File size: 10,201 Bytes
dbca390 f37f939 dbca390 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 |
import os
import sys
from pathlib import Path
from typing import Optional, Union
import logging
# Import document parsing libraries
try:
import PyPDF2
from docx import Document
import ebooklib
from ebooklib import epub
from bs4 import BeautifulSoup
except ImportError as e:
print(f"Missing required dependency: {e}")
print("Please install dependencies with: pip install -r requirements.txt")
sys.exit(1)
# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
class DocumentParser:
"""
A class to parse and extract text from various document formats.
Supports PDF, TXT, DOC, DOCX, and EPUB files.
"""
def __init__(self):
self.supported_formats = {
'application/pdf': self._parse_pdf,
'text/plain': self._parse_txt,
'application/vnd.openxmlformats-officedocument.wordprocessingml.document': self._parse_docx,
'application/msword': self._parse_doc,
'application/epub+zip': self._parse_epub
}
def get_file_type(self, file_path: Union[str, Path]) -> str:
"""
Detect the MIME type of a file using file extension.
Args:
file_path: Path to the file
Returns:
MIME type string
"""
return self._get_mime_from_extension(file_path)
def _get_mime_from_extension(self, file_path: Union[str, Path]) -> str:
"""
Determine MIME type from file extension.
Args:
file_path: Path to the file
Returns:
MIME type string
"""
extension = Path(file_path).suffix.lower()
extension_map = {
'.pdf': 'application/pdf',
'.txt': 'text/plain',
'.docx': 'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
'.doc': 'application/msword',
'.epub': 'application/epub+zip'
}
mime_type = extension_map.get(extension, 'unknown')
# If no extension or unknown extension, try to detect by content
if mime_type == 'unknown':
mime_type = self._detect_mime_by_content(file_path)
return mime_type
def _detect_mime_by_content(self, file_path: Union[str, Path]) -> str:
"""
Detect MIME type by reading file content.
Args:
file_path: Path to the file
Returns:
MIME type string
"""
try:
with open(file_path, 'rb') as f:
# Read first 1024 bytes to detect file type
header = f.read(1024)
# PDF detection
if header.startswith(b'%PDF'):
return 'application/pdf'
# ZIP-based formats (DOCX, EPUB)
if header.startswith(b'PK\x03\x04'):
# Check if it's EPUB by looking for mimetype file
try:
import zipfile
with zipfile.ZipFile(file_path, 'r') as zf:
if 'mimetype' in zf.namelist():
with zf.open('mimetype') as mf:
mimetype = mf.read().decode('utf-8').strip()
if mimetype == 'application/epub+zip':
return 'application/epub+zip'
# If not EPUB, assume DOCX
return 'application/vnd.openxmlformats-officedocument.wordprocessingml.document'
except:
pass
# Plain text detection (try to decode as UTF-8)
try:
header.decode('utf-8')
return 'text/plain'
except UnicodeDecodeError:
pass
except Exception as e:
logger.warning(f"Error detecting MIME type by content: {e}")
return 'unknown'
def extract_text(self, file_path: Union[str, Path]) -> Optional[str]:
"""
Extract text from a document file.
Args:
file_path: Path to the document file
Returns:
Extracted text as string, or None if extraction fails
"""
file_path = Path(file_path)
if not file_path.exists():
logger.error(f"File not found: {file_path}")
return None
try:
mime_type = self.get_file_type(file_path)
logger.info(f"Detected file type: {mime_type}")
if mime_type in self.supported_formats:
return self.supported_formats[mime_type](file_path)
else:
logger.error(f"Unsupported file type: {mime_type}")
return None
except Exception as e:
logger.error(f"Error extracting text from {file_path}: {e}")
return None
def _parse_pdf(self, file_path: Path) -> str:
"""
Extract text from PDF file.
Args:
file_path: Path to PDF file
Returns:
Extracted text
"""
text = ""
try:
with open(file_path, 'rb') as file:
pdf_reader = PyPDF2.PdfReader(file)
for page_num in range(len(pdf_reader.pages)):
page = pdf_reader.pages[page_num]
page_text = page.extract_text()
if page_text:
text += page_text + "\n"
except Exception as e:
logger.error(f"Error parsing PDF {file_path}: {e}")
raise
return text.strip()
def _parse_txt(self, file_path: Path) -> str:
"""
Extract text from plain text file.
Args:
file_path: Path to text file
Returns:
Extracted text
"""
try:
with open(file_path, 'r', encoding='utf-8') as file:
return file.read()
except UnicodeDecodeError:
# Try with different encoding
try:
with open(file_path, 'r', encoding='latin-1') as file:
return file.read()
except Exception as e:
logger.error(f"Error reading text file {file_path}: {e}")
raise
except Exception as e:
logger.error(f"Error reading text file {file_path}: {e}")
raise
def _parse_docx(self, file_path: Path) -> str:
"""
Extract text from DOCX file.
Args:
file_path: Path to DOCX file
Returns:
Extracted text
"""
try:
doc = Document(file_path)
text = ""
for paragraph in doc.paragraphs:
text += paragraph.text + "\n"
return text.strip()
except Exception as e:
logger.error(f"Error parsing DOCX {file_path}: {e}")
raise
def _parse_doc(self, file_path: Path) -> str:
"""
Extract text from DOC file (legacy Word format).
Note: This requires additional dependencies like antiword or catdoc.
Args:
file_path: Path to DOC file
Returns:
Extracted text
"""
try:
# Try using antiword if available
import subprocess
result = subprocess.run(['antiword', str(file_path)],
capture_output=True, text=True)
if result.returncode == 0:
return result.stdout.strip()
# Fallback: try catdoc
result = subprocess.run(['catdoc', str(file_path)],
capture_output=True, text=True)
if result.returncode == 0:
return result.stdout.strip()
raise Exception("Neither antiword nor catdoc found. Please install one of them.")
except FileNotFoundError:
raise Exception("antiword or catdoc not found. Please install one of them for DOC file support.")
except Exception as e:
logger.error(f"Error parsing DOC {file_path}: {e}")
raise
def _parse_epub(self, file_path: Path) -> str:
"""
Extract text from EPUB file.
Args:
file_path: Path to EPUB file
Returns:
Extracted text
"""
try:
book = epub.read_epub(file_path)
text = ""
for item in book.get_items():
if item.get_type() == ebooklib.ITEM_DOCUMENT:
content = item.get_content().decode('utf-8')
soup = BeautifulSoup(content, 'html.parser')
text += soup.get_text() + "\n"
return text.strip()
except Exception as e:
logger.error(f"Error parsing EPUB {file_path}: {e}")
raise
def main():
"""
Main function to demonstrate usage of the DocumentParser.
"""
if len(sys.argv) != 2:
print("Usage: python document_parsing.py <file_path>")
print("Supported formats: PDF, TXT, DOC, DOCX, EPUB")
sys.exit(1)
file_path = sys.argv[1]
parser = DocumentParser()
print(f"Extracting text from: {file_path}")
print("-" * 50)
extracted_text = parser.extract_text(file_path)
if extracted_text:
print("Extracted text:")
print(extracted_text)
print(f"\nTotal characters: {len(extracted_text)}")
else:
print("Failed to extract text from the file.")
sys.exit(1)
if __name__ == "__main__":
main()
|