FilesExpand file tree

main

/

pdf_parser.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

47 lines (35 loc) · 1.3 KB

main

/

pdf_parser.py

Copy path

Top

File metadata and controls

• Code
• Blame

47 lines (35 loc) · 1.3 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

import pdfplumber

class PDFParsingError(Exception):

pass

def is_valid_pdf(file_path):

try:

with open(file_path, "rb") as f:

header = f.read(5)

return header.startswith(b"%PDF-")

except OSError:

return False

def extract_text_from_pdf(file_path):

if not is_valid_pdf(file_path):

raise PDFParsingError("The uploaded file is not a valid PDF.")

extracted_pages = []

try:

with pdfplumber.open(file_path) as pdf:

if len(pdf.pages) == 0:

raise PDFParsingError("The PDF has no pages.")

for page in pdf.pages:

text = page.extract_text() or ""

extracted_pages.append(text)

except PDFParsingError:

raise

except Exception as exc:

# pdfplumber raises various low-level exceptions for corrupted

# or malformed PDFs - we don't want to leak that detail to the

# user, so we wrap it in our own error type.

raise PDFParsingError("Could not read the PDF file. It may be corrupted.") from exc

full_text = "\n".join(extracted_pages).strip()

if not full_text:

raise PDFParsingError(

"No readable text was found in this PDF. "

"It may be a scanned image without selectable text."

)

return full_text