feature: metadata information from pdf

README.md

@@ -17,7 +17,6 @@
 </p>
 <p align="center">
 <a href="https://discord.gg/JfbK3bS"><img src="https://img.shields.io/discord/758030555005714512.svg?label=Discord&logo=Discord&colorB=7289da&style=for-the-badge" alt="discord invite"></a>
-<img src="https://img.shields.io/github/pipenv/locked/dependency-version/py-contributors/audiobook/pyttsx3?style=for-the-badge" alt="pyttsx3">
 <a href="https://api.github.com/repos/py-contributors/audiobook/contributors"><img src="https://img.shields.io/github/contributors/py-contributors/audiobook?style=for-the-badge" alt="total contributors"></a>
 </p>
 

audiobook/__init__.py

@@ -1 +1 @@
-from audiobook.main import AudioBook
+from audiobook.main import AudioBook

audiobook/main.py

@@ -1,28 +1,25 @@
 
 import os
-from tqdm import tqdm
 import pyttsx3
 import logging
-logger = logging.getLogger("PyPDF2")
-logger.setLevel(logging.INFO)
+from tqdm import tqdm
 
-from audiobook.utils import response_to_text
 from audiobook.utils import speak_text
-from audiobook.utils import text_preprocessing
 from audiobook.utils import load_json
 from audiobook.utils import write_json_file
 
 from audiobook.utils import pdf_to_json
 from audiobook.utils import txt_to_json
 from audiobook.utils import mobi_to_json
-from audiobook.utils import docs_to_json
 from audiobook.utils import epub_to_json
 from audiobook.utils import html_to_json
 
 
 from audiobook.config import speed_dict
 from audiobook.config import supported_file_types
 
+logger = logging.getLogger("PyPDF2")
+logger.setLevel(logging.INFO)
 
 expand_usr = os.path.expanduser("~")
 BOOK_DIR = os.path.join(expand_usr, "audiobook/library")
@@ -44,7 +41,7 @@ class AudioBook:
         save_json_to_audio: save .mp3 audios from a json file in a folder
         save_book_audio: saves audio files in folder
         read_book: reads the book
-        
+
     sample usage:
         ab = AudioBook(speed="normal")
         ab.read_book(file_path, password="abcd")
@@ -62,63 +59,66 @@ def get_library(self):
             return "You have no books in your library"
         print("You Have total {} books in your library".format(len(total_books)))
         return total_books
-    
+
     def create_json_book(self, input_book_path, password=None):
         """ method to create json book from input file
             it calls respective method based on file format """
         json_filename = os.path.basename(input_book_path).split(".")[0] + ".json"
-        
+
         if os.path.exists(os.path.join(BOOK_DIR, json_filename)):
+            metadata = {}
             print("Book already exists in library, reading from library")
             json_book = load_json(os.path.join(BOOK_DIR, json_filename))
-            pages = len(json_book)
-            return json_book, pages
-        
+            metadata["pages"] = len(json_book)
+            return json_book, metadata
+
         elif input_book_path.endswith(".pdf"):
-            json_book, pages = pdf_to_json(input_book_path, password)
+            json_book, metadata = pdf_to_json(input_book_path, password)
         elif input_book_path.endswith(".txt"):
-            json_book, pages = txt_to_json(input_book_path)
+            json_book, metadata = txt_to_json(input_book_path)
         elif input_book_path.endswith(".epub"):
-            json_book, pages = epub_to_json(input_book_path)
-        elif input_book_path.endswith(".mobi"):
-            json_book, pages = mobi_to_json(input_book_path)
+            json_book, metadata = epub_to_json(input_book_path)
+        elif metadata.endswith(".mobi"):
+            json_book, metadata = mobi_to_json(input_book_path)
         elif input_book_path.startswith("http"):
-            json_book, pages = html_to_json(input_book_path)
-        
+            json_book, metadata = html_to_json(input_book_path)
+
         write_json_file(json_book, os.path.join(BOOK_DIR, json_filename))
 
