mirror-checker/projects/slackware.py

from bs4 import BeautifulSoup
import requests
import re
import datefinder  # another date finding library
from project import Project
from shared import CSC_MIRROR

class slackware(Project):
    """slackware class"""
    @staticmethod
    def checker(directory_URL, file_name):
        page = requests.get(directory_URL).text
        file_index = page.find(file_name)
        # print(page)

        if file_index == -1:
            return False

        str_dates = re.findall(r'(\d{2}-\w{3}-\d{4} \d{2}:\d{2})|(\d{4}-\d{2}-\d{2} \d{2}:\d{2})', page[file_index:])

        return list(datefinder.find_dates("".join(str_dates[0])))[0]

    @classmethod
    def scrape(cls, site1, site2):
        # getting the request from url
        r1 = requests.get(site1)
        r2 = requests.get(site2)
        
        # converting the text
        s1 = BeautifulSoup(r1.text,"html.parser")
        s2 = BeautifulSoup(r2.text,"html.parser")

        hrefs1 = [i.attrs['href'] for i in s1.find_all("a")]
        hrefs2 = [i.attrs['href'] for i in s2.find_all("a")]

        for href in hrefs1: # for a href directories
            if href.endswith("/") and href != "../" and href != "/" and not href.startswith("/") and not re.match(r'slackware-([1-7]|8\.0).*', href) and href != "slackware-iso/" and href != "slackware-current/" and href != "slackware-pre-1.0-beta/" and href != "unsupported/":
                # print(href)
                if href not in hrefs2:
                    return False
                elif cls.checker(site1+href, "CHECKSUMS.md5") != cls.checker(site2+href, "CHECKSUMS.md5"):
                    return False
        return True
    
    @staticmethod
    def check_iso(site1, site2):
        # getting the request from url
        r1 = requests.get(site1)
        r2 = requests.get(site2)
        
        # converting the text
        s1 = BeautifulSoup(r1.text,"html.parser")
        s2 = BeautifulSoup(r2.text,"html.parser")

        hrefs1 = [i.attrs['href'] for i in s1.find_all("a")]
        hrefs2 = [i.attrs['href'] for i in s2.find_all("a")]

        for href in hrefs1: # for a href directories
            if href.endswith("/") and href != "../" and href != "/" and not href.startswith("/") and not href.startswith("http"):
                # print(href)
                if href not in hrefs2:
                    return False
        return True

    @classmethod
    def check(cls, data, project, current_time):
        """Check if project packages are up-to-date"""
        
        csc_url = CSC_MIRROR + data[project]["csc"] + data[project]["file"]
        upstream_url = data[project]["upstream"] + data[project]["file"]
        
        # print(cls.check_iso(upstream_url+"slackware-iso/", csc_url+"slackware-iso/"))
        
        return cls.scrape(upstream_url, csc_url) and cls.check_iso(upstream_url+"slackware-iso/", csc_url+"slackware-iso/")