from bs4 import BeautifulSoup
from collections import defaultdict
import requests

base_url = "https://git.savannah.gnu.org/cgit/"

def forlist(repos):
    repo_details = []
    
    for repo in repos:
        repo_name = repo.a.text
        repo_url = get_url(repo_name, repo)
        print(repo_url)
        origin_link = find_origin_link(repo_url)
        try:
            time = repo.span['title']
        except Exception:
            time = None
        print(origin_link)

        if origin_link is not None:
            repo_details.append({
            'name': repo_name,
            'time': time,
            'desc': repo.find_all('a')[1].text,
            'origin_link': origin_link
            })

    return repo_details
        
# i.find('a',{"class":"button"})['href']
        

def find_origin_link(repo_url):
    
    #next_link='https://gitweb.torproject.org/chutney.git/'
    response = requests.get(repo_url)
    soup = BeautifulSoup(response.text,features="html.parser")

    origin_links = find_all_origin_link(soup)
    return priority_origin_link(origin_links)

def get_url(repo_name, repo):
    try :
        suffix = repo.a['href']
        (part1, part2, next_url) = self.base_url.split('/', 2)   
        print(next_url)
        return part1 + '//' + next_url + suffix
    except Exception:
        return base_url + repo_name + '/'



def find_all_origin_link(soup):
    origin_links = defaultdict(dict)
    found_clone_word = False
    for i in soup.find_all('tr'):
        if found_clone_word:
            link = i.text
            protocol = link[:link.find(':')]
            origin_links[protocol] = link
        if i.text == 'Clone':
            found_clone_word = True
    return origin_links

def priority_origin_link(origin_links):
    for protocol in ['https', 'http', 'git', 'ssh']:
        if protocol in origin_links:
            return origin_links[protocol]




response = requests.get(base_url)
soup = BeautifulSoup(response.text, 
                     features="html.parser").find('div', {"class": "content"})

repos = soup.find_all("tr", {"class": ""})


forlist(repos)