The Global Biodiversity Information Facility (GBIF) is an online database of occurrence information for species across the world. It contains museum records, and occurrence records from individuals.
This database can be accessed using R and then exported into an excel or .csv file for further analyses.
A quick 'how to':
# Requires the package 'dismo'
# Collect all occurrences for the Long-toed salamander (Ambystoma macrodactylum), even those that may be listed as a subspecies
> AMMA<-gbif("ambystoma", "macrodactylum*", geo=TRUE)
ambystoma macrodactylum* : 2739 occurrences found
# the * indicates that all species with the name "macrodactylum" be included. For example, Ambystoma macrodactylum croceum
# "geo=TRUE" means you want only the data with latitude and longitude information
# Unfortunately this includes NAS, so you have to subset the data to remove any NAs in the latitude and longitude columns
> AMMA<-subset(AMMA, !is.na(lon) & !is.na(lat))
# Now plot the latitude and longitude to look for any obvious outliers
> plot(AMMA$lon, AMMA$lat)
# Given that this species exists only in the Western US, it's odd to have a data point somewhere east of -100 degrees Longitude (in the Midwestern US), so I'm going to remove that data point
> AMMA<-subset(AMMA, AMMA[,8] < -100)
# This command subsets the data and keeps everything less than -100 (or west of -100). "[,8]" Denotes the 8th column, or the Longitude column.
# Export the dataset into an excel file by first converting it to a data frame (otherwise there will be no column structure)
> write.csv(AMMAdata, file="AMMAdata.csv")