-        return json_book, pages
+        return json_book, metadata
 
     def save_audio(self, input_book_path, password=None, save_page_wise=False):
         """ method to save audio files in folder """
-        json_book, _ = self.create_json_book(input_book_path, password)
-        
-        book_name = os.path.basename(input_book_path).split(".")[0]
+        json_book, metadata = self.create_json_book(input_book_path, password)
+
+        book_name = metadata['book_name']
         os.makedirs(book_name, exist_ok=True)
-        
+
         print('Saving audio files in folder: {}'.format(book_name))
-        
+
         if save_page_wise:
             for page_num, text in tqdm(json_book.items()):
-                self.engine.save_to_file(text, os.path.join(book_name, 
-                                                            book_name + 
-                                                            "_page_" + 
-                                                            (str(page_num)) + 
+                self.engine.save_to_file(text, os.path.join(book_name,
+                                                            book_name +
+                                                            "_page_" +
+                                                            (str(page_num)) +
                                                             ".mp3"))
                 self.engine.runAndWait()
 
         elif not save_page_wise:
             all_text = " ".join([text for text in json_book.values()])
             self.engine.save_to_file(all_text, os.path.join(book_name, book_name + ".mp3"))
             self.engine.runAndWait()
-            
+
     def read_book(self, input_book_path, password=None):
-        """ method to read the book 
-        
+        """ method to read the book
+
         input_book_path: filepath, url path or book name
         """
-        json_book, pages = self.create_json_book(input_book_path, password)
-
+        json_book, metadata = self.create_json_book(input_book_path, password)
+
+        pages = metadata["pages"]
+
         speak_text(self.engine, f"The book has total {str(pages)} pages!")
         speak_text(self.engine, "Please enter the page number: ", display=False)
         start_page = int(input("Please enter the page number: ")) - 1

audiobook/utils.py

@@ -1,10 +1,12 @@
-from bs4 import BeautifulSoup
 import re
+import os
+import mobi
 import json
 import PyPDF2
 import ebooklib
 from ebooklib import epub
-import mobi
+from bs4 import BeautifulSoup
+
 
 import html2text
 regex = re.compile(r'[\n\r\t]')
@@ -21,94 +23,126 @@ def write_json_file(json_data, filename):
 
 def text_preprocessing(input_text):
     """ function to preprocess text """
-    preprocessed_text = regex.sub("", input_text) 
+    preprocessed_text = regex.sub("", input_text)
     preprocessed_text = re.sub(' +', ' ', preprocessed_text)
     return preprocessed_text
-
+
+def response_to_text(chapter):
+    """ fuction to convert response to text
+
+        required for epub files
+        maybe required for html files
+    """
+    soup = BeautifulSoup(chapter, 'html.parser')
+    extracted_text = [para.get_text() for para in soup.find_all('p')]
+    extracted_text = ' '.join(extracted_text)
+    preprocessed_text = text_preprocessing(extracted_text)
+    return preprocessed_text
+
+def speak_text(engine, text, display=True):
+    """ function to speak text and display it """
+    if display:
+        print(text)
+    engine.say(text)
+    engine.runAndWait()
+
+def mobi_to_json(input_book_path):
+    """ sub method to create json book from mobi file """
+    metadata = {}
+    json_book = {}
+    book_name = os.path.basename(input_book_path).split(".")[0]
+    tempdir, filepath = mobi.extract(input_book_path)
+    with open(filepath, "r", encoding='utf-8') as fp:
+        content = fp.read()
+    book_data = html2text.html2text(content)
+    book_data = text_preprocessing(book_data)
+
+    for i in range(0, len(book_data), 2000):
+        page_num = i // 2000
+        json_book[str(page_num)] = book_data[i:i + 2000]
+
+    metadata["pages"] = len(json_book)
+    metadata["book_name"] = book_name
+    return json_book, metadata
+
 def pdf_to_json(input_book_path, password=None):
     """ sub method to create json book from pdf file"""
+    metadata = {}
     json_book = {}
+    book_name = os.path.basename(input_book_path).split(".")[0]
     with open(input_book_path, "rb") as fp:
         pdfReader = PyPDF2.PdfFileReader(fp)
         if pdfReader.isEncrypted:
             pdfReader.decrypt(password)
+
+        information = pdfReader.getDocumentInfo()
+
+        metadata["author"] = information.author
+        metadata["creator"] = information.creator
+        metadata["producer"] = information.producer
+        metadata["subject"] = information.subject
+        metadata["title"] = information.title
+        metadata["pages"] = pdfReader.numPages
+        metadata["book_name"] = book_name
+
         pages = pdfReader.numPages
         for page_num in range(0, pages):
             pageObj = pdfReader.getPage(page_num)
             extracted_text = pageObj.extractText()
             json_book[str(page_num)] = extracted_text
-    return json_book, pages
+
+    return json_book, metadata
 
