tags title_tag = soup.find('title') if title_tag: title_tag.replace_with(title_tag) if modified: with open(file_path, 'w', encoding='utf-8') as f: f.write(str(soup)) print(f"Modified {file_path}") html += f"<li><a href='./{file_path}'>{file}</a> - Modified words: {', '.join(modified_words)}</li>" except Exception as e: print(f"Error reading {file_path}: {e}") html += "</ul></body></html>" with open(output_file, 'w', encoding='utf-8') as f: f.write(html) print("See modified files list in", output_file) root_dir = './' # Example: Plain text to plain text # find_text = '''गुरुदेव''' # replace_text = '''पूज्य गुरुदेव''' # Example: HTML anchor tag to plain text find_text = '''<a href="../folders-special/hamari-vasiyat-aur-virasat.html" target="blank" title="पूज्य गुरुदेव— मैं व्यक्ति नहीं विचार हूँ।.....हम व्यक्ति के रूप में कब से खत्म हो गए। हम एक व्यक्ति हैं? नहीं हैं। हम कोई व्यक्ति नहीं हैं। हम एक सिद्धांत हैं, आदर्श हैं, हम एक दिशा हैं, हम एक प्रेरणा हैं।">पूज्य गुरुदेव</a>''' replace_text = '''पूज्य गुरुदेव''' output_file = 'find-replace-single-word-without-root-files-conditional.html' find_replace(root_dir, find_text, replace_text, output_file) end = time.time() print("Elapsed (with compilation) = %s" % (end

tags div_tags = soup.find_all('div') for div in div_tags: # Find all

tags within the

tag p_tags = div.find_all('p') for p in p_tags: # Concatenate the text content of all child nodes within the

tag p_text = ''.join(str(child) for child in p.children if isinstance(child, (NavigableString, Tag))) # Find all tags within the

tag and check if find_word is within any of them a_tags = p.find_all('a') skip_replace = any(find_word in a.get_text() or find_word in a.get('title', '') for a in a_tags) # Check if find_word matches the entire content of an tag allow_replace = any(str(a) == find_word for a in a_tags) if allow_replace: print(f"Found '{find_word}' as full tag in {file_path}") for a in a_tags: if str(a) == find_word: a.replace_with(replace_word) modified = True modified_words.append(f"{find_word} -> {replace_word}") elif not skip_replace and find_word in p_text: print(f"Found '{find_word}' in {file_path}") # Replace find_word in the text content of the

tag new_p_text = p_text.replace(find_word, replace_word) # Replace the text content of the

tag p.clear() p.append(BeautifulSoup(new_p_text, 'html.parser')) modified = True modified_words.append(f"{find_word} -> {replace_word}") # Find all heading tags heading_tags = ['h1', 'h2', 'h3', 'h4', 'h5', 'h6'] for tag in heading_tags: for heading in soup.find_all(tag): heading_text = ''.join(str(child) for child in heading.children if isinstance(child, (NavigableString, Tag))) if find_word in heading_text: print(f"Found '{find_word}' in {file_path}") # Replace find_word in the text content of the heading tag new_heading_text = heading_text.replace(find_word, replace_word) # Replace the text content of the heading tag heading.clear() heading.append(BeautifulSoup(new_heading_text, 'html.parser')) modified = True modified_words.append(f"{find_word} -> {replace_word}") # Exclude searching within tags title_tag = soup.find('title') if title_tag: title_tag.replace_with(title_tag) if modified: with open(file_path, 'w', encoding='utf-8') as f: f.write(str(soup)) print(f"Modified {file_path}") html += f"<li><a href='./{file_path}'>{file}</a> - Modified words: {', '.join(modified_words)}</li>" except Exception as e: print(f"Error reading {file_path}: {e}") html += "</ul></body></html>" with open(output_file, 'w', encoding='utf-8') as f: f.write(html) print("See modified files list in", output_file) root_dir = './' # Example: Plain text to plain text # find_text = '''गुरुदेव''' # replace_text = '''पूज्य गुरुदेव''' # Example: HTML anchor tag to plain text find_text = '''<a href="../folders-special/hamari-vasiyat-aur-virasat.html" target="blank" title="पूज्य गुरुदेव— मैं व्यक्ति नहीं विचार हूँ।.....हम व्यक्ति के रूप में कब से खत्म हो गए। हम एक व्यक्ति हैं? नहीं हैं। हम कोई व्यक्ति नहीं हैं। हम एक सिद्धांत हैं, आदर्श हैं, हम एक दिशा हैं, हम एक प्रेरणा हैं।">पूज्य गुरुदेव</a>''' replace_text = '''पूज्य गुरुदेव''' output_file = 'find-replace-single-word-without-root-files-conditional.html' find_replace(root_dir, find_text, replace_text, output_file) end = time.time() print("Elapsed (with compilation) = %s" % (end - start))

Files Modified during find-replace operation