\n\nclass DemoFetcher(IntFetcher):\n def __init__(self):\n self.next_page = []\n\n def fetch_detail_urls(self,html):\n d = pq(html)\n list = []\n\n for a in d('.post-title a'):\n url = d(a).attr('href')\n extras = {\"category\": \"Test for %s\" % url}\n list.append((url,extras))\n\n for l in d('.page-navigator a'):\n self.next_page.append(d(l).attr('href'))\n\n return list\n\n def start_page(self):\n return ['http://www.typechodev.com/','http://www.typechodev.com/index.php/category/questions/']\n\n def next_pages(self):\n return self.next_page\n\n\nclass DemoParser(IntParser):\n def parse(self,tag,html,extras):\n print \"Receive content from url %s for tag %s|%s\" % (extras.get('_url'),extras.get('category'),tag)\n\n\nif __name__ == '__main__':\n sp = Newspider()\n sp.config('GUARD_INTERVAL', 0)\n\n sp.add_parser(DemoParser())\n sp.add_fetcher(DemoFetcher())\n\n sp.run()\n\n", "description_content_type": null, "docs_url": null, "download_url": "UNKNOWN", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "http://www.typechodev.com", "keywords": "", "license": "MIT", "maintainer": null, "maintainer_email": null, "name": "newspider", "package_url": "https://pypi.org/project/newspider/", "platform": "any", "project_url": "https://pypi.org/project/newspider/", "project_urls": { "Download": "UNKNOWN", "Homepage": "http://www.typechodev.com" }, "release_url": "https://pypi.org/project/newspider/0.9.9/", "requires_dist": null, "requires_python": null, "summary": "\u5206\u7c7b\u6252\u6570\u636e\u7684\u7b80\u6613\u6846\u67b6", "version": "0.9.9" }, "last_serial": 2344210, "releases": { "0.9": [ { "comment_text": "", "digests": { "md5": "47d643b8c6ecf63b4747b91eacddd487", "sha256": "0e6d6d0d4b3b6fde05fdd567b53f5f9c59b8ec226445b3860fb9edfb079d8bb9" }, "downloads": -1, "filename": "newspider-0.9.tar.gz", "has_sig": false, "md5_digest": "47d643b8c6ecf63b4747b91eacddd487", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 5766, "upload_time": "2016-08-28T09:17:12", "url": "https://files.pythonhosted.org/packages/a7/15/6bcd7a67fd2ca601312153093b75290562936fcb3c1ac1c70fce95acf207/newspider-0.9.tar.gz" } ], "0.9.1": [ { "comment_text": "", "digests": { "md5": "9bd2be9ec45ca3ebba06248afb8deaa5", "sha256": "9e871a01209755f63cc914e06cd667115236a5eed07fddf1be22537fb05d16db" }, "downloads": -1, "filename": "newspider-0.9.1.tar.gz", "has_sig": false, "md5_digest": "9bd2be9ec45ca3ebba06248afb8deaa5", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 6157, "upload_time": "2016-08-28T09:33:15", "url": "https://files.pythonhosted.org/packages/db/97/6ab2be0bd9b087a94174fbb6b99a896cdb1a5022c47a0183eeaab1b2d434/newspider-0.9.1.tar.gz" } ], "0.9.2": [ { "comment_text": "", "digests": { "md5": "d16de1061ec6669fd3e671b1176f33d3", "sha256": "75c37cd76710c493f12a92d70b53f5d55af4675a70bf3caac9a7e2cb6cd6031d" }, "downloads": -1, "filename": "newspider-0.9.2.tar.gz", "has_sig": false, "md5_digest": "d16de1061ec6669fd3e671b1176f33d3", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 6412, "upload_time": "2016-09-03T08:24:49", "url": "https://files.pythonhosted.org/packages/28/55/34d91ae1e4a972aa8e7f0a46904770856699100169ad5d38ec140347f597/newspider-0.9.2.tar.gz" } ], "0.9.3": [ { "comment_text": "", "digests": { "md5": "a1a130f8a012c2cb89a5cb51b2e83489", "sha256": "35900a8aefcdb384b9609f515a7ef8ac941845bfc99e3520f1f3f9d411d314cb" }, "downloads": -1, "filename": "newspider-0.9.3.tar.gz", "has_sig": false, "md5_digest": "a1a130f8a012c2cb89a5cb51b2e83489", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 