An Efficient Method to Extract Geographic Information

Abstract

A ton of vital geographic information about spots, including points of interest, areas and personal information such as neighborhoods, phone numbers etc. can be found on the Internet. However, such information is not openly available using legitimate means. Furthermore, the given information is temperamental as it is static and not refreshed every now and again enough. In this paper, using the results of an internet list, an effective method to manage and collect datasets of spot names is demonstrated. The strategy proposed is to use the Google web crawler Application Programming Interface in order to recoup site pages related with express territory names and types of spots and after that analyses the resultant website pages to remove addresses and names of places. Using the data gathered from internet, the final result compiled is a dataset of spot names. We survey our philosophy by using accumulated data found using street view of Google Maps by examining signs belonging to businesses found in images. The conclusion exhibited by the results was that the modelled procedure efficiently created spot datasets on par with Google Maps and defeated the results of OSM.