make dumping details async

crawler/2_dump_detail.py

@@ -1,35 +1,39 @@
+import asyncio
 import json
 import pathlib
 from rec.query import detail_query
-from tqdm import tqdm
+from tqdm.asyncio import tqdm
 
 from data_access import Listing
 
 
-def dump_detail(listing_paths: list[str]):
-    incremental = True
+async def dump_detail(listing_paths: list[str]):
     listings = Listing.get_all_listings(listing_paths)
-    filtered_listings = []
-    for listing in listings:
-        # We introduced last_seen later, so not all entries have it.
-        # If it doesnt exist then its on the platform anymore. So skip
-        last_seen = listing.last_seen
-        if last_seen is None:
-            continue
+    filtered_listings = await tqdm.gather(
+        *[_dump_detail_for_listing(listing) for listing in listings]
+    )
+    return filtered_listings
 
-        if not incremental and last_seen <= 1:
-            filtered_listings.append(listing)
 
-        if incremental and not listing.path_detail_json().exists():
-            filtered_listings.append(listing)
+async def _dump_detail_for_listing(listing: Listing):
+    incremental = True
+    # We introduced last_seen later, so not all entries have it.
+    # If it doesnt exist then its on the platform anymore. So skip
+    last_seen = listing.last_seen
+    if last_seen is None:
+        return
 
-    for listing in tqdm(filtered_listings):
-        try:
-            d = detail_query(listing.identifier)
-            with open(listing.path_detail_json(), "w") as f:
-                json.dump(d, f)
-        except Exception as e:
-            print(e)
+    if not incremental and last_seen <= 1:
+        return
+
+    if incremental and not listing.path_detail_json().exists():
+        return
+    print('fetching', listing.identifier)
+
+    # for listing in tqdm(filtered_listings):
+    d = await detail_query(listing.identifier)
+    with open(listing.path_detail_json(), "w") as f:
+        json.dump(d, f)
 
 
 def main():

crawler/main.py

@@ -117,7 +117,7 @@ def dump_details(ctx: click.core.Context):
     data_dir = ctx.obj['data_dir']
     click.echo(f'Running dump_detail for listings stored in {data_dir}')
     listing_paths = sorted(list(pathlib.Path(data_dir).glob("*/listing.json")))
-    dump_detail_module.dump_detail(listing_paths)
+    asyncio.run(dump_detail_module.dump_detail(listing_paths))
 
 
 @cli.command()

crawler/rec/query.py

@@ -30,7 +30,7 @@ class PropertyType(enum.StrEnum):
     TERRACED = "terraced"
 
 
-def detail_query(detail_id: int):
+async def detail_query(detail_id: int):
     params = {
         "apiApplication": "ANDROID",
         "appVersion": "3.70.0",