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

working on meta data storage

Browse Source
This commit is contained in:
Raelon Masters
2020-06-14 19:42:49 -04:00
parent 76b631a5a4
commit e3ea56c216
2 changed files with 45 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
src/backend/lib/library.py
View File

@@ -115,26 +115,37 @@ class Catalogue:
except IndexError:
# cover = self.extract_cover_html(book_zip, book)
cover = DuckDuckGo().image_result(title)
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
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 = soup.find_all("dc:subject")
except AttributeError:
tags = None
ftags = None
breakpoint()
if tags is not None:
for tag in tags:
if ftags is None:
ftags = tag
ftags = tag.text
else:
ftags = ftags+","+tag
ftags = ftags + "," + tag.text
book_details = [
title,
author,
@@ -145,14 +156,14 @@ class Catalogue:
publisher,
date,
rights,
ftags
ftags,
]
return book_details
@staticmethod
def stripTags(source):
p = re.compile(r'<.*?>')
return p.sub('', source)
p = re.compile(r"<.*?>")
return p.sub("", source)
@staticmethod
def extract_metadata_mobi(book):