Created
September 5, 2019 16:23
-
-
Save ptpt/b106fee8253b4c78c148e7a57192f159 to your computer and use it in GitHub Desktop.
A command line tool used to download Mapillary data via Mapillary API v3
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
"""A command line tool used to download Mapillary data via Mapillary API v3 https://www.mapillary.com/developer/api-documentation/. | |
This tool fetches data and prints them line by line (http://ndjson.org/), and it handles pagination automatically. | |
Usage: | |
mapillary_download.py URL [HEADER...] | |
Examples: | |
Download map images in the United States: | |
mapillary_download.py "https://a.mapillary.com/v3/images?iso_countries=US&per_page=10000&client_id=YOUR_CLIENT" | |
Download image detections in a bounding box: | |
mapillary_download.py "https://a.mapillary.com/v3/map_features?layers=segmentations&bbox=13,13,14,14&client_id=YOUR_CLIENT" "Authorization: Bearer AUTH_TOKEN" | |
""" | |
from __future__ import print_function | |
import sys | |
import json | |
import logging | |
import requests | |
LOG = logging.getLogger() | |
handler = logging.StreamHandler(sys.stderr) | |
handler.setLevel(logging.INFO) | |
handler.setFormatter(logging.Formatter('%(asctime)s - %(levelname)-6s - %(message)s')) | |
LOG.addHandler(handler) | |
LOG.setLevel(logging.INFO) | |
def iteratorize(body): | |
if isinstance(body, list): | |
for b in body: | |
yield b | |
elif isinstance(body, dict): | |
features = body.get('features') | |
if isinstance(features, list) and body.get('type') == 'FeatureCollection': | |
for f in features: | |
yield f | |
else: | |
yield body | |
else: | |
yield body | |
def stringify_response(resp): | |
lines = [] | |
lines.append('{0} {1}'.format(resp.status_code, resp.reason)) | |
ctype = resp.headers.get('content-type') | |
lines.append('Content-Type: {0}'.format(ctype)) | |
lines.append(resp.text) | |
return '\n'.join(lines) | |
def download(url, headers=None): | |
""" | |
Fetch and iterate responses by sending the initial url request. | |
""" | |
if headers is None: | |
headers = {} | |
headers.setdefault('accept', 'application/json') | |
while True: | |
LOG.info('GET %s', url) | |
resp = requests.get(url, headers=headers, allow_redirects=True) | |
if 200 <= resp.status_code < 300: | |
try: | |
body = resp.json() | |
except json.JSONDecodeError as err: | |
LOG.error('Error JSON parsing response: %s', stringify_response(resp)) | |
raise err | |
for item in iteratorize(body): | |
yield item | |
next_link = resp.links.get('next') | |
if next_link is None: | |
break | |
url = next_link['url'] | |
elif 500 < resp.status_code: | |
LOG.warning('Retrying on response: %s', stringify_response(resp)) | |
else: | |
LOG.error('Error response: %s', stringify_response(resp)) | |
resp.raise_for_status() | |
if __name__ == '__main__': | |
if len(sys.argv) < 2: | |
print('usage: mapillary_download URL [HEADER...]', file=sys.stderr) | |
sys.exit(1) | |
url = sys.argv[1] | |
# parse headers | |
headers = {} | |
for pair in sys.argv[1:]: | |
try: | |
header, value = pair.split(':', 1) | |
except ValueError: | |
print('Invalid header {0}'.format(pair), file=sys.stderr) | |
sys.exit(1) | |
header = header.strip() | |
value = value.strip() | |
headers[header.lower()] = value | |
count = 0 | |
for item in download(url, headers=headers): | |
print(json.dumps(item)) | |
count += 1 | |
logging.info('Got %s items', count) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Got it working with a change here using: https://a.mapillary.com/v3/image_detections?layers=segmentations