Prepare For Output--Strip non-numbers
This is a simple script used from removing all non-numerical characters from numbers. This is particularly useful when attempting to normalize data before insertion into a database.
String [] variables = {"BUILDING_YEARBUILT", "BUILDING_YEARRENOVATED", "BUILDING_TOTAL_SF", "BUILDING_STORIES", "BUILDING_ELEVATORS", "LISTING_MAX_SF", "LISTING_MIN_SF"};
i = 0;
// Iterate through each variable in the array above
while (i < variables.length){
//Get the variables to be fixed
value = session.getVariable(variables[i]);
//Log the UNFIXED values
session.log("UNFIXED: " + variables[i] + " = " + value);
if(value != null){
//Remove non-numerical elements from number
value = value.replaceAll("\\D","");
// Set variables with new values
dataRecord.put(variables[i], value);
session.setVariable(variables[i], value);
//Log the FIXED values
session.log("FIXED " + variables[i] + " = " + session.getVariable(variables[i]));
}
i++;
}
i = 0;
// Iterate through each variable in the array above
while (i < variables.length){
//Get the variables to be fixed
value = session.getVariable(variables[i]);
//Log the UNFIXED values
session.log("UNFIXED: " + variables[i] + " = " + value);
if(value != null){
//Remove non-numerical elements from number
value = value.replaceAll("\\D","");
// Set variables with new values
dataRecord.put(variables[i], value);
session.setVariable(variables[i], value);
//Log the FIXED values
session.log("FIXED " + variables[i] + " = " + session.getVariable(variables[i]));
}
i++;
}
scraper on 07/16/2010 at 4:57 pm
- Printer-friendly version
- Login or register to post comments