starred/shelfmark
1
0
Fork 0
mirror of https://github.com/calibrain/shelfmark.git synced 2026-09-24 13:40:21 +01:00
Code Issues Packages Projects Releases 10 Wiki Activity

Improve book metadata handling in book_manager.py (#313)

Browse Source 
Refactor book metadata extraction and add helper function.
Fix #300 and #307
This commit is contained in:
CaliBrain
2025-11-15 03:42:40 -05:00
committed by GitHub
parent 6aed906dfe
commit 03321a5435
1 changed files with 19 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
book_manager.py
+19 -11
View File
@@ -227,15 +227,9 @@ def _parse_book_info_page(soup: BeautifulSoup, book_id: str) -> BookInfo:
# Filter out divs that are not text
original_divs = divs
divs = [div.text.strip() for div in divs if div.text.strip() != ""]
divs = [div for div in divs if div.text.strip() != ""]
separator_index = 6
for i, div in enumerate(divs):
if "·" in div.strip():
separator_index = i
break
_details = divs[separator_index].lower().split(" · ")
_details = _find_in_divs(divs, " · ").split(" · ")
format = ""
size = ""
for f in _details:
@@ -252,15 +246,15 @@ def _parse_book_info_page(soup: BeautifulSoup, book_id: str) -> BookInfo:
size = f.strip().lower()
book_title = divs[separator_index-3].strip("🔍")
book_title = _find_in_divs(divs, "🔍").strip("🔍").strip()
# Extract basic information
book_info = BookInfo(
id=book_id,
preview=preview,
title=book_title,
publisher=divs[separator_index-1],
author=divs[separator_index-2],
publisher=_find_in_divs(divs, "icon-[mdi--company]", isClass=True),
author=_find_in_divs(divs, "icon-[mdi--user-edit]", isClass=True),
format=format,
size=size,
download_urls=urls,
@@ -276,8 +270,22 @@ def _parse_book_info_page(soup: BeautifulSoup, book_id: str) -> BookInfo:
if info.get("Year"):
book_info.year = info["Year"][0]
# TODO :
# Backfill missing metadata from original book
# To do this, we need to cache the results of search_books() in some kind of LRU
return book_info
def _find_in_divs(divs: List[str], text: str, isClass: bool = False) -> str:
for div in divs:
if isClass:
if div.find(class_ = text):
return div.text.strip()
else:
if text in div.text.strip():
return div.text.strip()
return ""
def _get_download_urls_from_welib(book_id: str) -> set[str]:
if ALLOW_USE_WELIB == False:
return set()