Skip to content

GCS fetch: add discovery num_retries and query rate_delay #142

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
TimidRobot merged 2 commits into from
Nov 27, 2024
Merged

GCS fetch: add discovery num_retries and query rate_delay #142

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
08bf541
add discovery num_retries and query rate_delay
TimidRobot Nov 27, 2024
6a5e557
avoid double period
TimidRobot Nov 27, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 12 additions & 12 deletions scripts/1-fetch/gcs_fetch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@
import time
import traceback
import urllib.parse
from copy import copy

# Third-party
import googleapiclient.discovery
Expand All @@ -34,14 +35,14 @@
load_dotenv(PATHS["dotenv"])

# Constants
DEVELOPER_KEY = os.getenv("GCS_DEVELOPER_KEY")
CX = os.getenv("GCS_CX")
BASE_URL = "https://www.googleapis.com/customsearch/v1"
FILE1_COUNT = os.path.join(PATHS["data_phase"], "gcs_1_count.csv")
FILE2_LANGUAGE = os.path.join(
PATHS["data_phase"], "gcs_2_count_by_language.csv"
)
FILE3_COUNTRY = os.path.join(PATHS["data_phase"], "gcs_3_count_by_country.csv")
GCS_CX = os.getenv("GCS_CX")
GCS_DEVELOPER_KEY = os.getenv("GCS_DEVELOPER_KEY")
HEADER1_COUNT = ["PLAN_INDEX", "TOOL_IDENTIFIER", "COUNT"]
HEADER2_LANGUAGE = ["PLAN_INDEX", "TOOL_IDENTIFIER", "LANGUAGE", "COUNT"]
HEADER3_COUNTRY = ["PLAN_INDEX", "TOOL_IDENTIFIER", "COUNTRY", "COUNT"]
Expand Down Expand Up @@ -87,7 +88,11 @@ def get_search_service():
"""
LOGGER.info("Getting Google Custom Search API Service.")
return googleapiclient.discovery.build(
"customsearch", "v1", developerKey=DEVELOPER_KEY, cache_discovery=False
"customsearch",
"v1",
developerKey=GCS_DEVELOPER_KEY,
cache_discovery=False,
num_retries=5,
)


Expand Down Expand Up @@ -184,21 +189,15 @@ def query_gcs(args, service, last_completed_plan_index, plan):

max_tries = 5
initial_delay = 1 # in seconds
rate_delay = copy(initial_delay) # query gently
start = last_completed_plan_index + 1
stop = start + args.limit

for plan_row in plan[start:stop]: # noqa: E203
index = plan.index(plan_row)
query_info = f"index: {index}, tool: {plan_row['TOOL_IDENTIFIER']}"
encoded_tool_url = urllib.parse.quote(plan_row["TOOL_URL"], safe=":/")
query_params = {
"cx": CX,
# "num": records_per_query,
# "start": start_index,
# "cr": cr,
# "lr": lr,
"q": encoded_tool_url,
}
query_params = {"cx": GCS_CX, "q": encoded_tool_url}
if plan_row["COUNTRY"]:
query_info = f"{query_info}, country: {plan_row['COUNTRY']}"
query_params["cr"] = plan_row["CR"]
Expand All @@ -222,6 +221,7 @@ def query_gcs(args, service, last_completed_plan_index, plan):
results.get("searchInformation", {}).get("totalResults", 0)
)
success = True
time.sleep(rate_delay)
break # no need to try again

except HttpError as e:
Expand All @@ -230,7 +230,7 @@ def query_gcs(args, service, last_completed_plan_index, plan):
"Quota exceeded" in e.reason
and "Queries per day" in e.reason
):
LOGGER.warning(f"{e.status_code}: {e.reason}.")
LOGGER.warning(f"{e.status_code}: {e.reason}")
return # abort queries
else:
LOGGER.warning(
Expand Down