Build Status codecov PyPI version GitHub license

Download and unzip full size Landsat 5, 7, and 8 (a.k.a. LT5, LE7, LC8) images via the Google service automatically using a command line interface or a simple python script. (Now you can get all Landsat [1, 2, 3, 4, 5, 7, 8]!)

Python 2.7 and 3.6 compatible.

No credentials needed.

(削除) To get the package from PyPi: (削除ここまで)

Note: This package is no longer maintained on PyPi, just use

$ pip install git+git://github.com/dgketchum/Landsat578.git

if you want install/update the package with pip.

Landsat instruments orbit the earth in sun-synchronous fashion. They pass over each place at approximately the same time of day, every 16 days. The area within each image is predefined and is described by (path,row) coordinates of the World Reference System 2 (WRS2). This system applies to all Landsat missions since LT4. Every place on Earth falls under at lease one path/row 'scene.' Some places fall within overlapping path/row scenes. Landsat 'descends' from North to South in the day, these images are of most interest to researchers, though nighttime images are also available. You can get GIS data of WRS2 here.

See WRS2 over the US state of Montana. Scene 38, 27 is highlighted in purple. Note overlap of neighboring scenes.

The first time running this code will download and package a large list of scenes. This should thereafter be updated if one is after the latest imagery. This is a large file and will need about 3GB memory available to the python process to process it.

landsat --update-scenes

If you know the path and row of a location, you can enter it in the command line interface to download and unzip images there between your specified start and end dates. You must choose a satellite. Within the package you downloaded, you need to call landsat.py. Dates are entered as YYYY-MM-DD format, e.g. 2008年05月31日.

$ landsat -sat 7 --start 2007年05月01日 --end 2007年05月31日 --path 38 --row 27 -o /path/to/folder

This command will find the two images that were captured by Landsat 5 of scene 38, 27 in the month of May, 2007 and unzip them to your folder. Use the optional parameter --return-list to just get a list of what was found:

$ landsat -sat 7 --start 2007年05月01日 --end 2007年05月31日 --path 38 --row 27 --return-list

This will return the two image scene IDs and print to your screen.

['LE70360292007122EDC00', 'LE70360292007138EDC00']

These images happen to have been taken 2007年05月02日 (Day of Year, DOY: 122), and on 2007年05月18日 (DOY 138). See NOAA's day of year calendar.

The naming conventions of Landsat images are as follows from the USGS Landsat site.

You can also download by WGS decimal degrees coordinates (i.e., latitude and longitude):

$ landsat -sat 7 --start 2007年05月01日 --end 2007年05月31日 --lat 46.5 --lon -107.5 

A negative number lat is in the southern hemisphere, a negtive lon is the western hemisphere.

This package is easy to use within a python program:

from landsat.google import GoogleDownload
g = GoogleDownload(start='2015-01-01', end='2015-12-31', sat=8, path='38', row='28', output_path='path/to/place')
g.download()

landsat -h

This command will show you all positional (mandatory) and optional arguments.