Juridical information is important to organizations and individuals alike and is needed in all walks of life. The Finnish government has therefore published Finnish law and related juridical documents on the Web as a service called Finlex. However, even if the documents there are openly available for humans to read, the underlying data has not been open, is based on a traditional XML schema, and does not conform to new semantic metadata standards and Linked Data principles. As a result, the data is difficult to re-use in applications, the datasets are not interoperable with each other, are difficult to link to external data sources, and lots of manual work is needed in producing and using the data. To mitigate these problems, this paper presents Semantic Finlex, the first attempt at publishing Finnish law as a Linked Open Data service, with an analysis and examples of benefits and challenges encountered when applying the technology.