Merge pull request #27 from sat-utils/develop

publish 0.2.1

CHANGELOG.md

@@ -10,6 +10,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 
 ### Changed
 - Updated metadata fields for STAC 0.9.0-rc2
+- Update boto3-utils to 0.2.0
 
 ### Fixed
 - Point to correct github tag when linking to STAC collection metadata
@@ -39,4 +40,4 @@ Initial Release
 [Unreleased]: https://github.com/sat-utils/sat-stac-sentinel/compare/0.1.0...HEAD
 [v0.2.1]: https://github.com/sat-utils/sat-stac-sentinel/compare/0.2.0...0.2.1
 [v0.2.0]: https://github.com/sat-utils/sat-stac-sentinel/compare/0.1.0...0.2.0
-[v0.1.0]: https://github.com/sat-utils/sat-stac-sentinel/tree/0.1.0
+[v0.1.0]: https://github.com/sat-utils/sat-stac-sentinel/tree/0.1.0

requirements.txt

@@ -1,5 +1,6 @@
 pyproj==2.4.1
 shapely~=1.6.4.post2
-boto3-utils~=0.1.3
+boto3-utils~=0.2.0
+#git+git://github.com/matthewhanson/boto3-utils@develop
 xmljson~=0.2.0
 requests>=2.18.1

stac_sentinel/cli.py

@@ -29,6 +29,7 @@ def parse_args(args):
     parser.add_argument('--prefix', help='Only ingest scenes with a path starting with prefix', default=None)
     parser.add_argument('--start_date', help='Only ingest scenes with a Last Modified Date past provided start date', default=None)
     parser.add_argument('--end_date', help='Only ingest scenes with a Last Modified Date before provided end date', default=None)
+    parser.add_argument('--direct_from_s3', help='Get metadata direct from s3 instead of free endpoint', default=False, action='store_true')
 
     # output control
     parser.add_argument('--save', help='Save fetch Items as <id>.json files to this folder', default=None)
@@ -48,16 +49,15 @@ def cli():
     args = parse_args(sys.argv[1:])
     logging.basicConfig(stream=sys.stdout,
                         level=args.pop('log') * 10,
-                        datefmt='%Y-%m-%d %H:%M:%S')
+                        format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
 
     publish = args.pop('publish', None)
 
     collection_id = args.pop('collection')
     savepath = args.pop('save')
     if savepath is not None:
         makedirs(savepath, exist_ok=True)
-    for i, item in enumerate(SentinelSTAC.get_aws_archive(collection_id, **args)):
-        print(item['properties']['datetime'], item['id'])
+    for item in SentinelSTAC.get_aws_archive(collection_id, **args):
         # save items as JSON files
         if savepath:
             fname = op.join(savepath, '%s.json' % item['id'])

stac_sentinel/sentinel-s2-l1c.json

@@ -51,7 +51,7 @@
     "properties": {
         "constellation": "sentinel-2",
         "instruments": ["msi"],
-        "gsd": 10,
+        "eo:gsd": 10,
         "eo:bands": [
             {
                 "name": "B01",

stac_sentinel/sentinel-s2-l2a.json

@@ -51,7 +51,7 @@
     "properties": {
         "constellation": "sentinel-2",
         "instruments": ["msi"],
-        "gsd": 10,
+        "eo:gsd": 10,
         "eo:bands": [
             {
                 "name": "B01",

stac_sentinel/sentinel.py

@@ -106,7 +106,7 @@ def kml_to_geometry(cls, filename):
         return cls.coordinates_to_geometry(coordinates)
 
     @classmethod
-    def get_aws_archive(cls, collection, **kwargs):
+    def get_aws_archive(cls, collection, direct_from_s3=False, **kwargs):
         """ Generator function returning the archive of Sentinel data on AWS
         Keyword arguments:
         prefix -- Process only files keys begining with this prefix
@@ -120,16 +120,25 @@ def get_aws_archive(cls, collection, **kwargs):
         # get latest AWS inventory for this collection
         inventory_url = 's3://sentinel-inventory/%s/%s-inventory' % (collection, collection)
         inventory = s3().latest_inventory(inventory_url, **kwargs, suffix=cls.collections[collection])
-
+        #import pdb; pdb.set_trace()
         # iterate through latest inventory
-        for i, record in enumerate(inventory):
-            url = '%s/%s/%s' % (cls.FREE_URL, collection, record['Key'])
-            logger.debug('Fetching initial metadata: %s' % url)
+        from datetime import datetime
+        for i, url in enumerate(inventory):
+            if (i % 100) == 0:
+                logger.info('%s records' % i)
+
             try:
-                # get initial JSON file file
-                r = requests.get(url, stream=True)
-                base_url = 's3://%s/%s' % (record['Bucket'], op.dirname(record['Key']))  
-                metadata = json.loads(r.text)
+                if direct_from_s3:
+                    logger.debug('Fetching initial metadata: %s' % url)
+                    metadata = s3().read_json(url, requester_pays=True)
+                else:
+                    # use free endpoint to access file
+                    parts = s3().urlparse(url)
+                    _url = '%s/%s/%s' % (cls.FREE_URL, collection, parts['key'])                
+                    logger.debug('Fetching initial metadata: %s' % _url)
+                    r = requests.get(_url, stream=True)
+                    metadata = json.loads(r.text)
+
                 '''
                 fnames = [f"{base_url}/{a}" for a in md['filenameMap'].values() if 'annotation' in a and 'calibration' not in a]
                 metadata = {
@@ -140,11 +149,11 @@ def get_aws_archive(cls, collection, **kwargs):
                 '''                  
                 # transform to STAC Item
                 sentinel_scene = cls(collection, metadata)
-                item = sentinel_scene.to_stac(base_url=base_url)
+                item = sentinel_scene.to_stac(base_url=url)
                 yield item
 
             except Exception as err:
-                logger.error('Error creating STAC Item %s: %s' % (record['url'], err))
+                logger.error('Error creating STAC Item from %s, Error: %s' % (url, err))
                 continue
 
     def to_stac_from_s1l1c(self, **kwargs):