Example Page

This is not a valid HTML\n\t\t\t\n\t\t\"\"\"\n\t>>> h2d_instance = HTML2Data(html = html) #You can also create it from a url = url\n\nUsing XPATH config\n--------------------\nOne you have the object \n::\n\n\t>>> config = [\n {'name': 'header_title', 'xpath': '//head/title/text()'},\n {'name': 'body_title', 'xpath': '//h1/b/text()'},\n {'name': 'description', 'xpath': '//div[@class=\"description\"]/text()'},\n ]\n\n\t>>> h2d_instance.parse(config = config)\n\t{'header_title': 'Example Page', 'body_title': 'Title', 'description': 'This is not a valid HTML'}\n\nUsing CSS SELECTOR config\n-------------------------\n::\n\n\t>>> config = [\n\t {'name': 'header_title', 'css': 'head title'},\n\t {'name': 'body_title', 'css': 'h1 b '},\n\t {'name': 'description', 'css': 'div.description'},\n\t ]\n\n\t>>> h2d_instance.parse(config = config)\n\t{'header_title': 'Example Page', 'body_title': 'Title', 'description': 'This is not a valid HTML'}\n\n\nReal life example\n-----------------\n::\n\n\timport urllib2\n\n\tfrom html2data import HTML2Data\n\n\tresponse = urllib2.urlopen('http://sil.senado.cl/cgi-bin/sil_ultproy.pl')\n\thtml = response.read()\n\n\tconfig = [\n\t {'name': 'fecha', 'css': 'td:nth-child(1)'},\n\t {'name': 'id', 'css': 'td:nth-child(2) a'},\n\t {'name': 'nombre', 'css': 'td:nth-child(3)'},\n\t {'name': 'estado', 'css': 'td:nth-child(4)'},\n\t]\n\n\thtml_instance = HTML2Data(html = html)\n\trows = html_instance.parse_one(css = 'td td tr', multiple = True, text = False)\n\tfor row_element in rows:\n\t row_in_html = HTML2Data(tree = row_element)\n\t print row_in_html.parse(config = config)\n\nYou will get something like:\n::\n\n\t{'nombre': 'Reforma Constitucional que restablece obligatoriedad del voto.', 'fecha': '24/11/2011', 'estado': 'En tramitaci\u00f3n', 'id': '8062-07'}\n\t..\n\t{'nombre': 'Proh\u00edbe el anatocismo.', 'fecha': '02/11/2011', 'estado': 'En tramitaci\u00f3n', 'id': '8007-03'}\n\n\nRequirement\n===========\n\n * lxml 2.0+\n * httplib2\n\nTests\n=====\nRequirement\n-----------\n\n * ludibrio\n * nose\n\nRun\n---\n\n >> nosetests", "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/dperezrada/html2data", "keywords": "html2data html data xpath crawler transform", "license": "BSD", "maintainer": null, "maintainer_email": null, "name": "html2data", "package_url": "https://pypi.org/project/html2data/", "platform": "UNKNOWN", "project_url": "https://pypi.org/project/html2data/", "project_urls": { "Download": "UNKNOWN", "Homepage": "https://github.com/dperezrada/html2data" }, "release_url": "https://pypi.org/project/html2data/0.4.3/", "requires_dist": null, "requires_python": null, "summary": "A simple way to transform a HTML file or URL to structured data.", "version": "0.4.3" }, "last_serial": 793036, "releases": { "0.1": [ { "comment_text": "", "digests": { "md5": "dac674411abd2550ca01ef47e4db0c6c", "sha256": "5366153f6b059c0c62b3d65f664563987a312d7f0f78f05f42bc0ec723f21d12" }, "downloads": -1, "filename": "html2data-0.1.tar.gz", "has_sig": false, "md5_digest": "dac674411abd2550ca01ef47e4db0c6c", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 1944, "upload_time": "2010-08-30T00:27:53", "url": "https://files.pythonhosted.org/packages/53/d7/9a4a5ceba2a9f4bb7692551fa448e5da28dc1a7f3c4f1652715af00e87dd/html2data-0.1.tar.gz" } ], "0.2": [ { "comment_text": "", "digests": { "md5": "72f5a884625f7f299ff3b2b7f901384b", "sha256": "e1f007745dc45dee46cb3a0adf899706a5a1f7c4d43293a6553afcc61e2e5de8" }, "downloads": -1, "filename": "html2data-0.2.tar.gz", "has_sig": false, "md5_digest": "72f5a884625f7f299ff3b2b7f901384b", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 