Tübitak Dergileri

import requests
from bs4 import BeautifulSoup as Soup
import re
from pathlib import Path
import os

session = requests.session()
session.headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36 Edg/80.0.361.69'
requests.packages.urllib3.disable_warnings()
session.verify=False

def get_session_cookie(session=session):
    url = 'https://services.tubitak.gov.tr/edergi/user/index.jsp'
    session.get(url, verify=False)

def downloader(url, filename):
    path = Path(filename)
    path.parent.mkdir(parents=True, exist_ok=True)
    with session.get(url, stream=True) as r:
        r.raise_for_status()
        with open(path, 'wb') as f:
            for chunk in r.iter_content(chunk_size=8*2**10):
                if chunk:
                    f.write(chunk)

def download_pdf(page_link):
    res = session.get(page_link)
    soup = Soup(res.text, 'html.parser')
    magazine_name = soup.find('font', {'class':'DergiAdi'})
    info = magazine_name.parent.next_sibling.get_text()
    info = re.match('(?P<ay>\w+) +(?P<yil>\d{4}).*? (?P<sayi>\d+)', info.strip())
    ay, yil, sayi = info.groups()
    magazine_name = magazine_name.get_text()
    pdf_name = f'tubitak/{magazine_name}/{magazine_name}-{yil}-{ay}-{sayi}.pdf'
    pdf_link = f'https://services.tubitak.gov.tr/edergi/user/{soup.find("a").get("href")}'
    downloader(pdf_link, pdf_name)
    print(f'{pdf_name} indirildi')

def index(year, magazine, session=session):
    url = 'https://services.tubitak.gov.tr/edergi/user/yilList1.jsp'
    data = {'submitButton': '', 'yil':year, 'dergiKodu':magazine}
    res = session.post(url, data=data)
    soup = Soup(res.text, 'html.parser')
    return soup

def get_year(year, magazine, session=session):
    soup = index(year, magazine, session)
    links = soup.find_all('a')
    links = [f'https://services.tubitak.gov.tr/edergi/user/{link.get("href")}' for link in links]
    return links

def get_years(magazine, session=session):
    soup = index(2020, magazine, session)
    year_select = soup.find('select', {'name': 'yil'})
    years = [option.get('value') for option in year_select.find_all('option')]
    return years

def magazine_downloader(magazine):
    years = get_years(magazine)
    downloaded_path = f'tubitak/downloaded{magazine}.txt'
    downloaded = []
    if os.path.exists(downloaded_path):
        with open(downloaded_path) as f:
            downloaded = f.read().strip().split('\n')
    for year in years:
        links = get_year(year, magazine)
        for link in links:
            if link not in downloaded:
                download_pdf(link)
                with open(downloaded_path, 'a') as f:
                    f.write(f'{link}\n')


def get_magazine_codes():
    soup = index(2020, 4, session)
    magazine_select = soup.find('select', {'name': 'dergiKodu'})
    options = [(option.get('value'), option.get_text()) for option in magazine_select.find_all('option')][1:]
    print(f'{"kod":^5} - {"dergi adı":<30}')
    for option in options:
        print(f'{option[0]:^5} - {option[1]:<30})')


if __name__ == '__main__':
    get_magazine_codes()
    dergi_kodu = input('indirmek istediğiniz derginin kodunu giriniz: ')
    magazine_downloader(dergi_kodu)