Spaces:
Sleeping
Sleeping
| import os | |
| import chardet | |
| def extract_text(file_path: str) -> str: | |
| ext = os.path.splitext(file_path)[1].lower() | |
| try: | |
| if ext == ".txt": | |
| return _read_txt(file_path) | |
| elif ext == ".pdf": | |
| return _read_pdf(file_path) | |
| elif ext == ".docx": | |
| return _read_docx(file_path) | |
| elif ext == ".epub": | |
| return _read_epub(file_path) | |
| elif ext == ".odt": | |
| return _read_odt(file_path) | |
| elif ext == ".rtf": | |
| return _read_rtf(file_path) | |
| elif ext in (".html", ".htm"): | |
| return _read_html(file_path) | |
| else: | |
| return f"Unsupported format: {ext}" | |
| except Exception as e: | |
| return f"Error reading file: {str(e)}" | |
| def _read_txt(path: str) -> str: | |
| with open(path, "rb") as f: | |
| raw = f.read() | |
| detected = chardet.detect(raw) | |
| encoding = detected.get("encoding", "utf-8") or "utf-8" | |
| return raw.decode(encoding, errors="replace") | |
| def _read_pdf(path: str) -> str: | |
| from PyPDF2 import PdfReader | |
| reader = PdfReader(path) | |
| text = [] | |
| for page in reader.pages: | |
| page_text = page.extract_text() | |
| if page_text: | |
| text.append(page_text) | |
| return "\n\n".join(text) | |
| def _read_docx(path: str) -> str: | |
| from docx import Document | |
| doc = Document(path) | |
| return "\n\n".join(p.text for p in doc.paragraphs if p.text.strip()) | |
| def _read_epub(path: str) -> str: | |
| import ebooklib | |
| from ebooklib import epub | |
| from bs4 import BeautifulSoup | |
| book = epub.read_epub(path, options={"ignore_ncx": True}) | |
| text = [] | |
| for item in book.get_items(): | |
| if item.get_type() == ebooklib.ITEM_DOCUMENT: | |
| soup = BeautifulSoup(item.get_content(), "html.parser") | |
| item_text = soup.get_text(separator="\n") | |
| if item_text.strip(): | |
| text.append(item_text.strip()) | |
| return "\n\n".join(text) | |
| def _read_odt(path: str) -> str: | |
| from odf.opendocument import load | |
| from odf.text import P | |
| doc = load(path) | |
| paragraphs = doc.getElementsByType(P) | |
| text = [] | |
| for p in paragraphs: | |
| t = "" | |
| for node in p.childNodes: | |
| if hasattr(node, "data"): | |
| t += node.data | |
| elif hasattr(node, "__str__"): | |
| t += str(node) | |
| if t.strip(): | |
| text.append(t.strip()) | |
| return "\n\n".join(text) | |
| def _read_rtf(path: str) -> str: | |
| from striprtf.striprtf import rtf_to_text | |
| with open(path, "r", errors="replace") as f: | |
| rtf_content = f.read() | |
| return rtf_to_text(rtf_content) | |
| def _read_html(path: str) -> str: | |
| from bs4 import BeautifulSoup | |
| with open(path, "r", encoding="utf-8", errors="replace") as f: | |
| soup = BeautifulSoup(f.read(), "html.parser") | |
| for tag in soup(["script", "style", "nav", "header", "footer"]): | |
| tag.decompose() | |
| return soup.get_text(separator="\n") |