from glob import glob
from urllib.parse import urlparse


links_dict = {}

def parse_saymyname(link: str):
    parsed = urlparse(link)
    splitted_path = parsed.path.split("/")
    first_letter = splitted_path[2]

    first_letter_list = links_dict.get(first_letter)
    if not first_letter_list: 
        links_dict[first_letter] = list()

    joined_path = '/'.join(splitted_path[:4])
    url = f"{parsed.scheme}://{parsed.hostname}{joined_path}"

    if not url in links_dict[first_letter]:
        links_dict[first_letter].append(url)

# Iterating series
for file in glob("data/*.saymyname.website-series.txt"):
    with open(file, "r") as fp:
        links = fp.readlines()
        
        for link in links:
            if "saymyname" in link:
                parse_saymyname(link)


text = "# Almas Movie Archive (Only Series)"
for k, v in links_dict.items():
    print(f"{k}: {len(v)}")

    for link in v:
        parsed_link = urlparse(link)
        name = parsed_link.path.split("/")[-1]
        text += f"{k}: [{name}]({link.replace(' ', '%20')})\n\n"

with open("series.md", "w") as fp:
    fp.write(text)