2085, "upload_time": "2010-08-30T01:23:09", "url": "https://files.pythonhosted.org/packages/df/f8/3794cfc594507443c52827298809e4b6e50209390eeb930810e8c3295863/html2data-0.2.tar.gz" } ], "0.3": [ { "comment_text": "", "digests": { "md5": "bea39d30c952a8057fdef1ff5c7fe647", "sha256": "6de4aa992a1ba76d030db89fbbaefaa4c54c6e1e24b7e43449e5eeca7e038986" }, "downloads": -1, "filename": "html2data-0.3.tar.gz", "has_sig": false, "md5_digest": "bea39d30c952a8057fdef1ff5c7fe647", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 2433, "upload_time": "2010-09-02T15:36:03", "url": "https://files.pythonhosted.org/packages/d9/30/e3a33f1fd937a6ac26c509b867a6242d51598ffbaec6242b98c51efa96c0/html2data-0.3.tar.gz" } ], "0.4": [ { "comment_text": "", "digests": { "md5": "d29d2a15fb9579bd9c8f5c7ba27f8b77", "sha256": "af7290e935282f861e44bc7cad5a4ed8a7d6912279ae6c49ba25a65685942521" }, "downloads": -1, "filename": "html2data-0.4.tar.gz", "has_sig": false, "md5_digest": "d29d2a15fb9579bd9c8f5c7ba27f8b77", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 3331, "upload_time": "2011-11-10T13:48:08", "url": "https://files.pythonhosted.org/packages/3e/e4/c73febf873f4ee38e6e2cc976db7489affed8d06394f5cb431b462144d78/html2data-0.4.tar.gz" } ], "0.4.1": [ { "comment_text": "", "digests": { "md5": "c8ca4dd0759f06381e9efce50fb48bb1", "sha256": "4956968a43a5bba4b797432eeda9925ee2e04dd4b7b946033c4df76dfcc46af9" }, "downloads": -1, "filename": "html2data-0.4.1.tar.gz", "has_sig": false, "md5_digest": "c8ca4dd0759f06381e9efce50fb48bb1", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 3509, "upload_time": "2011-11-10T14:46:08", "url": "https://files.pythonhosted.org/packages/5c/32/5a68e5a5aed43d9f3833a76d0e6d362fbb3d73a609d32f8cb99688dd1173/html2data-0.4.1.tar.gz" } ], "0.4.2": [ { "comment_text": "", "digests": { "md5": "0596eadf7a3b7f2487616c9fc4fd9ba0", "sha256": "49d60b4a765480a998ff1113a3b0c8e5d98a8c496333a3c480804f1b2fd726f2" }, "downloads": -1, "filename": "html2data-0.4.2.tar.gz", "has_sig": false, "md5_digest": "0596eadf7a3b7f2487616c9fc4fd9ba0", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 3833, "upload_time": "2011-11-25T02:42:24", "url": "https://files.pythonhosted.org/packages/b0/3b/04496322d1e893440b83805dfa6e513a10a1d1efe94f6e3c492346b1a974/html2data-0.4.2.tar.gz" } ], "0.4.3": [ { "comment_text": "", "digests": { "md5": "a3710a11125fc0ce353f44e28178e9cb", "sha256": "0c3335cadb1ac350c3a6dae571a96b45289c7dceb8de95dbe24ca9fa49199628" }, "downloads": -1, "filename": "html2data-0.4.3.tar.gz", "has_sig": false, "md5_digest": "a3710a11125fc0ce353f44e28178e9cb", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4337, "upload_time": "2011-11-25T11:58:13", "url": "https://files.pythonhosted.org/packages/bd/91/b718643eaa9dd8307236ddf3100c3e40236e0aa03b0e08237a55998d0b40/html2data-0.4.3.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "a3710a11125fc0ce353f44e28178e9cb", "sha256": "0c3335cadb1ac350c3a6dae571a96b45289c7dceb8de95dbe24ca9fa49199628" }, "downloads": -1, "filename": "html2data-0.4.3.tar.gz", "has_sig": false, "md5_digest": "a3710a11125fc0ce353f44e28178e9cb", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4337, "upload_time": "2011-11-25T11:58:13", "url": "https://files.pythonhosted.org/packages/bd/91/b718643eaa9dd8307236ddf3100c3e40236e0aa03b0e08237a55998d0b40/html2data-0.4.3.tar.gz" } ] }