thor-downloader

thor-downloader.py

import requests
from bs4 import BeautifulSoup

main_url = "https://www.thorlabs.com/newgrouppage9.cfm?objectgroup_id=3569"
main_page = BeautifulSoup(requests.get(main_url).text, 'html.parser')
products = main_page.find_all(class_="prodNumber")
prod_urls = []
for product in products:
    prod_urls.append("https://www.thorlabs.com/" + product.contents[0].get('href'))

for prod_url in prod_urls:
    prod_page = BeautifulSoup(requests.get(prod_url).text, 'html.parser')
    pdf = prod_page.find(class_="downloadDoc")
    pdf_url = "https://www.thorlabs.com/" + pdf.get('href')
    pdf_filename = pdf.get('data-filename')
    with open(pdf_filename, "wb") as pdf:
        for chunk in requests.get(pdf_url, stream=True).iter_content(chunk_size=1024):
            if chunk:
                pdf.write(chunk)

Install dependencies first:

pip install requests
pip install beautifulsoup4