import os
import re
import time
import logging
import zipfile
import requests
import bibtexparser
from tqdm import tqdm
from urllib.parse import quote, urlencode
import gradio as gr
from bs4 import BeautifulSoup
import io
from docx import Document
from docx.shared import Inches
from docx.enum.text import WD_ALIGN_PARAGRAPH
# Configure logging
logging.basicConfig(level=logging.INFO,
format='%(asctime)s - %(levelname)s: %(message)s')
logger = logging.getLogger(__name__)
class PaperDownloader:
def __init__(self, output_dir='papers'):
self.output_dir = output_dir
os.makedirs(output_dir, exist_ok=True)
# Updated download sources
self.download_sources = [
'https://sci-hub.ee/',
'https://sci-hub.st/',
'https://sci-hub.ru/',
'https://sci-hub.ren/',
'https://sci-hub.mksa.top/',
'https://sci-hub.se/',
'https://libgen.rs/scimag/'
]
# Request headers
self.headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8'
}
def clean_doi(self, doi):
"""Clean and encode DOI for URL"""
if not isinstance(doi, str):
return None
return quote(doi.strip()) if doi else None
def download_paper_scihub(self, doi):
"""Improved method to download paper from Sci-Hub"""
if not doi:
logger.warning("DOI not provided")
return None
for base_url in self.download_sources:
try:
scihub_url = f"{base_url}{self.clean_doi(doi)}"
# Request with more tolerance
response = requests.get(scihub_url,
headers=self.headers,
allow_redirects=True,
timeout=15)
# Search for multiple PDF URL patterns
pdf_patterns = [
r'(https?://[^\s<>"]+?\.pdf)',
r'(https?://[^\s<>"]+?download/[^\s<>"]+)',
r'(https?://[^\s<>"]+?\/pdf\/[^\s<>"]+)',
]
pdf_urls = []
for pattern in pdf_patterns:
pdf_urls.extend(re.findall(pattern, response.text))
# Try downloading from found URLs
for pdf_url in pdf_urls:
try:
pdf_response = requests.get(pdf_url,
headers=self.headers,
timeout=10)
# Verify if it's a PDF
if 'application/pdf' in pdf_response.headers.get('Content-Type', ''):
logger.debug(f"Found PDF from: {pdf_url}")
return pdf_response.content
except Exception as e:
logger.debug(f"Error downloading PDF from {pdf_url}: {e}")
except Exception as e:
logger.debug(f"Error trying to download {doi} from {base_url}: {e}")
return None
def download_paper_libgen(self, doi):
"""Download from Libgen, handles the query and the redirection"""
if not doi:
return None
base_url = 'https://libgen.rs/scimag/'
try:
search_url = f"{base_url}?q={self.clean_doi(doi)}"
response = requests.get(search_url, headers=self.headers, allow_redirects=True, timeout=10)
response.raise_for_status()
if "No results" in response.text:
logger.debug(f"No results for DOI: {doi} on libgen")
return None
soup = BeautifulSoup(response.text, 'html.parser')
# Find the link using a specific selector
links = soup.select('table.c > tbody > tr:nth-child(2) > td:nth-child(1) > a')
if links:
link = links[0]
pdf_url = link['href']
pdf_response = requests.get(pdf_url, headers=self.headers, allow_redirects=True, timeout=10)
if 'application/pdf' in pdf_response.headers.get('Content-Type', ''):
logger.debug(f"Found PDF from: {pdf_url}")
return pdf_response.content
except Exception as e:
logger.debug(f"Error trying to download {doi} from libgen: {e}")
return None
def download_paper_google_scholar(self, doi):
"""Search google scholar to find an article with the given doi, try to get the pdf"""
if not doi:
return None
try:
query = f'doi:"{doi}"'
params = {'q': query}
url = f'https://scholar.google.com/scholar?{urlencode(params)}'
response = requests.get(url, headers = self.headers, timeout = 10)
response.raise_for_status()
soup = BeautifulSoup(response.text, 'html.parser')
# Find any links with [PDF]
links = soup.find_all('a', string=re.compile(r'\[PDF\]', re.IGNORECASE))
if links:
pdf_url = links[0]['href']
pdf_response = requests.get(pdf_url, headers = self.headers, timeout=10)
if 'application/pdf' in pdf_response.headers.get('Content-Type', ''):
logger.debug(f"Found PDF from: {pdf_url}")
return pdf_response.content
except Exception as e:
logger.debug(f"Google Scholar error for {doi}: {e}")
return None
def download_paper_crossref(self, doi):
"""Alternative search method using Crossref"""
if not doi:
return None
try:
# Search for open access link
url = f"https://api.crossref.org/works/{doi}"
response = requests.get(url, headers=self.headers, timeout=10)
if response.status_code == 200:
data = response.json()
work = data.get('message', {})
# Search for open access links
links = work.get('link', [])
for link in links:
if link.get('content-type') == 'application/pdf':
pdf_url = link.get('URL')
if pdf_url:
pdf_response = requests.get(pdf_url, headers=self.headers)
if 'application/pdf' in pdf_response.headers.get('Content-Type', ''):
logger.debug(f"Found PDF from: {pdf_url}")
return pdf_response.content
except Exception as e:
logger.debug(f"Crossref error for {doi}: {e}")
return None
def download_with_retry(self, doi, max_retries=3, initial_delay=2):
"""Downloads a paper using multiple strategies with exponential backoff"""
pdf_content = None
retries = 0
delay = initial_delay
while retries < max_retries and not pdf_content:
try:
pdf_content = (
self.download_paper_scihub(doi) or
self.download_paper_libgen(doi) or
self.download_paper_google_scholar(doi) or
self.download_paper_crossref(doi)
)
if pdf_content:
return pdf_content
except Exception as e:
logger.error(f"Error in download attempt {retries + 1} for DOI {doi}: {e}")
if not pdf_content:
retries += 1
logger.warning(f"Retry attempt {retries} for DOI: {doi} after {delay} seconds")
time.sleep(delay)
delay *= 2 # Exponential backoff
return None
def download_single_doi(self, doi):
"""Downloads a single paper using a DOI"""
if not doi:
return None, "Error: DOI not provided", "Error: DOI not provided", None, None
try:
pdf_content = self.download_with_retry(doi)
if pdf_content:
if doi is None:
return None, "Error: DOI not provided", "", None, None
filename = f"{str(doi).replace('/', '_').replace('.', '_')}.pdf"
filepath = os.path.join(self.output_dir, filename)
with open(filepath, 'wb') as f:
f.write(pdf_content)
logger.info(f"Successfully downloaded: {filename}")
return filepath, f'{doi}', "", None
else:
logger.warning(f"Could not download: {doi}")
return None, f"Could not download {doi}", f'{doi}', None, None
except Exception as e:
logger.error(f"Error processing {doi}: {e}")
return None, f"Error processing {doi}: {e}", f"Error processing {doi}: {e}", None, None
# Create PaperDownloader instance
downloader = PaperDownloader()
def download_doi_callback(doi):
filepath, success_message, fail_message, _, _ = downloader.download_single_doi(doi)
if filepath:
return filepath, success_message, fail_message
else:
return None, fail_message, success_message
# Test or connect to a Gradio interface
iface = gr.Interface(
fn=download_doi_callback,
inputs=gr.Textbox(label="Enter DOI", placeholder="Enter DOI to download"),
outputs=[
gr.File(label="Download Paper"),
gr.HTML(label="Success Message"),
gr.HTML(label="Failure Message")
],
live=True,
)
iface.launch()