th3r00t/pyShelf
1
0
Fork 0
mirror of https://github.com/th3r00t/pyShelf.git synced 2026-04-28 01:59:35 -04:00
Code Issues Packages Projects Releases Wiki Activity

Added sanitization to book title collection. Stripping patterns mathching Book 0-9*+ -

Browse Source
This commit is contained in:
Raelon Masters
2020-06-20 23:28:20 -04:00
parent 55f1dd7813
commit 13fc85f6ff
1 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/backend/lib/library.py
View File

@@ -26,6 +26,8 @@ class Catalogue:
self.opf_regx = re.compile(r"\.opf") self.opf_regx = re.compile(r"\.opf")
self.cover_regx = re.compile(r"\.jpg|\.jpeg|\.png|\.bmp|\.gif") self.cover_regx = re.compile(r"\.jpg|\.jpeg|\.png|\.bmp|\.gif")
self.html_regx = re.compile(r"\.html") self.html_regx = re.compile(r"\.html")
self.title_sanitization_regx = re.compile(r"^(Book )+[0-9]*")
self.title_sanitization_lvl2_regx = re.compile(r"^(Book )+[0-9]*\W+(-)")
self.root_dir = config.root self.root_dir = config.root
self.book_folder = config.book_path self.book_folder = config.book_path
self.books = None self.books = None
@@ -69,6 +71,7 @@ class Catalogue:
""" """
def process_by_filetype(self, book): def process_by_filetype(self, book):
print(str(book), end='\r', flush=True)
if book.endswith(".epub"): if book.endswith(".epub"):
epub = self.process_epub(book) epub = self.process_epub(book)
return self.extract_metadata_epub(epub) return self.extract_metadata_epub(epub)
@@ -107,6 +110,12 @@ class Catalogue:
title = book["path"].split("/")[-1].rsplit(".", 1)[0] title = book["path"].split("/")[-1].rsplit(".", 1)[0]
else: else:
title = title.contents[0] title = title.contents[0]
if re.match(self.title_sanitization_regx, title):
breakpoint()
if re.match(self.title_sanitization_lvl2_regx, title):
title = re.split(r"-+\W", title)[1]
else: title = re.split(self.title_sanitization_regx, title)[2]
author = soup.find("dc:creator") author = soup.find("dc:creator")
if author is not None: if author is not None:
author = author.contents[0] author = author.contents[0]