数据挖掘中映射数据的算法
我需要抓取一些网页并从中提取内容。我计划选择一些特定的关键字并映射与它们有某种关系的数据。但我不知道如何才能做到这一点。谁能建议我一些算法来做到这一点？
例如，我需要下载一些关于苹果的网页，并将关于苹果的相关数据映射到它并存储在数据库中，这样，如果有人需要有关它的具体信息，我可以快速准确地提供。
此外，指出有用的库也会很有帮助。我打算用 python 来做。
I need to scrape some webpages and extract content from them. I'm planning to select some specific keywords and map the data that has some relationship b/w them. But I have no Idea, how I could do that. Could anyone suggest me some algorithms for doing it?.
For example I need to download some webpages about apples and map the relevant data about apples to it and store in database so that, if someone needs specific information about it, I could provide it fastly and accurately.
Also it would be helpful pointing out helpful libraries too. I'm planning to do it in python.
如果你对这篇内容有疑问，欢迎到本站社区发帖提问 参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱，如果其他用户或者作者回复了您的评论，将不能在第一时间通知您！
发布评论
评论（2）
看看NLTK，Pattern 或 Orange 模块。
Toby Segaran 的《集体智慧编程：构建智能 Web 2.0 应用程序》是一本好书阅读。
Have a look at NLTK, Pattern or Orange modules.
As a start "Programming collective intelligence: building smart web 2. 0 applications" by Toby Segaran is a good book to read.
您可以尝试基于词频-逆文档频率的算法TF-IDF< /a>，在 Java 中我会推荐 Solr ...实际上你可以使用 Solr 并访问它与 python 参见此处
You could try algorithms based on term frequency–inverse document frequency TF-IDF, in Java I would recommend Solr ... well actually you could use Solr and access it with python see here