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

Now acquiring more book details

Browse Source
This commit is contained in:
Raelon Masters
2020-06-13 23:36:03 -04:00
parent 7d39d1534a
commit 76b631a5a4
1 changed files with 25 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
src/backend/lib/library.py
View File

@@ -115,13 +115,26 @@ class Catalogue:
except IndexError:
# cover = self.extract_cover_html(book_zip, book)
cover = DuckDuckGo().image_result(title)
description = soup.find("dc:description")
identifier = soup.find("dc:identifier")
publisher = soup.find("dc:identifier")
date = soup.find("dc:date")
rights = soup.find("dc:rights")
tags = soup.find_all("dc:subject")
try: description = self.stripTags(soup.find("dc:description").text)
except AttributeError: description = None
try: identifier = self.stripTags(soup.find("dc:identifier").text)
except AttributeError: identifier = None
try: publisher = self.stripTags(soup.find("dc:publisher").text)
except AttributeError: publisher = None
try: date = self.stripTags(soup.find("dc:date").text)
except AttributeError: date = None
try: rights = self.stripTags(soup.find("dc:rights").text)
except AttributeError: rights = None
try: tags = self.stripTags(soup.find_all("dc:subject").text)
except AttributeError: tags = None
ftags = None
breakpoint()
if tags is not None:
for tag in tags:
if ftags is None:
ftags = tag
else:
ftags = ftags+","+tag
book_details = [
title,
author,
@@ -132,10 +145,15 @@ class Catalogue:
publisher,
date,
rights,
tags
ftags
]
return book_details
@staticmethod
def stripTags(source):
p = re.compile(r'<.*?>')
return p.sub('', source)
@staticmethod
def extract_metadata_mobi(book):
book = Mobi(book)