Spaces:
Build error
Build error
| import streamlit as st | |
| from PIL import Image | |
| import pytesseract | |
| import requests | |
| # Set the path to Tesseract-OCR engine on your system | |
| pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe' | |
| # Function to extract text from the image using Tesseract | |
| def extract_text_from_image(image): | |
| text = pytesseract.image_to_string(image, lang='eng+hin') | |
| return text | |
| # Function to highlight the keyword in yellow and bold in the extracted text | |
| def highlight_text(text, keyword): | |
| # Split text into lines to highlight keywords in their respective lines | |
| lines = text.splitlines() | |
| highlighted_lines = [] | |
| for line in lines: | |
| highlighted_line = line.replace(keyword, f"<span style='background-color: yellow; font-weight: bold;'>{keyword}</span>") | |
| highlighted_lines.append(highlighted_line) | |
| # Join the lines back into a single string | |
| return "<br>".join(highlighted_lines) | |
| # Function to get the meaning of the searched keyword using the Dictionary API | |
| def get_keyword_meaning(keyword): | |
| # Handler function to retrieve word meaning | |
| def handler(word): | |
| url = f"https://api.dictionaryapi.dev/api/v2/entries/en/{word}" | |
| r = requests.get(url) | |
| return r.json() | |
| # Call the handler function with the keyword | |
| data = handler(keyword) | |
| print(f"Response Data: {data}") # Debugging output | |
| if isinstance(data, list) and len(data) > 0: | |
| try: | |
| meanings = data[0]['meanings'][0]['definitions'] | |
| meaning = meanings[0]['definition'] if meanings else "Meaning not found." | |
| except (IndexError, KeyError): | |
| meaning = "Meaning not found." | |
| elif isinstance(data, dict) and 'message' in data: | |
| meaning = data['message'] # For error messages | |
| else: | |
| meaning = "Could not retrieve meaning. Check your internet connection." | |
| return meaning | |
| # Streamlit application | |
| st.title("OCR Web Application") | |
| # Step 1: Upload image file (JPEG, PNG) | |
| uploaded_file = st.file_uploader("Upload an image file (JPEG, PNG)", type=["jpg", "jpeg", "png"]) | |
| if uploaded_file is not None: | |
| # Step 2: Open and display the uploaded image | |
| image = Image.open(uploaded_file) | |
| st.image(image, caption="Uploaded Image", use_column_width=True) | |
| # Step 3: Extract text from the image | |
| extracted_text = extract_text_from_image(image) | |
| st.subheader("Extracted Text:") | |
| # Display the extracted text as-is with line breaks | |
| st.text(extracted_text) # Use st.text to preserve the formatting | |
| # Step 4: Search for keywords in the extracted text | |
| search_keyword = st.text_input("Enter keyword to search in the extracted text:") | |
| if search_keyword: | |
| if search_keyword.lower() in extracted_text.lower(): | |
| # Highlight matching keywords in the extracted text | |
| highlighted_text = highlight_text(extracted_text, search_keyword) | |
| st.subheader("Search Results:") | |
| # Display the highlighted text as HTML to apply the background color and bold text | |
| st.markdown(highlighted_text, unsafe_allow_html=True) | |
| # Step 5: Get and display the meaning of the searched keyword | |
| meaning = get_keyword_meaning(search_keyword.lower()) | |
| st.subheader(f"Meaning of '{search_keyword}':") | |
| st.write(meaning) | |
| else: | |
| # No matches found message | |
| st.subheader("Search Results:") | |
| st.write("No matches found.") | |