Merge pull request #42 from th3r00t/mobi

Now with mobi support!

config.json

@@ -1 +1 @@
-{"TITLE": "pyShelf E-Book Server", "VERSION": "0.5.0", "BOOKPATH": "/srv/Books", "DB_HOST": "localhost", "DB_PORT": "5432", "DATABASE": "pyshelf", "USER": "pyshelf", "PASSWORD": "pyshelf", "BOOKSHELF": "data/shelf.json", "ALLOWED_HOSTS": "*", "hostname": "localhost", "webport": "8000", "wsgiport": "8001"}
+{"TITLE": "pyShelf E-Book Server", "VERSION": "0.5.0", "BOOKPATH": "/srv/Books", "DB_HOST": "localhost", "DB_PORT": "5432", "DATABASE": "pyshelf", "USER": "pyshelf", "PASSWORD": "pyshelf", "BOOKSHELF": "data/shelf.json", "ALLOWED_HOSTS": "*", "hostname": "localhost", "webport": "8000", "wsgiport": "8001"}

importBooks

@@ -1,4 +1,4 @@
-#!python
+#!/usr/bin/env python
 
 import pathlib
 import sys

installer

@@ -1,4 +1,4 @@
-#!python
+#!/usr/bin/ env python
 import json
 import os
 import pathlib

makeCollections

@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 
 import pathlib
 import sys

pyproject.toml

@@ -7,4 +7,4 @@ use_parentheses = true
 # NOTE: the known_third_party setting is managed by
 # seed-isort-config and should not be modified directly.
 # Any changes made to this setting will be overwritten.
-known_third_party = ["backend", "bs4", "django", "interface", "prompt_toolkit", "psycopg2", "pyfiglet", "requests"]
+known_third_party = ["backend", "bs4", "django", "interface", "mobi", "prompt_toolkit", "psycopg2", "pyfiglet", "requests"]

requirements.txt

@@ -16,4 +16,5 @@ django-debug-toolbar
 psycopg2-binary
 prompt_toolkit
 psutil
-pyfiglet
+pyfiglet
+mobi-python

src/backend/lib/library.py

@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 import json
 import os
 import pathlib
@@ -7,6 +7,8 @@ import zipfile
 
 from bs4 import BeautifulSoup
 
+from mobi import Mobi
+
 from .api_hooks import DuckDuckGo
 from .config import Config
 from .storage import Storage
@@ -26,8 +28,7 @@ class Catalogue:
         self.html_regx = re.compile(r"\.html")
         self.root_dir = config.root
         self.book_folder = config.book_path
-        self.book_shelf = config.book_shelf
+        # self.book_shelf = config.book_shelf
-        self._book_list_expanded = None
         self.books = None
         self.db_pointer = config.catalogue_db
         self.config = config
@@ -56,24 +57,30 @@ class Catalogue:
 
         :returns self._book_list_expanded: json string containing all book metadata
         """
-        self.scan_folder() # Populate file list
+        self.scan_folder()  # Populate file list
-        regx = re.compile(r"\.epub")
+        regx = re.compile(r"\.epub|\.mobi")
         try:
             self.books = list(filter(regx.search, filter(None, self.file_list)))
         except TypeError as e:
             print(e)
-        self._book_list_expanded = {}
+        """
-        with open(self.book_shelf, "w") as f:
+        for book in self.books:
-            for book in self.books:
+            self._book_list_expanded[book] = self.process_by_filetype(book)
-                self._book_list_expanded[book] = self.process_book(book)
-            json.dump(self._book_list_expanded, f)
         return self._book_list_expanded
+        """
+
+    def process_by_filetype(self, book):
+        if book.endswith(".epub"):
+            epub = self.process_epub(book)
+            return self.extract_metadata_epub(epub)
+        elif book.endswith(".mobi"):
+            return self.extract_metadata_mobi(book)
 
     @staticmethod
-    def process_book(book):
+    def process_epub(book):
         """Return dictionary of epub file contents"""
-        book = zipfile.ZipFile(book, "r")
         details = {}
+        book = zipfile.ZipFile(book, "r")
         with book as book_zip:
             details["files"] = []
             details["path"] = book.filename
@@ -86,7 +93,7 @@ class Catalogue:
                     details["files"].append(match.string)
         return details
 
-    def extract_metadata(self, book):
+    def extract_metadata_epub(self, book):
         """
         Return extracted metadata and cover picture
         book['path'] == Full path to ebook file
@@ -94,7 +101,7 @@ class Catalogue:
         """
         book_zip = zipfile.ZipFile(book["path"], "r")
         with book_zip as f:
-            content = self.extract_content(book_zip, book)
+            content = self.extract_content(f, book)
             soup = BeautifulSoup(content, "lxml")
             title = soup.find("dc:title")
             if title is None:
@@ -105,13 +112,27 @@ class Catalogue:
             if author is not None:
                 author = author.contents[0]
             try:
-                cover = self.extract_cover_image(book_zip, book)
+                cover = self.extract_cover_image(f, book)
             except IndexError:
                 # cover = self.extract_cover_html(book_zip, book)
                 cover = DuckDuckGo().image_result(title)
             book_details = [title, author, cover, book["path"]]
         return book_details
 
+    @staticmethod
+    def extract_metadata_mobi(book):
+        book = Mobi(book)
+        book.parse()
+        try:
+            cover_image = book.readImageRecord(0)
+        except KeyError:
+            cover_image = None
+        title = book.title().decode("utf-8")
+        author = book.author().decode("utf-8")
+        breakpoint()
+        # TODO some files are still passing encoded data for author.
+        return [title, author, cover_image, book.f.name]
+
     def extract_content(self, book_zip, book):
         """
         Opens epub as zip file filters then stores as list any files matching opf_regx
@@ -161,12 +182,13 @@ class Catalogue:
         Gets a list of new files via compare_shelf_current.
         Iterates over list and inserts new books into database.
         """
+        # TODO Refactor metadata extraction into process_book \
+        # call to more easily handle additional formats
         book_list = self.compare_shelf_current()
         db = Storage(self.config)
         for book in book_list:
-            book = self.process_book(book)
+            book = self.process_by_filetype(book)
-            extracted = self.extract_metadata(book)
+            db.insert_book(book)
-            db.insert_book(extracted)
         inserted = db.commit()
         if inserted is not True:
             print(inserted)

src/backend/pyShelf_MakeCollections.py

@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 import os
 import sys
 import time
@@ -16,7 +16,7 @@ def MakeCollections(root):
     config = Config(root)  # Get configuration settings
     # InitFiles(config.file_array)  # Initialize file system
     _storage = Storage(config)
-    _storage.make_collections() 
+    _storage.make_collections()
     _t2 = time.time()
     scan_time = round(_t2 - _t1)
     print("Collections Made.")

src/backend/pyShelf_ScanLibrary.py

@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 import os
 import sys
 import time