Skip to content
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

🔥 Removal of cc indexes arg #87

Merged
merged 4 commits into from
Nov 20, 2023
Merged

🔥 Removal of cc indexes arg #87

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
826f886
🔥 removal of cc indexes
hynky1999 Oct 24, 2023
1589601
Merge branch 'main' into cc_indexes_server_arg
hynky1999 Nov 19, 2023
d531146
fix
hynky1999 Nov 19, 2023
eda7acb
Merge branch 'main' into cc_indexes_server_arg
hynky1999 Nov 20, 2023
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
7 changes: 2 additions & 5 deletions cmoncrawl/aggregator/athena_query.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@
crawl_url_to_name,
prepare_athena_sql_query,
)
from cmoncrawl.aggregator.utils.constants import CC_INDEXES_SERVER
from cmoncrawl.aggregator.utils.helpers import (
get_all_CC_indexes,
remove_bucket_prefix,
Expand Down Expand Up @@ -79,7 +80,6 @@ class AthenaAggregator(IAggregator):
def __init__(
self,
urls: List[str],
cc_indexes_server: str = "http://index.commoncrawl.org/collinfo.json",
match_type: MatchType = MatchType.EXACT,
cc_servers: Optional[List[str]] = None,
since: datetime = datetime.min,
Expand All @@ -97,7 +97,6 @@ def __init__(
table_name: str = "ccindex",
) -> None:
self.urls = urls
self.cc_indexes_server = cc_indexes_server
self.match_type = match_type
self.cc_servers = cc_servers
self.since = since
Expand Down Expand Up @@ -143,9 +142,7 @@ async def aopen(self) -> AthenaAggregator:
)
async with ClientSession() as client:
if not self.cc_servers:
self.cc_servers = await get_all_CC_indexes(
client, self.cc_indexes_server
)
self.cc_servers = await get_all_CC_indexes(client, CC_INDEXES_SERVER)
# create bucket if not exists
async with self.aws_client.client("s3") as s3:
# Check if bucket exists
Expand Down
7 changes: 2 additions & 5 deletions cmoncrawl/aggregator/gateway_query.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@
)

from cmoncrawl.aggregator.base import IAggregator
from cmoncrawl.aggregator.utils.constants import CC_INDEXES_SERVER
from cmoncrawl.aggregator.utils.helpers import (
crawl_to_year,
get_all_CC_indexes,
Expand Down Expand Up @@ -67,7 +68,6 @@ class GatewayAggregator(IAggregator):
def __init__(
self,
urls: List[str],
cc_indexes_server: str = "http://index.commoncrawl.org/collinfo.json",
match_type: MatchType = MatchType.EXACT,
cc_servers: Optional[List[str]] = None,
since: datetime = datetime.min,
Expand All @@ -79,7 +79,6 @@ def __init__(
max_requests_per_second: int = 20,
) -> None:
self.urls = urls
self.cc_indexes_server = cc_indexes_server
self.cc_servers = cc_servers
self.since = since
self.to = to
Expand All @@ -96,9 +95,7 @@ async def aopen(self) -> GatewayAggregator:
await self.client.__aenter__()

if not self.cc_servers:
self.cc_servers = await get_all_CC_indexes(
self.client, self.cc_indexes_server
)
self.cc_servers = await get_all_CC_indexes(self.client, CC_INDEXES_SERVER)
return self

async def __aenter__(self) -> GatewayAggregator:
Expand Down
1 change: 1 addition & 0 deletions cmoncrawl/aggregator/utils/constants.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
CC_INDEXES_SERVER = "https://index.commoncrawl.org/collinfo.json"
3 changes: 2 additions & 1 deletion tests/gateway_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@
MatchType,
)
from cmoncrawl.aggregator.gateway_query import GatewayAggregator
from cmoncrawl.aggregator.utils.constants import CC_INDEXES_SERVER
from cmoncrawl.aggregator.utils.helpers import get_all_CC_indexes, unify_url_id


Expand Down Expand Up @@ -38,7 +39,7 @@ async def test_indexer_num_pages(self):
self.assertEqual(num_pages, 14)

async def test_indexer_all_CC(self):
indexes = await get_all_CC_indexes(self.client, self.di.cc_indexes_server)
indexes = await get_all_CC_indexes(self.client, CC_INDEXES_SERVER)
indexes = sorted(indexes)
indexes = indexes[
: indexes.index("https://index.commoncrawl.org/CC-MAIN-2022-27-index") + 1
Expand Down
Loading