pdf-grabber/main.py

import requests, time, re, os, configparser, sys, argparse, shutil
from bs4 import BeautifulSoup

def main(args):
  print(f"Fetching PDFs.")
  if not os.path.isdir("pdfs"):
    print("First-time setup...")
    os.mkdir("pdfs")
    
  config = configparser.ConfigParser(interpolation=None)
  if not os.path.isfile('config.ini'):
    print("config.ini is missing!")
    sys.exit(0)
  config.read('config.ini')

  if "username" not in config["DEFAULT"] or "password" not in config["DEFAULT"] or config["DEFAULT"]["username"] == "" or config["DEFAULT"]["password"] == "":
    print("username and password must be present in config.ini.")
    sys.exit(0)

  INFOVAYA_ROOT = "https://events.infovaya.com/"

  info = { "username": config["DEFAULT"]["username"],
          "password": config["DEFAULT"]["password"],
          "action": "login"
          }

  s = requests.Session()
  q = s.post("{}login".format(INFOVAYA_ROOT), data=info)
  q.raise_for_status()

  sessions_request = s.get("{}event?id=88&actionMenu=sessions".format(INFOVAYA_ROOT))
  sessions_request.raise_for_status()
  sessions_page_soup = BeautifulSoup(sessions_request.text, "html.parser")
  print("Starting to search for PDFs. This may take a while...")
  for session_link in sessions_page_soup.find_all("a", href=re.compile("session\?id")):
    time.sleep(0.05)
    page_request = s.get("{}{}".format(INFOVAYA_ROOT, session_link["href"]))
    page_request.raise_for_status()
    page_soup = BeautifulSoup(page_request.text, "html.parser")
    page_title = page.soup.h1.string
    for pdf_tag in page_soup.find_all("a", href=re.compile("pdfviewer")):
      pdf_name = pdf_tag["href"].split("/")[-1]
      file_name = "{}-{}".format(page_title.replace(" ", "_"), pdf_name)
      pdf_request = s.get("{}{}".format(INFOVAYA_ROOT, pdf_tag["href"]), stream=True)
      pdf_request.raise_for_status()
      print("Fetching PDF for '{}'...".format(page_title))
        with open(file_name, "wb") as file:
          pdf_request.raw.decode_content = True
          shutil.copyfileobj(pdf_request.raw, file)
          print("Saved as pdfs/{}".format(file_name))
  
  print("Finished fetching thread.")

if __name__ == "__main__":
  parser = argparse.ArgumentParser()
  parser.add_argument("thread", action="store", help="The threadid from the thread's URL")
  parser.add_argument("-i", "--images", action="store_true", help="Set this flag to download images as well as HTML.\nNOTE: This may be VERY bandwidth and disk intensive!")
  args = parser.parse_args()
  main(args)