Spaces:
Running
Running
File size: 2,287 Bytes
372531f |
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 |
import os
import requests
import tempfile
from urllib.parse import urlparse
from langchain_community.document_loaders import PyMuPDFLoader
class PyMuPDFScraper:
def __init__(self, link, session=None):
"""
Initialize the scraper with a link and an optional session.
Args:
link (str): The URL or local file path of the PDF document.
session (requests.Session, optional): An optional session for making HTTP requests.
"""
self.link = link
self.session = session
def is_url(self) -> bool:
"""
Check if the provided `link` is a valid URL.
Returns:
bool: True if the link is a valid URL, False otherwise.
"""
try:
result = urlparse(self.link)
return all([result.scheme, result.netloc]) # Check for valid scheme and network location
except Exception:
return False
def scrape(self) -> str:
"""
The `scrape` function uses PyMuPDFLoader to load a document from the provided link (either URL or local file)
and returns the document as a string.
Returns:
str: A string representation of the loaded document.
"""
try:
if self.is_url():
response = requests.get(self.link, timeout=5, stream=True)
response.raise_for_status()
with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_file:
temp_filename = temp_file.name # Get the temporary file name
for chunk in response.iter_content(chunk_size=8192):
temp_file.write(chunk) # Write the downloaded content to the temporary file
loader = PyMuPDFLoader(temp_filename)
doc = loader.load()
os.remove(temp_filename)
else:
loader = PyMuPDFLoader(self.link)
doc = loader.load()
return str(doc)
except requests.exceptions.Timeout:
print(f"Download timed out. Please check the link : {self.link}")
except Exception as e:
print(f"Error loading PDF : {self.link} {e}")
|