This commit is contained in:
esenke
2025-12-08 22:16:31 +08:00
commit 01adcfdf60
305 changed files with 50879 additions and 0 deletions

View File

@@ -0,0 +1,97 @@
import asyncio
from typing import List
import signal
import httpx
from rich.progress import TaskID, Event
from rsi_download.cli import progress
from rsi_download.download.search import SearchResult
from rsi_download.cli import Preview
import os
done_event = Event()
def handle_sigint(signum, frame):
done_event.set()
signal.signal(signal.SIGINT, handle_sigint)
async def download_tci_products_data(
task_id: TaskID, product: SearchResult, access_token: str, mm_band: str = "R10m"
):
headers = {"Authorization": f"Bearer {access_token}"}
progress.start_task(task_id)
async with httpx.AsyncClient() as client:
client.headers.update(headers)
# create the tci image url
granule_url = f"https://zipper.dataspace.copernicus.eu/odata/v1/Products({product.id})/Nodes({product.name})/Nodes(GRANULE)/Nodes"
granule_resp = await client.get(
f"{granule_url}", follow_redirects=True, headers=headers
)
granule_folder = granule_resp.json()
img_data_url = f"{granule_url}({granule_folder['result'][0]['Name']})/Nodes(IMG_DATA)/Nodes({mm_band})/Nodes"
img_data_resp = await client.get(img_data_url, follow_redirects=True)
img_data = img_data_resp.json()
tci_name = [img["Name"] for img in img_data["result"] if "TCI" in img["Name"]][
0
]
tci_url = f"{img_data_url}({tci_name})/$value"
async with client.stream(
method="GET",
url=tci_url,
headers=headers,
) as response:
progress.update(task_id, total=int(response.headers["Content-length"]))
with open(f"{tci_name}", "wb") as file:
progress.start_task(task_id)
async for chunk in response.aiter_bytes():
if chunk:
file.write(chunk)
progress.update(task_id, advance=len(chunk))
if done_event.is_set():
return
progress.console.log(f"Downloaded {tci_name}")
async def download_data(task_id: TaskID, product: SearchResult, preview: Preview, access_token: str):
headers = {"Authorization": f"Bearer {access_token}"}
async with httpx.AsyncClient() as client:
client.headers.update(headers)
async with client.stream(
"GET",
url=f"https://zipper.dataspace.copernicus.eu/odata/v1/Products({product.id})/$value",
headers=headers,
) as response:
progress.update(task_id, total=int(response.headers["Content-length"]))
with open(f"out_raw/{preview.name.replace('.SAFE', '.zip')}", "wb") as file:
progress.start_task(task_id)
async for chunk in response.aiter_bytes():
if chunk:
file.write(chunk)
progress.update(task_id, advance=len(chunk))
if done_event.is_set():
return
progress.console.log(f"Downloaded {preview.name.replace('.SAFE', '.zip')}")
async def download_products_data(
products: List[SearchResult], previews: List[Preview], access_token: str, tci_only: bool = False
):
with progress:
download_tasks = []
for product, preview in zip(products, previews):
task_id = progress.add_task(
f"{preview.name.replace('.SAFE', '.zip')}",
filename=f"{preview.name.replace('.SAFE', '.zip')}",
start=False,
)
if tci_only:
download_tasks.append(
download_tci_products_data(task_id, product, access_token)
)
else:
download_tasks.append(download_data(task_id, product, preview, access_token))
# os.rename(f"product-{product.id}.zip", f"{preview.name.replace('.SAFE', '.zip')}")
await asyncio.gather(*download_tasks)

View File

@@ -0,0 +1,78 @@
from __future__ import annotations
from typing import List
import msgspec
import httpx
from rsi_download.exceptions import SearchException
from rsi_download.geo.geo_types import GeoJsonPolygon
ESA_SEARCH_URL = r"https://catalogue.dataspace.copernicus.eu/odata/v1/Products"
class ContentData(msgspec.Struct, rename="pascal"):
"""Odata search result start and end date"""
start: str
end: str
class Asset(msgspec.Struct, rename="pascal"):
"""Odata search Asset"""
type_: str = msgspec.field(name="Type")
id: str
download_link: str
s3_path: str
class SearchResult(msgspec.Struct, rename="pascal"):
"""Odata search Result"""
id: str
name: str
content_length: int
origin_date: str
s3_path: str
content_date: ContentData
geo_footprint: GeoJsonPolygon
assets: List[Asset]
class SearchContent(msgspec.Struct):
value: List[SearchResult]
next_link: str | None = msgspec.field(default=None, name="@odata.nextLink")
async def search_odata(
long: float,
lat: float,
cloud_coverage: float,
time_lt: str,
time_gt: str,
max_: int,
platform_name: str,
) -> SearchContent:
# filter voor zoeken op cloudCover, Productype en orbitDirection.
# lt = less then
# eq = equal to
# gt = greater then
# sentinel-2
if platform_name == "S2":
search_filter = f"OData.CSC.Intersects(area=geography'SRID=4326;POINT ({long:.4f} {lat:.4f})') and Attributes/OData.CSC.DoubleAttribute/any(att:att/Name eq 'cloudCover' and att/OData.CSC.DoubleAttribute/Value lt {cloud_coverage:.2f}) and Attributes/OData.CSC.StringAttribute/any(att:att/Name eq 'productType' and att/OData.CSC.StringAttribute/Value eq 'S2MSI2A') and ContentDate/Start gt {time_gt} and ContentDate/Start lt {time_lt}"
elif platform_name == "S1":
search_filter = f"OData.CSC.Intersects(area=geography'SRID=4326;POINT ({long:.4f} {lat:.4f})') and Attributes/OData.CSC.StringAttribute/any(att:att/Name eq 'productType' and att/OData.CSC.StringAttribute/Value eq 'IW_GRDH_1S') and ContentDate/Start gt {time_gt} and ContentDate/Start lt {time_lt}"
elif platform_name == "WV3":
search_filter = f"OData.CSC.Intersects(area=geography'SRID=4326;POINT ({long:.4f} {lat:.4f})') and Attributes/OData.CSC.StringAttribute/any(att:att/Name eq 'platformName' and att/OData.CSC.StringAttribute/Value eq 'WorldView-3') and ContentDate/Start gt {time_gt} and ContentDate/Start lt {time_lt}"
else:
raise ValueError(f"Invalid platform name: {platform_name}")
async with httpx.AsyncClient() as client:
r = await client.get(
url=f"{ESA_SEARCH_URL}?$filter={search_filter}&$top={max_}&$expand=Assets",
timeout=60,
)
if not r.status_code == 200:
raise SearchException(f"Error getting data: {r.text}")
return msgspec.json.decode(r.content, type=SearchContent)