pytesseract.pytesseract.tesseract_cmd = r\"C:\\Program Files\\Tesseract-OCR\\tesseract.exe\"\r\n<\/code><\/pre>\nAdjust the path if you installed Tesseract in a different location.<\/p>\n
5. (Optional) Create a requirements.txt<\/h5>\n
To install all packages at once, you can create a requirements.txt<\/code> file with the following content:<\/p>\npytesseract\r\nPillow\r\nfpdf\r\npython-docx\r\n<\/code><\/pre>\nThen run:<\/p>\n
pip install -r requirements.txt\r\n<\/code><\/pre>\nNow your Python environment is fully ready to build the project and extract text from images easily!<\/p>\n
Project Overview: Extract the text From an image to pdf and word file<\/h3>\n
This simple Python application allows users to:<\/p>\n
\n- Select an image (formats: PNG, JPG, BMP, TIFF)<\/li>\n
- Extract text using OCR<\/li>\n
- View extracted text in a scrollable text box<\/li>\n
- Save extracted text as a Word (.docx) file<\/li>\n
- Save extracted text as a PDF (.pdf) file<\/li>\n<\/ol>\n
How It Works<\/h4>\n1. Selecting an Image<\/h5>\n
Click the “Select Image” button to open a file dialog where you can choose an image file. The application supports PNG, JPG, BMP, and TIFF formats.<\/p>\n
2. Extracting Text<\/h5>\n
After selecting an image, click “Extract Text”. The app uses Tesseract OCR to scan the image and retrieve all readable text, which is displayed inside a scrollable text widget.<\/p>\n
3. Saving as Word or PDF<\/h5>\n
Once the text is extracted, you can choose to save it as a Word document or a PDF file. The application ensures Unicode font support for multi-language text.<\/p>\n
Key Code Snippets<\/h4>\n
\nSelecting an Image File<\/h5>\nfilepath = filedialog.askopenfilename(\r\n filetypes=[(\"Image Files\", \"*.png *.jpg *.jpeg *.bmp *.tiff\")]\r\n)<\/code><\/pre>\nExtracting Text Using pytesseract<\/h5>\nimg = Image.open(image_path)\r\ntext = pytesseract.image_to_string(img)<\/code><\/pre>\nSaving Text as a Word Document<\/h5>\ndoc = Document()\r\ndoc.add_paragraph(text)\r\ndoc.save(filepath)<\/code><\/pre>\nSaving Text as a PDF Document<\/h5>\npdf = FPDF()\r\npdf.add_page()\r\npdf.add_font('DejaVu', '', font_path, uni=True)\r\npdf.set_font('DejaVu', '', 12)\r\nfor line in text.split('\\n'):\r\n pdf.multi_cell(0, 10, line)\r\npdf.output(filepath)<\/code><\/pre>\nBenefits of Automating Text Extraction<\/h5>\n\n- Saves time compared to manual typing<\/li>\n
- Improves data entry accuracy<\/li>\n
- Streamlines document management<\/li>\n
- Boosts productivity for businesses and individuals<\/li>\n<\/ul>\n
\nComplete Code extract-text.py<\/h3>\nimport tkinter as tk\r\nfrom tkinter import filedialog, messagebox, ttk\r\nfrom tkinter.scrolledtext import ScrolledText\r\nfrom PIL import Image\r\nimport pytesseract\r\nfrom docx import Document\r\nfrom fpdf import FPDF\r\nimport os\r\nimport threading\r\n\r\n# Set path to tesseract.exe\r\npytesseract.pytesseract.tesseract_cmd = r\"C:\\Program Files\\Tesseract-OCR\\tesseract.exe\" # Adjust if needed\r\n\r\ndef select_image():\r\n filepath = filedialog.askopenfilename(\r\n title=\"Select an image file\",\r\n filetypes=[(\"Image Files\", \"*.png *.jpg *.jpeg *.bmp *.tiff\")]\r\n )\r\n if filepath:\r\n entry_file.delete(0, tk.END)\r\n entry_file.insert(0, filepath)\r\n\r\ndef extract_text_threaded():\r\n threading.Thread(target=extract_text).start()\r\n\r\ndef extract_text():\r\n image_path = entry_file.get()\r\n if not os.path.exists(image_path):\r\n messagebox.showerror(\"Error\", \"Image file does not exist!\")\r\n return\r\n\r\n try:\r\n progress_bar.place(relx=0.5, rely=0.5, anchor=\"center\") # Centered inside text box\r\n progress_bar.start()\r\n\r\n img = Image.open(image_path)\r\n text = pytesseract.image_to_string(img)\r\n\r\n if not text.strip():\r\n messagebox.showinfo(\"No Text\", \"No text detected in the image.