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

refactor: Extract pocketbook file opening method

Browse source
This commit is contained in:
Marty Oehme 2024-01-24 14:55:28 +01:00
parent 86d53a19d4
commit 6a8f8a03bc
Signed by: Marty
GPG key ID: EDBF2ED917B2EF6A
1 changed files with 14 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
papis_extract/extractors/pocketbook.py
View file

@ -23,14 +23,12 @@ class PocketBookExtractor:
Returns all readable annotations contained in the file Returns all readable annotations contained in the file
passed in, with highlights, notes and pages if available. passed in, with highlights, notes and pages if available.
""" """
annotations: list[Annotation] = [] content = self._read_file(filename)
try: if not content:
with open(filename) as f:
html = BeautifulSoup(f.read(), features="xml")
except FileNotFoundError:
logger.error(f"Could not open file {filename} for extraction.")
return [] return []
html = BeautifulSoup(content, features="xml")
annotations: list[Annotation] = []
for bm in html.select("div.bookmark"): for bm in html.select("div.bookmark"):
content = (bm.select_one("div.bm-text>p") or html.new_string("")).text content = (bm.select_one("div.bm-text>p") or html.new_string("")).text
note = (bm.select_one("div.bm-note>p") or html.new_string("")).text note = (bm.select_one("div.bm-note>p") or html.new_string("")).text
@ -58,3 +56,13 @@ class PocketBookExtractor:
f"{'annotation' if len(annotations) == 1 else 'annotations'} for {filename}." f"{'annotation' if len(annotations) == 1 else 'annotations'} for {filename}."
) )
return annotations return annotations
def _read_file(self, filename: Path) -> str:
try:
with open(filename) as f:
return f.read()
except FileNotFoundError:
logger.error(f"Could not open file {filename} for extraction.")
return ""