{ "info": { "author": "kafka0102", "author_email": "yujianjia@sensedeal.ai", "bugtrack_url": null, "classifiers": [ "Intended Audience :: Developers", "License :: OSI Approved :: BSD License", "Operating System :: OS Independent", "Programming Language :: Python", "Programming Language :: Python :: 3.6", "Topic :: Internet :: WWW/HTTP", "Topic :: Internet :: WWW/HTTP :: Dynamic Content" ], "description": "# sense-text-extractor\n\nsense-text-extractor\u662f\u6b63\u6587\u62bd\u53d6\u5ba2\u6237\u7aef\u5e93\n\n\n## \u5b89\u88c5\u65b9\u5f0f(\u5f53\u524d\u7248\u672c0.0.1)\n\n pip install sense-text-extractor\n\n## \u4f7f\u7528\u6307\u5357\n\n\u57fa\u4e8esense-core\u7684settings.ini\u7684label\u914d\u7f6e\u8c03\u7528\uff1a\n\n from sense_text_extractor import SenseTextExtractor\n extractor = SenseTextExtractor(label='text_extractor')\n text = extractor.extract_text(\"http://sports.sina.com.cn/g/pl/2019-01-11/doc-ihqhqcis5048507.shtml\", \"\u7a46\u91cc\u5c3c\u5965\u5728\u7b49\u5f85\u590d\u51fa\")\n print(text)\n\n\u4f7f\u7528host\u548cport\u7684\u8c03\u7528\uff1a\n\n extractor = SenseTextExtractor('52.83.143.61', '6681')\n text = extractor.extract_text(\"http://sports.sina.com.cn/g/pl/2019-01-11/doc-ihqhqcis5048507.shtml\", \"\u7a46\u91cc\u5c3c\u5965\u5728\u7b49\u5f85\u590d\u51fa\")\n print(text)\n\n\n## \u4f7f\u7528\u8bf4\u660e\n\nextract_text\u65b9\u6cd5\u53ef\u80fd\u629b\u51fa\u5f02\u5e38\uff0c\u9700\u8981\u81ea\u5df1\u6355\u6349\u3002\u8fd4\u56de\u7ed3\u679c\u662fstring\uff0c\u5982\u679c\u662f''\u5b57\u7b26\u4e32\uff0c\u8868\u793a\u53ef\u80fd\u6ca1\u6709\u62bd\u53d6\u51fa\u6b63\u6587\u3002\n\u5982\u679c\u7528\u4e8e\u722c\u866b\uff0cextract_text\u9700\u8981\u4f20\u5165\u7b2c\u4e09\u4e2a\u53c2\u6570\uff0c\u4e5f\u5c31\u662f\u4e0b\u8f7d\u7684html\u6e90\u7801\uff0c\u5426\u5219extractor\u7684sever\u7aef\u56e0\u4e3a\u83b7\u53d6\u8d85\u65f6\u800c\u629b\u51fa\u5f02\u5e38\uff0c\u4e5f\u5bb9\u6613\u88ab\u53cd\u722c\u866b\u9650\u5236\u3002\n\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": "", "keywords": "", "license": "BSD License", "maintainer": "", "maintainer_email": "", "name": "sense-text-extractor", "package_url": "https://pypi.org/project/sense-text-extractor/", "platform": "", "project_url": "https://pypi.org/project/sense-text-extractor/", "project_urls": null, "release_url": "https://pypi.org/project/sense-text-extractor/0.0.5/", "requires_dist": [ "grpcio", "protobuf", "sense-core (>=0.0.18)" ], "requires_python": "", "summary": "sense_text_extractor", "version": "0.0.5" }, "last_serial": 4943982, "releases": { "0.0.1": [ { "comment_text": "", "digests": { "md5": "9cba326bc43c15bf484891120c3d1620", "sha256": "a9896e4e7099e808eae30cce218567294e3d75e7027172e1b3be42efbf590326" }, "downloads": -1, "filename": "sense_text_extractor-0.0.1-py3-none-any.whl", "has_sig": false, "md5_digest": "9cba326bc43c15bf484891120c3d1620", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 