\")\r\n return\r\n\r\n text_box.config(state=tk.NORMAL)\r\n text_box.delete(1.0, tk.END)\r\n text_box.insert(tk.END, text)\r\n text_box.config(state=tk.NORMAL)\r\n\r\n except Exception as e:\r\n messagebox.showerror(\"Error\", str(e))\r\n finally:\r\n progress_bar.stop()\r\n progress_bar.place_forget() # Hide progress bar\r\n\r\ndef save_as_word():\r\n text = text_box.get(1.0, tk.END).strip()\r\n if not text:\r\n messagebox.showwarning(\"Warning\", \"No text to save!\")\r\n return\r\n\r\n filepath = filedialog.asksaveasfilename(\r\n defaultextension=\".docx\",\r\n filetypes=[(\"Word Document\", \"*.docx\")]\r\n )\r\n if filepath:\r\n try:\r\n doc = Document()\r\n doc.add_paragraph(text)\r\n doc.save(filepath)\r\n messagebox.showinfo(\"Saved\", f\"Text saved as Word file:\\n{filepath}\")\r\n except Exception as e:\r\n messagebox.showerror(\"Error\", str(e))\r\n\r\ndef save_as_pdf():\r\n text = text_box.get(1.0, tk.END).strip()\r\n if not text:\r\n messagebox.showwarning(\"Warning\", \"No text to save!\")\r\n return\r\n\r\n filepath = filedialog.asksaveasfilename(\r\n defaultextension=\".pdf\",\r\n filetypes=[(\"PDF file\", \"*.pdf\")]\r\n )\r\n if filepath:\r\n try:\r\n pdf = FPDF()\r\n pdf.add_page()\r\n \r\n # Add a Unicode font (DejaVuSans.ttf must be in the same folder)\r\n font_path = os.path.join(os.path.dirname(__file__), r\"D:\\Python\\extract-text\\DejavuSans.ttf\")\r\n pdf.add_font('DejaVu', '', font_path, uni=True)\r\n pdf.set_font('DejaVu', '', 12)\r\n \r\n for line in text.split('\\n'):\r\n pdf.multi_cell(0, 10, line)\r\n\r\n pdf.output(filepath)\r\n messagebox.showinfo(\"Saved\", f\"Text saved as PDF file:\\n{filepath}\")\r\n except Exception as e:\r\n messagebox.showerror(\"Error\", str(e))\r\n\r\n\r\n# Helper function to get correct path for icon\r\ndef resource_path(relative_path):\r\n try:\r\n # PyInstaller creates a temp folder and stores path in _MEIPASS\r\n base_path = sys._MEIPASS\r\n except Exception:\r\n base_path = os.path.abspath(\".\")\r\n return os.path.join(base_path, relative_path)\r\n\r\n# --- GUI ---\r\nroot = tk.Tk()\r\nroot.title(\"Image to Text Extractor\")\r\nroot.minsize(400, 600) # Minimum window size\r\n\r\nframe = tk.Frame(root, padx=10, pady=10)\r\nframe.pack(fill=tk.BOTH, expand=True)\r\n\r\n# Widgets\r\nbtn_select = tk.Button(frame, text=\"Select Image\", command=select_image)\r\nentry_file = tk.Entry(frame, width=50)\r\nbtn_extract = tk.Button(frame, text=\"Extract Text\", command=extract_text_threaded)\r\n\r\ntext_frame = tk.Frame(frame)\r\ntext_box = ScrolledText(text_frame, width=80, height=20, wrap=tk.WORD)\r\n\r\nprogress_bar = ttk.Progressbar(text_frame, orient=tk.HORIZONTAL, mode='indeterminate', length=200)\r\nprogress_bar.place_forget()\r\n\r\nbtn_save_word = tk.Button(frame, text=\"Save as Word\", command=save_as_word)\r\nbtn_save_pdf = tk.Button(frame, text=\"Save as PDF\", command=save_as_pdf)\r\n\r\n# Layout function (dynamic)\r\ndef layout_widgets(event=None):\r\n width = root.winfo_width()\r\n\r\n # Clear old layout\r\n for widget in frame.winfo_children():\r\n widget.grid_forget()\r\n widget.pack_forget()\r\n\r\n if width < 500: # Mobile Layout\r\n btn_select.pack(pady=5, fill=tk.X)\r\n entry_file.pack(pady=5, fill=tk.X)\r\n btn_extract.pack(pady=5, fill=tk.X)\r\n\r\n text_frame.pack(pady=10, fill=tk.BOTH, expand=True)\r\n text_box.pack(fill=tk.BOTH, expand=True)\r\n\r\n btn_save_word.pack(pady=5, fill=tk.X)\r\n btn_save_pdf.pack(pady=5, fill=tk.X)\r\n\r\n else: # Desktop Layout\r\n btn_select.grid(row=0, column=0, padx=5, pady=5)\r\n entry_file.grid(row=0, column=1, padx=5, pady=5, sticky=\"ew\")\r\n btn_extract.grid(row=0, column=2, padx=5, pady=5)\r\n\r\n frame.grid_columnconfigure(1, weight=1)\r\n\r\n text_frame.grid(row=1, column=0, columnspan=3, pady=10, sticky=\"nsew\")\r\n text_box.pack(fill=tk.BOTH, expand=True)\r\n\r\n btn_save_word.grid(row=2, column=0, pady=5)\r\n btn_save_pdf.grid(row=2, column=2, pady=5)\r\n\r\n # Make sure frame expands correctly\r\n frame.pack(fill=tk.BOTH, expand=True)\r\n\r\n# Bind resize event\r\nroot.bind(\"\", layout_widgets)\r\n\r\n# Initialize layout\r\nlayout_widgets()\r\n\r\nroot.mainloop()\r\n<\/code><\/pre>\n
\n