Spaces:
Running
Running
File size: 2,241 Bytes
5301c48 |
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 |
import os
from typing import Dict, Any
from starfish.data_ingest.parsers.base_parser import BaseParser
class PPTParser(BaseParser):
"""Parser for PowerPoint presentations"""
def __init__(self):
super().__init__()
self.supported_extensions = [".pptx"]
self.metadata = {}
def parse(self, file_path: str) -> str:
"""Parse a PPTX file into plain text
Args:
file_path: Path to the PPTX file
Returns:
Extracted text from the presentation
"""
try:
from pptx import Presentation
except ImportError:
raise ImportError("python-pptx is required for PPTX parsing. Install it with: pip install python-pptx")
prs = Presentation(file_path)
# Extract metadata
self.metadata = {
"title": prs.core_properties.title,
"author": prs.core_properties.author,
"created": prs.core_properties.created,
"modified": prs.core_properties.modified,
"slides": len(prs.slides),
}
# Extract text from slides
all_text = []
for i, slide in enumerate(prs.slides):
slide_text = []
slide_text.append(f"--- Slide {i+1} ---")
# Get slide title
if slide.shapes.title and slide.shapes.title.text:
slide_text.append(f"Title: {slide.shapes.title.text}")
# Get text from shapes
for shape in slide.shapes:
if hasattr(shape, "text") and shape.text:
slide_text.append(shape.text)
all_text.append("\n".join(slide_text))
return "\n\n".join(all_text)
def get_metadata(self) -> Dict[str, Any]:
"""Get presentation metadata
Returns:
Dictionary containing presentation metadata
"""
return self.metadata
def is_supported(self, file_path: str) -> bool:
"""Check if the file is supported by this parser
Args:
file_path: Path to the file
Returns:
True if the file is supported, False otherwise
"""
return os.path.splitext(file_path)[1].lower() in self.supported_extensions
|