Understanding and extracting spatial information from text is vital for a wide range of applications, including geographic information systems (GIS), smart cities, disaster prevention, and logistics planning. This capability empowers decision-makers to gain crucial insights into geographic distributions and trends.However, the inherent complexity of geographic expressions in natural language presents significant hurdles for traditional extraction methods. These challenges stem from variations in place names, vague directional cues, and implicit spatial relationships.To address these challenges, we introduce SpatialWebAgent, an automated agent system that leverages large language models (LLMs). SpatialWebAgent is designed to extract, standardize, and ground spatial information from natural language text directly onto maps. Our system excels at handling the diverse and often ambiguous nature of geographic expressions—from varying place names and vague directions to implicit spatial relationships that demand flexible combinations of localization functions—by tapping into the powerful geospatial reasoning capabilities of LLMs. SpatialWebAgent employs a series of specialized tools to convert this extracted information into precise coordinates, which are then visualized on interactive maps.A demonstration of SpatialWebAgent is available at https://sites.google.com/view/SpatialWebAgent.