downloading all *.gpx route files from the Canterbury Tramping Club website

gistfile1.py

# commands to get the links (bash)
# $ wget -c -r --no-parent -k -U Mozilla http://www.ctc.org.nz/
# $ find ./www.ctc.org.nz/ -name "*gpx*" > gpxfiles.txt 
# gpxfiles.txt has the numbers used in the script below

import re
import os
import requests

numberlist = [6,92,32,86,4,28,27,103,75,46,90,91,1,10,35,97,20,72,52,69,9,12,96,22,40,102,78,14,82,99,83,84,51,58,42,79,55,26,81,53,76,39,56,3,80,45,77,94,60,47,33,95,36,48,2,50,24,25,71,88,16,89,23,11,98,49,31,18,57,13,19,43,61,44,54,74,37,93,7,85,59,104,100,73,8,30,101,41,34,17,38,70,29,21,15,5,87]

for number in numberlist:

  url = "http://www.ctc.org.nz/dbgpx.php?id=%s" % (number)

  r = requests.get(url)

  print r.headers

  filename = re.findall("filename=\"(.+)\"", r.headers['content-disposition'])
  directory = os.getcwd()

  with open("%s/%s" % (directory, filename[0]), "wb") as some_file:
      some_file.write(r.content)