4271, "upload_time": "2019-01-11T14:10:13", "url": "https://files.pythonhosted.org/packages/82/50/09294e7026ae45e7dd4fabc503f93774531ccfc8b30a038ae077ba90ba3d/sense_text_extractor-0.0.1-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "3932a0731fcaacb3d47126c69cb470db", "sha256": "da8c66ee4ea8e98bb82796c9cea4b2155f0af48df7441578db33ed7c1db33e4f" }, "downloads": -1, "filename": "sense-text-extractor-0.0.1.tar.gz", "has_sig": false, "md5_digest": "3932a0731fcaacb3d47126c69cb470db", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 3435, "upload_time": "2019-01-11T14:10:21", "url": "https://files.pythonhosted.org/packages/70/93/8aa36b0bc2b79c6023182161d372152e64ac4782b8d9641495de3dc501e7/sense-text-extractor-0.0.1.tar.gz" } ], "0.0.2": [ { "comment_text": "", "digests": { "md5": "a8875104384a8dc0957553327a730f01", "sha256": "534b68fa53f1a40214b3d9b44403b8707307be26e07a56abeff73f964fed7fea" }, "downloads": -1, "filename": "sense_text_extractor-0.0.2-py3-none-any.whl", "has_sig": false, "md5_digest": "a8875104384a8dc0957553327a730f01", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 5260, "upload_time": "2019-02-25T07:56:12", "url": "https://files.pythonhosted.org/packages/ef/7c/48f52299440f15fcfd6d4d646cc5be517170a7e0e421fe60a2d4932dc3b7/sense_text_extractor-0.0.2-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "53c27cec66313b3ae01a2aa445c57e23", "sha256": "5a228b7018ff6da2841ca3c20a03ce13a605b40f7f5b9192811d471f4904c39d" }, "downloads": -1, "filename": "sense-text-extractor-0.0.2.tar.gz", "has_sig": false, "md5_digest": "53c27cec66313b3ae01a2aa445c57e23", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4458, "upload_time": "2019-02-25T07:56:14", "url": "https://files.pythonhosted.org/packages/67/26/fd429b14b5ccb4f993a5e0444737de80e506ebaf4ad39b232331a339b159/sense-text-extractor-0.0.2.tar.gz" } ], "0.0.3": [ { "comment_text": "", "digests": { "md5": "7cb0c009273e8c30d6cc309479840e57", "sha256": "364f8f00e48d972b33ce26e74875f5c6e0846acdb9ea55e887fe42227771be5f" }, "downloads": -1, "filename": "sense_text_extractor-0.0.3-py3-none-any.whl", "has_sig": false, "md5_digest": "7cb0c009273e8c30d6cc309479840e57", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 5448, "upload_time": "2019-02-25T09:24:13", "url": "https://files.pythonhosted.org/packages/37/2b/a5b8fd6b18436ffa39a590bb4ebc769ba5bad47ecb65748259ea7c425aa8/sense_text_extractor-0.0.3-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "3dba2e32fa172bf537f843ad86da8bb8", "sha256": "93f992ac95c7f0a16ad942b9ef0f95817a2cd332c2bf2f794ba5745855a6bb1e" }, "downloads": -1, "filename": "sense-text-extractor-0.0.3.tar.gz", "has_sig": false, "md5_digest": "3dba2e32fa172bf537f843ad86da8bb8", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4743, "upload_time": "2019-02-25T09:24:15", "url": "https://files.pythonhosted.org/packages/a1/68/36cce1fdd65022979a5e11336f92647dd2aca83118bff4e4339ca6d38cd1/sense-text-extractor-0.0.3.tar.gz" } ], "0.0.4": [ { "comment_text": "", "digests": { "md5": "f235e088b844f087395f2d48ba4b1197", "sha256": "c1d12d02e4f3e172068d44b334657d65d9e0c4b34174d6f4604d93bf3efb7874" }, "downloads": -1, "filename": "sense_text_extractor-0.0.4-py3-none-any.whl", "has_sig": false, "md5_digest": "f235e088b844f087395f2d48ba4b1197", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 