 def txt_to_json(input_book_path):
     """ sub method to create json book from txt file """
     json_book = {}
+    metadata = {}
+    book_name = os.path.basename(input_book_path).split(".")[0]
     with open(input_book_path, "r") as fp:
         file_txt_data = fp.read()
     file_txt_data = text_preprocessing(file_txt_data)
+
     for i in range(0, len(file_txt_data), 2000):
         page_num = i // 2000
         json_book[str(page_num)] = file_txt_data[i:i + 2000]
-    return json_book, len(json_book)     
+
+    metadata["pages"] = len(json_book)
+    metadata["book_name"] = book_name
+    return json_book, metadata
 
 
 def docs_to_json(input_book_path):
     """ sub method to create json book from docs file """
     pass
 
 def epub_to_json(input_book_path):
+    metadata = {}
     json_book = {}
+    book_name = os.path.basename(input_book_path).split(".")[0]
     book = epub.read_epub(input_book_path)
     text = " ".join([response_to_text(chapter.get_body_content()) for chapter in book.get_items_of_type(ebooklib.ITEM_DOCUMENT)])
     for i in range(1, len(text) + 1, 2000):
         page_num = i // 2000
         json_book[str(page_num)] = text[i:i + 2000]
 
-    return json_book, len(json_book)
+    metadata["pages"] = len(json_book)
+    metadata["book_name"] = book_name
+    return json_book, metadata
 
 def html_to_json(url):
     """ method to create json book from web article """
+    metadata = {}
     json_book = {}
+    book_name = os.path.basename(url).split(".")[0]
     article_scraper = ArticleWebScraper(url)
     page_data = article_scraper.get_page_data()
     page_data = text_preprocessing(page_data)
     for i in range(0, len(page_data), 2000):
         page_num = i // 2000
         json_book[str(page_num)] = page_data[i:i + 2000]
 
-    return json_book, len(json_book)   
-
-def response_to_text(chapter):
-    """ fuction to convert response to text
-
-        required for epub files
-        maybe required for html files
-    """
-    soup = BeautifulSoup(chapter, 'html.parser')
-    extracted_text = [para.get_text() for para in soup.find_all('p')]
-    extracted_text = ' '.join(extracted_text)
-    preprocessed_text = text_preprocessing(extracted_text)
-    return preprocessed_text
-
+    metadata["pages"] = len(json_book)
+    metadata["book_name"] = book_name
+    return json_book, metadata
 
-def speak_text(engine, text, display=True):
-    """ function to speak text and display it """
-    if display:
-        print(text)
-    engine.say(text)
-    engine.runAndWait()
-
-
-def mobi_to_json(input_book_path):
-    """ sub method to create json book from mobi file """
-    json_book = {}
-    tempdir, filepath = mobi.extract(input_book_path)
-    with open(filepath, "r", encoding='utf-8') as fp:
-        content = fp.read()
-    book_data = html2text.html2text(content)
-    book_data = text_preprocessing(book_data)
-
-    for i in range(0, len(book_data), 2000):
-        page_num = i // 2000
-        json_book[str(page_num)] = book_data[i:i + 2000]
 
-    return json_book, len(json_book)