6335, "upload_time": "2016-09-03T09:17:51", "url": "https://files.pythonhosted.org/packages/1d/d8/f03290e00289708cd2d8d8bd4cc1d273e30856aad8b41daca2dbe28372a7/newspider-0.9.3.tar.gz" } ], "0.9.5": [ { "comment_text": "", "digests": { "md5": "364192cf01cd6b4b08b8a89d91e67135", "sha256": "2821dd3d4c7bd4f75b960a211a4663734906ede74e35df6c92a136898c84c952" }, "downloads": -1, "filename": "newspider-0.9.5.tar.gz", "has_sig": false, "md5_digest": "364192cf01cd6b4b08b8a89d91e67135", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 6436, "upload_time": "2016-09-03T10:19:41", "url": "https://files.pythonhosted.org/packages/a9/e1/2b4a1d5fe6fc241159ce4e557a3d5f307053c310dd72d4f2db12d7a615dd/newspider-0.9.5.tar.gz" } ], "0.9.6": [ { "comment_text": "", "digests": { "md5": "96fdf2e053fb398fc334e8a93864c719", "sha256": "493a7efd099d8285935b6610f684295be42175682b8d7635642ffdb831eb081c" }, "downloads": -1, "filename": "newspider-0.9.6.tar.gz", "has_sig": false, "md5_digest": "96fdf2e053fb398fc334e8a93864c719", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 8080, "upload_time": "2016-09-03T11:54:11", "url": "https://files.pythonhosted.org/packages/a8/38/c34028f608c035ae4ec5d4c8dce1a9a6f1ab8dc7d4b855ecd9d45c360ef9/newspider-0.9.6.tar.gz" } ], "0.9.7": [ { "comment_text": "", "digests": { "md5": "6e78ba46f93a8743b5ea3042e858ad88", "sha256": "8c7d3dee2145f6388dd48deffcc70cc23c21be17e2d8b19ebb7843042d3ee325" }, "downloads": -1, "filename": "newspider-0.9.7.tar.gz", "has_sig": false, "md5_digest": "6e78ba46f93a8743b5ea3042e858ad88", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 7803, "upload_time": "2016-09-04T03:41:45", "url": "https://files.pythonhosted.org/packages/6c/98/75a97174fc8f2d8bc93ddb47169a6b0daf0a4dd2b02da6b9c90ebb8e158f/newspider-0.9.7.tar.gz" } ], "0.9.8": [ { "comment_text": "", "digests": { "md5": "9d43831f666f087210ffda3e0de9c1b1", "sha256": "dd7d4bcc0320dec1a9651af1d40a5c0982528dfa89a8169d8a0e7c42e77fae3f" }, "downloads": -1, "filename": "newspider-0.9.8.tar.gz", "has_sig": false, "md5_digest": "9d43831f666f087210ffda3e0de9c1b1", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 7892, "upload_time": "2016-09-04T04:00:11", "url": "https://files.pythonhosted.org/packages/a2/7d/82812af2ed7af4f2e5b96029394541e36c755b547df6bbe0be630db9c758/newspider-0.9.8.tar.gz" } ], "0.9.9": [ { "comment_text": "", "digests": { "md5": "e11f816e342dda8c2adf3c4df2f82bff", "sha256": "ec8f628be4c38c9b4aa9e13a38d6ab1e462f9532695262c36b47ae3418a2d109" }, "downloads": -1, "filename": "newspider-0.9.9.tar.gz", "has_sig": false, "md5_digest": "e11f816e342dda8c2adf3c4df2f82bff", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 7963, "upload_time": "2016-09-15T13:04:11", "url": "https://files.pythonhosted.org/packages/5f/b3/86af61ea05bccee02f2658de289ef087cbd71c26a0f7b35e31223414bd4c/newspider-0.9.9.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "e11f816e342dda8c2adf3c4df2f82bff", "sha256": "ec8f628be4c38c9b4aa9e13a38d6ab1e462f9532695262c36b47ae3418a2d109" }, "downloads": -1, "filename": "newspider-0.9.9.tar.gz", "has_sig": false, "md5_digest": "e11f816e342dda8c2adf3c4df2f82bff", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 7963, "upload_time": "2016-09-15T13:04:11", "url": "https://files.pythonhosted.org/packages/5f/b3/86af61ea05bccee02f2658de289ef087cbd71c26a0f7b35e31223414bd4c/newspider-0.9.9.tar.gz" } ] }