run ruff

src/extractor/extractors/media.py

@@ -88,7 +88,7 @@ def load_media(path: Path, link_registry: LinkRegistry) -> Optional[pd.DataFrame
 
     media_df = media_df[media_df.columns.intersection(EXPORT_COLUMNS)]
 
-    media_df = media_df.rename(columns=RENAME_COLUMNS, errors='ignore')
+    media_df = media_df.rename(columns=RENAME_COLUMNS, errors="ignore")
 
     link_registry.add_linkables(
         "media", media_df["source_url"].to_list(), media_df.index.to_list()

src/extractor/extractors/pages.py

@@ -78,7 +78,7 @@ def load_pages(path: Path, link_registry: LinkRegistry) -> Optional[pd.DataFrame
     )
 
     pages_df = pages_df[pages_df.columns.intersection(EXPORT_COLUMNS)]
-    pages_df = pages_df.rename(columns=RENAME_COLUMNS, errors='ignore')
+    pages_df = pages_df.rename(columns=RENAME_COLUMNS, errors="ignore")
 
     link_registry.add_linkables(
         "pages", pages_df["link"].to_list(), pages_df.index.to_list()

src/extractor/extractors/posts.py

@@ -123,7 +123,7 @@ def load_posts(
     )
 
     posts_df = posts_df[posts_df.columns.intersection(EXPORT_COLUMNS)]
-    posts_df = posts_df.rename(columns=RENAME_COLUMNS, errors='ignore')
+    posts_df = posts_df.rename(columns=RENAME_COLUMNS, errors="ignore")
 
     return posts_df
 

tests/extractors/test_posts.py

@@ -1,4 +1,3 @@
-import json
 from datetime import datetime
 from pathlib import Path
 
@@ -15,9 +14,8 @@
 )
 from extractor.parse.translations._resolver import TranslationLink
 from helpers.df import ordered_col
-from pytest_mock import MockerFixture
-
 from helpers.file import json_without_cols
+from pytest_mock import MockerFixture
 
 
 def mock_translation_extractor(post_bs: BeautifulSoup, link: str, translation_pickers):
@@ -202,8 +200,9 @@ def test_resolves_media(posts_df_and_registry):
         idx=1,
     )
 
+
 def test_no_yoast_columns(datadir, scrape_urls_files):
-    path = json_without_cols(datadir / "posts.json", {'yoast_head', 'yoast_head_json'})
+    path = json_without_cols(datadir / "posts.json", {"yoast_head", "yoast_head_json"})
 
     posts_df = load_posts(path, LinkRegistry(), scrape_urls_files, None)
-    assert posts_df.iloc[0].og_image_url is None
+    assert posts_df.iloc[0].og_image_url is None

tests/extractors/test_users.py

@@ -13,7 +13,8 @@ def test_user_load(datadir, users_df):
     expected_df = pd.read_json(datadir / "users_df_out.json", orient="table")
     assert users_df.equals(expected_df)
 
+
 def test_no_yoast_columns(datadir):
-    path = json_without_cols(datadir / "users.json", {'yoast_head', 'yoast_head_json'})
+    path = json_without_cols(datadir / "users.json", {"yoast_head", "yoast_head_json"})
     users_df = load_users(path)
-    assert users_df.iloc[0].avatar is None
+    assert users_df.iloc[0].avatar is None

tests/helpers/file.py

@@ -1,15 +1,19 @@
 import json
-from pathlib import Path
-from typing import List, Set
 import tempfile
+from pathlib import Path
+from typing import Set
+
 
 def json_without_cols(in_file: Path, del_cols: Set[str]) -> Path:
     in_data = json.loads(in_file.read_text())
-    delete_keys = {'yoast_head', 'yoast_head_json'}
-    out_data = [{key: item[key] for key, value in item.items() if key not in delete_keys} for item in in_data]
+    delete_keys = {"yoast_head", "yoast_head_json"}
+    out_data = [
+        {key: item[key] for key, value in item.items() if key not in delete_keys}
+        for item in in_data
+    ]
 
-    with tempfile.NamedTemporaryFile(mode='w+', delete=False) as f:
+    with tempfile.NamedTemporaryFile(mode="w+", delete=False) as f:
         json.dump(out_data, f)
         path = f.name
 
-    return Path(path)
+    return Path(path)