39 lines
1.3 KiB
Python
39 lines
1.3 KiB
Python
from bs4 import BeautifulSoup
|
|
import requests
|
|
from project import Project
|
|
from shared import CSC_MIRROR
|
|
|
|
class ubuntu_ports(Project):
|
|
"""ubuntu_ports class"""
|
|
|
|
@staticmethod
|
|
def scrape(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("/"):
|
|
# print(href)
|
|
if href not in hrefs2:
|
|
return False
|
|
elif requests.get(site1+href+"Release").text != requests.get(site2+href+"Release").text:
|
|
return False
|
|
return True
|
|
|
|
@classmethod
|
|
def check(cls, data, project):
|
|
"""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"]
|
|
|
|
# calling function
|
|
return cls.scrape(upstream_url, csc_url) |