Dev.to

Downloooooad PDFs without using web Browsers with python

Install the library first: (pip install googlesearch-python) import os import requests from googlesearch import search def search_pdfs(query, num_results=10): pdf_links = [] query += " filetype:pdf" for result in search(query, num_results=num_results): if result.lower().endswith(".pdf"): pdf_links.append(result) return pdf_links def download_pdf(url, save_dir="pdf_downloads"): if not os.path.exists(save_dir): os.makedirs(save_dir) try: filename = url.split("/")[-1].split("?")[0] filepath = os.path.join(save_dir, filename) response = requests.get(url, stream=True) response.raise_for_status() with open(filepath, "wb") as f: for chunk in response.iter_content(chunk_size=8192): if chunk: f.write(chunk) print(f"✅ Downloaded: {filename}") except Exception as e: print(f"❌ Failed to download {url} - {e}") Example usage if name == "main": query = input("Enter search term: ") pdf_links = search_pdfs(query, num_results=10) print("\n

Apr 16, 2025 - 21:41
 0
Downloooooad PDFs without using web Browsers with python

Install the library first: (pip install googlesearch-python)

import os
import requests
from googlesearch import search

def search_pdfs(query, num_results=10):
pdf_links = []
query += " filetype:pdf"
for result in search(query, num_results=num_results):
if result.lower().endswith(".pdf"):
pdf_links.append(result)
return pdf_links

def download_pdf(url, save_dir="pdf_downloads"):
if not os.path.exists(save_dir):
os.makedirs(save_dir) 

try:
    filename = url.split("/")[-1].split("?")[0]
    filepath = os.path.join(save_dir, filename)

    response = requests.get(url, stream=True)
    response.raise_for_status()

    with open(filepath, "wb") as f:
        for chunk in response.iter_content(chunk_size=8192):
            if chunk:
                f.write(chunk)

    print(f"✅ Downloaded: {filename}")
except Exception as e:
    print(f"❌ Failed to download {url} - {e}")

Example usage

if name == "main":
query = input("Enter search term: ")
pdf_links = search_pdfs(query, num_results=10) 

print("\n
Read More

Tags:

Previous Article

Gerando Pagamentos via Pix com a AbacatePay

Next Article

GoTransactional Message Queue: A Lightweight Solution Based on SQLite

Related Posts

AI in Autonomous Vehicles: Are We Ready for a Driverless Future?

AI in Autonomous Vehicles: Are We Ready for a Driverles...

Mar 17, 2025  0

Mar 17, 2025  0

Mar 3, 2025  0