5481, "upload_time": "2019-03-15T10:24:24", "url": "https://files.pythonhosted.org/packages/11/70/03c889f80a2b91dc454884475c7da8bca34b75936a152cd94b9007ec8262/sense_text_extractor-0.0.4-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "6244c986d4a84a99c968dadd7969e93a", "sha256": "2111d5fdd20325deefbd2f84fe5d2e5b79a97e0adcd77c54d7f490aa0f5e66af" }, "downloads": -1, "filename": "sense-text-extractor-0.0.4.tar.gz", "has_sig": false, "md5_digest": "6244c986d4a84a99c968dadd7969e93a", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4777, "upload_time": "2019-03-15T10:24:26", "url": "https://files.pythonhosted.org/packages/af/3c/9ae1a792e19ed95550a0a0bc58643dc2e5f3b32d9f4c20ee1e627e0077e4/sense-text-extractor-0.0.4.tar.gz" } ], "0.0.5": [ { "comment_text": "", "digests": { "md5": "3010e1d564e6e327102c65e1e43bdcba", "sha256": "3f41eeb1319668c2451d3a96e7f3f687990d0612e6cc49d30f42ee4bdc0b0cbb" }, "downloads": -1, "filename": "sense_text_extractor-0.0.5-py3-none-any.whl", "has_sig": false, "md5_digest": "3010e1d564e6e327102c65e1e43bdcba", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 5556, "upload_time": "2019-03-15T12:38:11", "url": "https://files.pythonhosted.org/packages/b6/45/4eab1b89e332c85bffe4ce378f82e0eb5e4b21d398304a28e79c5ba0667a/sense_text_extractor-0.0.5-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "5332ec6a79bea6d04eb0b4f00108c691", "sha256": "571606f23643ec966c1018762eb4d78449b49fa02c420acbdc87bdeba602d17e" }, "downloads": -1, "filename": "sense-text-extractor-0.0.5.tar.gz", "has_sig": false, "md5_digest": "5332ec6a79bea6d04eb0b4f00108c691", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4839, "upload_time": "2019-03-15T12:38:12", "url": "https://files.pythonhosted.org/packages/62/3a/124e936e99c571a4ce17c3bddd15118804d16478d128b1884b39eec1d0eb/sense-text-extractor-0.0.5.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "3010e1d564e6e327102c65e1e43bdcba", "sha256": "3f41eeb1319668c2451d3a96e7f3f687990d0612e6cc49d30f42ee4bdc0b0cbb" }, "downloads": -1, "filename": "sense_text_extractor-0.0.5-py3-none-any.whl", "has_sig": false, "md5_digest": "3010e1d564e6e327102c65e1e43bdcba", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 5556, "upload_time": "2019-03-15T12:38:11", "url": "https://files.pythonhosted.org/packages/b6/45/4eab1b89e332c85bffe4ce378f82e0eb5e4b21d398304a28e79c5ba0667a/sense_text_extractor-0.0.5-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "5332ec6a79bea6d04eb0b4f00108c691", "sha256": "571606f23643ec966c1018762eb4d78449b49fa02c420acbdc87bdeba602d17e" }, "downloads": -1, "filename": "sense-text-extractor-0.0.5.tar.gz", "has_sig": false, "md5_digest": "5332ec6a79bea6d04eb0b4f00108c691", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4839, "upload_time": "2019-03-15T12:38:12", "url": "https://files.pythonhosted.org/packages/62/3a/124e936e99c571a4ce17c3bddd15118804d16478d128b1884b39eec1d0eb/sense-text-extractor-0.0.5.tar.gz" } ] }