US Forest Service Research Image Library Scraper

scraper.py

import requests

output_dir = "/Volumes/KCHAU'S T5/US Forest Service Research Image Library/"

url_base = 'https://www.fs.usda.gov/rds/imagedb/images/'

# 19677 = total number of images in data base
file_number = 19677

while file_number > 0:
    filename = str(file_number) + '.jpg'
    r = requests.get(url_base + filename)
    if r.status_code != 404:
        img_data = r.content
        with open(output_dir+filename, 'wb') as handler:
            handler.write(img_data)
    file_number -= 1