support: PdfMinor support adding

README.md

@@ -36,6 +36,11 @@ sh setup.sh
 pip install audiobook
 ```
 
+## Usages
+
+The audiobook is a python module for listening to your favourite PDF book.
+
+
 ```python
 from audiobook import AudioBook
 # argument: Speech-Speed="slow/normal/fast", volume = 0.0 to 1.0
@@ -48,16 +53,25 @@ ab.save_audio(self, input_book_path, password=None, save_page_wise=False):
 - input_book_path: path to pdf file
 - password: password to pdf file
 - save_page_wise: if True, saves each page as a separate mp3 file
+- extraction_engine: "pypdf2/pdfminor" for extracting text from pdf file
 
 ab.read_book(file_path) # listen to the book
 ab.create_json_book(file_path) # create json file of the book
 
 ab.get_library() # get all the books in your library
 ```
 
-## Usages
+## Supported File Formats
 
-The audiobook is a python module for listening to your favourite PDF book.
+| File Format | Supported | Engine |
+| :--- | :---: | :---: |
+| PDF | :white_check_mark: | pypdf2/pdfminor |
+| TXT | :white_check_mark: |  not required  |
+| EPUB | :white_check_mark: | not required  |
+| MOBI | :white_check_mark: | not required  |
+| HTML | :white_check_mark: | not required  |
+| DOCX | :white_check_mark: | not required  |
+| ODT | :x: | not required  |
 
 ## Test
 
@@ -93,12 +107,17 @@ This project is currently in development. Any contributions are welcome.
 
 ## Changelog
 
+**V2.0.2**
+- [x] Docs files support added
+- [x] Pdfminor as engine added 
+
 **V2.0.1**
 
 - [x] Mobi file support
 - [x] Epub file support
 - [x] User can now save the audiobook for future
 - [x] User library added    
+- [
 
 **V2.0.0**
 

audiobook/doc_parser/pdf_parser.py

@@ -0,0 +1,74 @@
+import io
+
+import PyPDF2
+
+from pdfminer.pdfinterp import PDFResourceManager
+from pdfminer.pdfinterp import PDFPageInterpreter
+from pdfminer.converter import TextConverter
+from pdfminer.layout import LAParams
+from pdfminer.pdfpage import PDFPage
+
+
+class PdfMinerDocParser(object):
+    """
+
+    PdfMinor Doc Parser:
+        1. get_metadata : get metadata of pdf file
+        2. get_text : convert pdf to text
+        3. get_toc : get table of contents if available
+
+    """
+    def __init__(self):
+        self.laparams = LAParams(char_margin=1, line_margin=0.5, all_texts=True)
+
+    def get_metadata(self):
+        pass
+
+    def get_text(self, filepath, password=None, maxpages=0, caching=True):
+        """ function to read all the text from pdf file """
+        pagenos = set()
+        rsrcmgr = PDFResourceManager()
+        retstr = io.StringIO()
+
+        device = TextConverter(rsrcmgr, retstr, laparams=self.laparams)
+
+        with open(filepath, 'rb') as fp:
+            interpreter = PDFPageInterpreter(rsrcmgr, device)
+
+            for page in PDFPage.get_pages(fp=fp, pagenos=pagenos, maxpages=maxpages, password=password, caching=caching):
+                interpreter.process_page(page)
+
+            pdf_data = retstr.getvalue()
+            return pdf_data
+
+
+class PyPDF2DocParser(object):
+    """
+    PyPdf2 Doc Parser:
+
+    methods:
+        1. get_metadata : get metadata of pdf file
+        2. get_text : convert pdf to text
+        3. get_toc : get table of contents if available
+
+    """
+    def __init__(self):
+        pass
+
+    def get_metadata(self):
+        pass
+
+    def get_text(self, filepath, password=None, maxpages=0):
+        """ function to read all the text from pdf file """
+        pdf_data = ""
+        with open(filepath, "rb") as fp:
+            pdfReader = PyPDF2.PdfFileReader(fp)
+            if password:
+                pdfReader.decrypt(password)
+            num_pages = pdfReader.numPages
+            if maxpages:
+                num_pages = min(num_pages, maxpages)
+            for i in range(num_pages):
+                pageObj = pdfReader.getPage(i)
+                pdf_data += pageObj.extractText()  # BUG: Page 1Page 2Page 3Page 4Page 5
+        return pdf_data

audiobook/main.py

@@ -62,7 +62,7 @@ def get_library(self):
         )
         return total_books
 
