Script for getting images from CCAR

colorado.py

# coding: UTF-8

import os
import datetime
import mechanize
import urllib

# Set directory name.
directory_name = "images"

if not os.path.isdir(directory_name):
    os.mkdir(directory_name)

# Set dates.
start_date = datetime.date(2005, 1, 1)
end_date = datetime.date(2010, 12, 31)

current_date = start_date

while current_date <= end_date:
    
    print current_date
    
    browser = mechanize.Browser()
    browser.set_handle_robots(False)
    
    # Open web page.
    response = browser.open("http://argo.colorado.edu/~realtime/modis/")
    
    # print "=== HTML Source ==="
    # print response.read()
    
    # Check forms.
    # print "\n=== Fomrs ==="
    # for form in browser.forms():
    #     print form
    
    # Select first form.
    browser.select_form(nr=0)
    
    # Set day.
    browser["month"] = [current_date.strftime("%m")]
    browser["day1"] = [current_date.strftime("%d")[0]]
    browser["day2"] = [current_date.strftime("%d")[1]]
    browser["year"] = [current_date.strftime("%y")]
    # Set location.
    browser["alon0"] = "135"
    browser["alon1"] = "160"
    browser["alat0"] = "30"
    browser["alat1"] = "45"
    # Set options.
    browser["day_opt"] = ["7"]
    browser["cont_opt"] = ["T"]
    browser["cont_anot"] = ["T"]
    
    # Check forms.
    # print "\n=== Forms ==="
    # for form in browser.forms():
    #     print form
    
    # Submit.
    response = browser.submit()
    
    # print "=== HTML Source ==="
    # print response.read()
    
    # Check links.
    # print "\n=== Links ==="
    for link in browser.links():
        # print link
        if link.url[-4:] == ".gif":
            print link.url
            urllib.urlretrieve(link.url, directory_name + "/" + current_date.isoformat() + ".gif")
    
    current_date += datetime.timedelta(7)

print "Ended."