parser/__init__.py

@@ -10,7 +10,6 @@ from .lenenergo import LenenergoParser
 from .preprocess import (
     COL_NS,
     ICOL_NS,
-    PR_COL_NS,
     group_by_index,
     preprocess_df,
     preprocess_read_df,
@@ -21,7 +20,6 @@ __all__ = (
     "async_fetch_building_id",
     "async_fetch_building_ids",
     "COL_NS",
-    "PR_COL_NS",
     "concurrent_fetch_builing_ids",
     "fetch_builing_ids",
     "get_building_id",

parser/building_id.py

@@ -45,10 +45,7 @@ async def async_fetch_building_id(
     async with session.get(
         "https://geocode.gate.petersburg.ru/parse/eas", params={"street": street}
     ) as r:
-        try:
+        res = await r.json()
-            res = await r.json()
-        except aiohttp.client_exceptions.ContentTypeError:
-            res = "error"
 
         if "error" in res:
             return None, None, None

parser/preprocess.py

@@ -21,23 +21,6 @@ COL_NS = {
     "lng": "Долгота",
 }
 
-PR_COL_NS = (
-    "index",
-    "region",
-    "area",
-    "town",
-    "street",
-    "branch",
-    "res",
-    "comment",
-    "building_id",
-    "lat",
-    "lng",
-    "start",
-    "finish",
-)
-
-
 ICOL_NS = dict(map(reversed, COL_NS.items()))
 
 

runner/__main__.py

@@ -1,17 +1,11 @@
 import schedule
 
-from .config import REFETCH_PERIOD_H, STORE_NULL_BID
+from .config import REFETCH_PERIOD_H
 from .job import job
 from .scheduler import run_continuously
 
 schedule.every(REFETCH_PERIOD_H).hours.do(job)
 stop_run_continuously = run_continuously()
 
-print(
-    f"Scheduled to run every {REFETCH_PERIOD_H} hour and "
-    + ("" if STORE_NULL_BID else "not ")
-    + "to store NULL building_id"
-)
-
 # First run
 job()

runner/config.py

@@ -1,9 +1,6 @@
 import os
 
-from parser import PR_COL_NS
-
 REFETCH_PERIOD_H = int(os.environ.get("REFETCH_PERIOD_H", "4"))
-STORE_NULL_BID = os.environ.get("STORE_NULL_BID", "False") == "True"
 
 POSTGRES_USER = os.environ.get("POSTGRES_USER", "lenenergo")
 POSTGRES_PASSWORD = os.environ.get("POSTGRES_PASSWORD", "lenenergo")
@@ -12,9 +9,3 @@ POSTGRES_HOST = os.environ.get("POSTGRES_HOST", "localhost")
 POSTGRES_PORT = int(os.environ.get("POSTGRES_PORT", "5432"))
 
 DB_URL = os.environ.get("DB_URL", None)
-
-DB_COLUMNS_MAP = dict(zip(PR_COL_NS, PR_COL_NS))
-"""
-Feel free to rewrite mapping like 
-DB_COLUMNS_MAP["<COL_NS key>"] = "<corresponding db column name>"
-"""

runner/job.py

@@ -4,13 +4,23 @@ from parser import pipeline
 import pandas as pd
 import psycopg
 
-from .config import DB_COLUMNS_MAP, STORE_NULL_BID
 from .database import db_credentials
 
-
+sql_statement = """COPY records (
-sql_statement = "".join(
+    index,
-    ("COPY records (", ", ".join(DB_COLUMNS_MAP.values()), ") FROM STDIN")
+    region,
-)
+    area,
+    town,
+    street,
+    branch,
+    res,
+    comment,
+    building_id,
+    lat,
+    lng,
+    start,
+    finish
+) FROM STDIN"""
 
 
 def job():
@@ -26,8 +36,6 @@ def job():
             with cursor.copy(sql_statement) as copy:
                 for _, row in parser.df.iterrows():
                     row = row.where((pd.notnull(row)), None)
-                    if row["building_id"] is not None or STORE_NULL_BID:
+                    copy.write_row(row.to_list())
-                        db_row = row.rename(DB_COLUMNS_MAP)
-                        copy.write_row(db_row.to_list())
 
     print(f"Fetched in {datetime.now() - fetch_start}\n{parser}")