udata-hydra 2.0.0.dev2438__tar.gz → 2.0.0.dev2497__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/PKG-INFO +1 -1
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/pyproject.toml +1 -1
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/crawl.py +3 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/README.md +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/__init__.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/analysis/__init__.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/analysis/csv.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/analysis/errors.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/analysis/helpers.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/analysis/resource.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/app.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/cli.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/config_default.toml +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/context.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/db/__init__.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/db/check.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/db/resource.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/logger.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/__init__.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/csv/20221205_initial_up_rev1.sql +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/csv/20230130_drop_migrations.sql +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/csv/20230206_datetime_aware.sql +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/main/20221205_initial_up_rev1.sql +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/main/20221206_rev1_up_rev2.sql +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/main/20221206_rev2_up_rev3.sql +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/main/20221208_rev3_up_rev4.sql +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/main/20221208_rev4_up_rev5.sql +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/main/20230119_rev5_up_rev6.sql +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/main/20230121_rev6_up_rev7.sql +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/main/20230121_rev7_up_rev8.sql +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/main/20230130_drop_migrations.sql +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/main/20230206_datetime_aware.sql +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/main/20230515_rev8_up_rev9.sql +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/main/20230606_rev9_up_rev10.sql +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/migrations/main/20231102_drop_csv_analysis.sql +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/routes/__init__.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/routes/checks.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/routes/resources.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/routes/status.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/schemas/__init__.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/schemas/check.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/schemas/resource.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/utils/__init__.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/utils/app_version.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/utils/csv.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/utils/file.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/utils/http.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/utils/minio.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/utils/queue.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/utils/reader.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/utils/timer.py +0 -0
- {udata_hydra-2.0.0.dev2438 → udata_hydra-2.0.0.dev2497}/udata_hydra/worker.py +0 -0
|
@@ -9,7 +9,7 @@ readme = "README.md"
|
|
|
9
9
|
|
|
10
10
|
[tool.poetry]
|
|
11
11
|
name = "udata-hydra"
|
|
12
|
-
version = "2.0.0.
|
|
12
|
+
version = "2.0.0.dev2497"
|
|
13
13
|
description = "Async crawler and parsing service for data.gouv.fr"
|
|
14
14
|
authors = ["Opendata Team <opendatateam@data.gouv.fr>"]
|
|
15
15
|
license = "MIT"
|
|
@@ -132,6 +132,9 @@ async def process_check_data(check_data: dict) -> Tuple[int, bool]:
|
|
|
132
132
|
|
|
133
133
|
|
|
134
134
|
async def is_backoff(domain: str) -> Tuple[bool, str]:
|
|
135
|
+
"""Check if we should not crawl on this domain
|
|
136
|
+
Returns a tuple with if it should backoff or not (boolean) and the reason why (string)
|
|
137
|
+
"""
|
|
135
138
|
backoff = False, ""
|
|
136
139
|
no_backoff = [f"'{d}'" for d in config.NO_BACKOFF_DOMAINS]
|
|
137
140
|
no_backoff = f"({','.join(no_backoff)})"
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|