-    def create_json_book(self, input_book_path, password=None):
+    def create_json_book(self, input_book_path, password=None, extraction_engine=None):
         """method to create json book from input file
         it calls respective method based on file format"""
         json_filename = (
@@ -77,7 +77,7 @@ def create_json_book(self, input_book_path, password=None):
             return json_book, metadata
 
         elif input_book_path.endswith(".pdf"):
-            json_book, metadata = pdf_to_json(input_book_path, password)
+            json_book, metadata = pdf_to_json(input_book_path, password, extraction_engine=extraction_engine)
         elif input_book_path.endswith(".txt"):
             json_book, metadata = txt_to_json(input_book_path)
         elif input_book_path.endswith(".epub"):
@@ -93,9 +93,10 @@ def create_json_book(self, input_book_path, password=None):
 
         return json_book, metadata
 
-    def save_audio(self, input_book_path, password=None, save_page_wise=False):
+    def save_audio(self, input_book_path, password=None, save_page_wise=False, extraction_engine=None):
         """method to save audio files in folder"""
-        json_book, metadata = self.create_json_book(input_book_path, password)
+
+        json_book, metadata = self.create_json_book(input_book_path, password, extraction_engine)
 
         book_name = metadata["book_name"]
         os.makedirs(book_name, exist_ok=True)
@@ -120,12 +121,12 @@ def save_audio(self, input_book_path, password=None, save_page_wise=False):
             )
             self.engine.runAndWait()
 
-    def read_book(self, input_book_path, password=None):
+    def read_book(self, input_book_path, password=None, extraction_engine=None):
         """method to read the book
 
         input_book_path: filepath, url path or book name
         """
-        json_book, metadata = self.create_json_book(input_book_path, password)
+        json_book, metadata = self.create_json_book(input_book_path, password, extraction_engine)
 
         pages = metadata["pages"]
 
@@ -154,6 +155,7 @@ def read_book(self, input_book_path, password=None):
             "3. Type 'n' to read next page\n "
             "4. Type 'q' to quit:\n "
             "5. Type page number to read that page:\n"
+
             user_input = input(input_message)
             if user_input == "r":
                 speak_text(self.engine, f"Reading page {str(start_page+1)}")

audiobook/utils.py

@@ -6,13 +6,12 @@
 import ebooklib
 import html2text
 import mobi
-import PyPDF2
 from bs4 import BeautifulSoup
 from ebooklib import epub
 
-from audiobook.article_web_scraper import ArticleWebScraper
-
-regex = re.compile(r"[\n\r\t]")
+from audiobook.doc_parser.web_parser import ArticleWebScraper
+from audiobook.doc_parser.pdf_parser import PyPDF2DocParser
+from audiobook.doc_parser.pdf_parser import PdfMinerDocParser
 
 
 def load_json(filename):
@@ -27,6 +26,7 @@ def write_json_file(json_data, filename):
 
 def text_preprocessing(input_text):
     """function to preprocess text"""
+    regex = re.compile(r"[\n\r\t]")
     preprocessed_text = regex.sub("", input_text)
     preprocessed_text = re.sub(" +", " ", preprocessed_text)
     return preprocessed_text
@@ -73,32 +73,28 @@ def mobi_to_json(input_book_path):
     return json_book, metadata
 
 
-def pdf_to_json(input_book_path, password=None):
+def pdf_to_json(input_book_path, password=None, extraction_engine="pypdf2"):
     """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
 
+    if extraction_engine == "pdfminer":
+        print("Using pdfminer")
+        pdf_parser = PdfMinerDocParser()
+    elif extraction_engine == "pypdf2":
+        print("Using pypdf2")
+        pdf_parser = PyPDF2DocParser()
+    else:
+        raise NotImplementedError("Only pdfminer and pypdf2 are supported")
+
+    text = pdf_parser.get_text(input_book_path, password=password)
+    text = text_preprocessing(text)
+
+    for i in range(0, len(text), 2000):
+        page_num = i // 2000
+        json_book[str(page_num)] = text[i: i + 2000]
+
+    metadata = len(json_book)
     return json_book, metadata