2021-10-16 14:56:29 -04:00
|
|
|
from bs4 import BeautifulSoup
|
|
|
|
|
import requests
|
|
|
|
|
from project import Project
|
|
|
|
|
from shared import CSC_MIRROR
|
|
|
|
|
|
|
|
|
|
class x_org(Project):
|
|
|
|
|
"""x.org class"""
|
|
|
|
|
@classmethod
|
|
|
|
|
def scrape(cls, files, site):
|
|
|
|
|
# getting the request from url
|
|
|
|
|
r = requests.get(site)
|
|
|
|
|
|
|
|
|
|
# converting the text
|
|
|
|
|
s = BeautifulSoup(r.text,"html.parser")
|
|
|
|
|
|
|
|
|
|
for i in s.find_all("a"): # for a href directories
|
|
|
|
|
href = i.attrs['href']
|
|
|
|
|
|
|
|
|
|
if href.endswith("/") and href != "../" and href != "/" and not href.startswith("/") and not href.startswith("xcb"):
|
|
|
|
|
site_next = site+href
|
|
|
|
|
|
|
|
|
|
if href not in files:
|
|
|
|
|
files.append(href)
|
|
|
|
|
# print(href)
|
|
|
|
|
# calling it self
|
|
|
|
|
cls.scrape(files, site_next)
|
|
|
|
|
elif href != "../" and href != "/" and not href.startswith("/") and not href.startswith("xcb") and href != "?C=N;O=D" and href != "?C=M;O=A" and href != "?C=S;O=A" and href != "?C=D;O=A":
|
|
|
|
|
# print(href)
|
|
|
|
|
files.append(href)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@classmethod
|
2022-01-01 14:54:28 -05:00
|
|
|
def check(cls, data, project, current_time):
|
2021-10-16 14:56:29 -04:00
|
|
|
"""Check if project packages are up-to-date"""
|
|
|
|
|
# lists
|
|
|
|
|
files1=[]
|
|
|
|
|
files2=[]
|
|
|
|
|
|
|
|
|
|
csc_url = CSC_MIRROR + data[project]["csc"] + data[project]["file"]
|
|
|
|
|
upstream_url = data[project]["upstream"] + data[project]["file"]
|
|
|
|
|
|
|
|
|
|
# calling function
|
|
|
|
|
cls.scrape(files1, csc_url)
|
|
|
|
|
cls.scrape(files2, upstream_url)
|
|
|
|
|
|
|
|
|
|
# print(set(files1) - set(files2))
|
|
|
|
|
|
2022-01-01 14:54:28 -05:00
|
|
|
return set(files1) == set(files2)
|
