File size: 1,627 Bytes
35b22df
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""Docs parser.

Contains parsers for docx, pdf files.

"""
from pathlib import Path
from typing import Dict

from gpt_index.readers.file.base_parser import BaseParser


class PDFParser(BaseParser):
    """PDF parser."""

    def _init_parser(self) -> Dict:
        """Init parser."""
        return {}

    def parse_file(self, file: Path, errors: str = "ignore") -> str:
        """Parse file."""
        try:
            import PyPDF2
        except ImportError:
            raise ImportError(
                "PyPDF2 is required to read PDF files: `pip install PyPDF2`"
            )
        text_list = []
        with open(file, "rb") as fp:
            # Create a PDF object
            pdf = PyPDF2.PdfReader(fp)

            # Get the number of pages in the PDF document
            num_pages = len(pdf.pages)

            # Iterate over every page
            for page in range(num_pages):
                # Extract the text from the page
                page_text = pdf.pages[page].extract_text()
                text_list.append(page_text)
        text = "\n".join(text_list)

        return text


class DocxParser(BaseParser):
    """Docx parser."""

    def _init_parser(self) -> Dict:
        """Init parser."""
        return {}

    def parse_file(self, file: Path, errors: str = "ignore") -> str:
        """Parse file."""
        try:
            import docx2txt
        except ImportError:
            raise ImportError(
                "docx2txt is required to read Microsoft Word files: "
                "`pip install docx2txt`"
            )

        text = docx2txt.process(file)

        return text