Marty/papis-extract
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

chore: Format files with ruff

Browse source
This commit is contained in:
Marty Oehme 2025-09-11 10:53:50 +02:00
parent a854ef00d6
commit 96cd4929c9
Signed by: Marty
GPG key ID: 4E535BC19C61886E
8 changed files with 29 additions and 41 deletions
Download patch file Download diff file Expand all files Collapse all files

3
papis_extract/extractors/__init__.py
View file

@ -3,9 +3,8 @@ from importlib.util import find_spec
import papis.logging
from papis_extract.extraction import Extractor
from papis_extract.extractors import pdf
from papis_extract.extractors import pdf, readera
from papis_extract.extractors.pocketbook import PocketBookExtractor
from papis_extract.extractors import readera
logger = papis.logging.get_logger(__name__)

4
papis_extract/extractors/pdf.py
View file

@ -32,9 +32,7 @@ class PdfExtractor:
annotations: list[Annotation] = []
try:
with mu.Document(filename) as doc:
for (
page
) in doc: # pyright: ignore [reportUnknownVariableType] - missing stub
for page in doc: # pyright: ignore [reportUnknownVariableType] - missing stub
annot: mu.Annot
for annot in page.annots():
quote, note = self._retrieve_annotation_content(page, annot)

9
papis_extract/extractors/pocketbook.py
View file

@ -44,16 +44,13 @@ class PocketBookExtractor:
annotations: list[Annotation] = []
for bm in html.select("div.bookmark"):
content = str(
(bm.select_one("div.bm-text>p") or html.new_string("")).text
or "" # pyright: ignore [reportUnknownArgumentType]
(bm.select_one("div.bm-text>p") or html.new_string("")).text or "" # pyright: ignore [reportUnknownArgumentType]
)
note = str(
(bm.select_one("div.bm-note>p") or html.new_string("")).text
or "" # pyright: ignore [reportUnknownArgumentType]
(bm.select_one("div.bm-note>p") or html.new_string("")).text or "" # pyright: ignore [reportUnknownArgumentType]
)
page = int(
(bm.select_one("p.bm-page") or html.new_string("")).text
or 0 # pyright: ignore [reportUnknownArgumentType]
(bm.select_one("p.bm-page") or html.new_string("")).text or 0 # pyright: ignore [reportUnknownArgumentType]
)
el_classes = bm.attrs.get("class", "").split(" ")