resume-rag / utils.py
suvadityamuk's picture
changes
d6cf17e
import gdown
import os
from urllib.parse import urlparse, parse_qs
def download_pdf_from_gdrive(url, output_path=None):
"""
Download a PDF file from Google Drive using the provided sharing URL.
Parameters:
url (str): The Google Drive sharing URL of the PDF file
output_path (str, optional): The path where the PDF should be saved.
If not provided, saves in current directory.
Returns:
str: Path to the downloaded file if successful, None if failed
Raises:
ValueError: If the URL is invalid or doesn't point to a Google Drive file
"""
try:
# Check if URL is provided
if not url:
raise ValueError("URL cannot be empty")
# Handle different types of Google Drive URLs
if 'drive.google.com' not in url:
raise ValueError("Not a valid Google Drive URL")
# Extract file ID from the URL
if '/file/d/' in url:
file_id = url.split('/file/d/')[1].split('/')[0]
elif 'id=' in url:
file_id = parse_qs(urlparse(url).query)['id'][0]
else:
raise ValueError("Could not extract file ID from the URL")
# Set default output path if none provided
if not output_path:
output_path = 'downloaded_file.pdf'
# Ensure the output path ends with .pdf
if not output_path.lower().endswith('.pdf'):
output_path += '.pdf'
# Create the directory if it doesn't exist
os.makedirs(os.path.dirname(output_path) if os.path.dirname(output_path) else '.', exist_ok=True)
# Download the file
output = gdown.download(id=file_id, output=output_path, quiet=False)
if output is None:
raise ValueError("Download failed - file might be inaccessible or not exist")
return output
except Exception as e:
print(f"Error downloading PDF: {str(e)}")
return None
def merge_strings_with_prefix(strings):
"""Merges strings in a list that start with a specific prefix.
Args:
strings: A list of strings.
Returns:
A new list of merged strings.
"""
result = []
current_merged_string = ""
for string in strings:
if string.startswith("•"):
if current_merged_string:
result.append(current_merged_string)
current_merged_string = string
else:
current_merged_string += string
if current_merged_string:
result.append(current_merged_string)
return result