updated ubuntu_ports

dev
Tom 12 months ago
parent fe7d22e1e5
commit 68e13c327e
  1. 15
      data.json
  2. 3
      debian code study.txt
  3. 10
      distros.json
  4. 2
      main.py
  5. 20
      projects.json
  6. 21
      projects/gentooportage.py
  7. 41
      projects/ubuntu_ports.py
  8. 4
      test.py

@ -21,7 +21,7 @@
"file": "zzz/time.txt"
},
"Arch": {
"out_of_sync_since": null,
"out_of_sync_since": 1634455547,
"out_of_sync_interval": 86400,
"csc": "archlinux/",
"upstream": "http://arch.mirror.constant.com/",
@ -35,7 +35,7 @@
"file": "centos/TIME"
},
"Ceph": {
"out_of_sync_since": 1633340186,
"out_of_sync_since": null,
"out_of_sync_interval": 86400,
"csc": "ceph/",
"upstream": "https://download.ceph.com/",
@ -73,14 +73,14 @@
"file": "project/trace/deb-multimedia.org"
},
"DebianPorts": {
"out_of_sync_since": null,
"out_of_sync_since": 1634455547,
"out_of_sync_interval": 86400,
"csc": "",
"upstream": "https://deb.debian.org/",
"file": "debian-ports/project/trace/porta.debian.org"
},
"DebianSecurity": {
"out_of_sync_since": null,
"out_of_sync_since": 1634455547,
"out_of_sync_interval": 86400,
"csc": "",
"upstream": "http://debian.mirror.iweb.ca/",
@ -118,6 +118,7 @@
"out_of_sync_since": null,
"out_of_sync_interval": 86400,
"csc": "rsync://rsync4.ca.gentoo.org/",
"upstream": "https://mirrorstats.gentoo.org/rsync/",
"upstream1": "rsync://rsync1.de.gentoo.org/",
"upstream2": "rsync://rsync8.de.gentoo.org/",
"file": "gentoo-portage/Manifest"
@ -279,9 +280,9 @@
"ubuntu_ports": {
"out_of_sync_since": 1633341982,
"out_of_sync_interval": 86400,
"csc": "ubuntu-ports/project/trace/",
"upstream": "http://ports.ubuntu.com/ubuntu-ports/project/trace/",
"file": "anonster.canonical.com"
"csc": "ubuntu-ports/",
"upstream": "http://ports.ubuntu.com/ubuntu-ports/",
"file": "dists/"
},
"ubuntu_releases": {
"out_of_sync_since": null,

@ -1,3 +0,0 @@
they use this for DBs in the code:
Psycopg is a PostgreSQL adapter for the Python programming language. This tool allows us to connect the capabilities of the Python language and libraries to obtain, manipulate, input, and update data stored in a PostgreSQL database.

@ -1,10 +0,0 @@
[
["OpenBSD", "https://mirror.csclub.uwaterloo.ca/OpenBSD/", "https://ftp.openbsd.org/pub/OpenBSD/", "timestamp"],
["kernel", "http://mirror.csclub.uwaterloo.ca/kernel.org/linux/kernel/next/", "https://mirrors.edge.kernel.org/pub/linux/kernel/next/", "sha256sums.asc"],
["debian", "http://mirror.csclub.uwaterloo.ca/debian/project/trace/", "https://ftp-master.debian.org/debian/project/trace/", "master"],
["GNU", "http://mirror.csclub.uwaterloo.ca/gnu/", "https://mirrors.kernel.org/gnu/", "mirror-updated-timestamp.txt"],
["almalinux", "https://mirror.csclub.uwaterloo.ca/almalinux/", "https://repo.almalinux.org/almalinux/", "TIME"],
["alpine", "https://mirror.csclub.uwaterloo.ca/alpine/", "https://dl-cdn.alpinelinux.org/alpine/", "last-updated"],
["Apache", "https://mirror.csclub.uwaterloo.ca/apache/zzz/", "https://downloads.apache.org/zzz/", "time.txt"],
["CentOS", "https://mirror.csclub.uwaterloo.ca/centos/", "https://vault.centos.org/", "timestamp.txt"]
]

@ -67,7 +67,7 @@ if __name__ == "__main__":
print(f"Failure: {project} does not exist")
continue
project_class = getattr(sys.modules[__name__], project)
if project == "CPAN" or project == "ubuntu" or project == "ubuntu_releases" or project == "manjaro" or project == "mxlinux" or project == "mxlinux_iso" or project == "slackware" or project == "trisquel" or project == "cran" or project == "ctan":
if project == "CPAN" or project == "ubuntu" or project == "ubuntu_releases" or project == "manjaro" or project == "mxlinux" or project == "mxlinux_iso" or project == "slackware" or project == "trisquel" or project == "cran" or project == "ctan" or project == "gentooportage":
checker_result = project_class.check(data, project, current_time)
if checker_result:
print(f"Success: {project} up-to-date")

@ -1,20 +0,0 @@
[
[
"OpenBSD",
"https://mirror.csclub.uwaterloo.ca/OpenBSD/",
"https://ftp.openbsd.org/pub/OpenBSD/",
"timestamp"
],
[
"kernel",
"http://mirror.csclub.uwaterloo.ca/kernel.org/linux/kernel/next/",
"https://mirrors.edge.kernel.org/pub/linux/kernel/next/",
"sha256sums.asc"
],
[
"debian",
"http://mirror.csclub.uwaterloo.ca/debian/project/trace/",
"https://ftp-master.debian.org/debian/project/trace/",
"master"
]
]

@ -6,13 +6,20 @@ import os
from project import Project
import requests
import datefinder # another date finding library
from datetime import timedelta
from datetime import datetime
import re
import pandas as pd
class GentooPortage(Project):
"""GentooPortage class"""
@staticmethod
def check(data, project):
rsync_command = "rsync -q {}{} {}"
"""rsync_command = "rsync -q {}{} {}"
os.system(rsync_command.format(data[project]["csc"],
data[project]["file"],
"csc_manifest"))
@ -29,4 +36,14 @@ class GentooPortage(Project):
os.system("rm csc_manifest")
os.system("rm upstream_manifest1")
os.system("rm upstream_manifest2")
return 0 in [len(output1), len(output2)]
return 0 in [len(output1), len(output2)]"""
# i'm changing the above code to the bottom one, since the above one only works in linux
page = requests.get(data[project]["upstream"]).text
indexOfFile = page.find("rsync4.ca.gentoo.org")
m = re.search(r'(\d+ hour)|(\d+ hours)|(\d+(\.)?\d+ days)', page[indexOfFile:])
duration = pd.to_timedelta(m.group(0))
return duration <= pd.to_timedelta(data[project]["out_of_sync_interval"], unit='s')

@ -1,8 +1,39 @@
"""
Contains ubuntu_ports class
"""
from bs4 import BeautifulSoup
import requests
from project import Project
from shared import CSC_MIRROR
class ubuntu_ports(Project):
"""ubuntu_ports class"""
"""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)

@ -7,7 +7,7 @@ from datetime import timedelta
import time
import pandas as pd
import re # for salt stack specifically
from projects import netbsd
from projects import ubuntu_ports
import json # import json to read project info stored in json file
# this function is brute force looping through the whole directory and checking dates
@ -65,7 +65,7 @@ def get_latest_date(web_dir):
if __name__ =="__main__":
with open("data.json", "r", encoding="utf-8") as file:
data = json.load(file)
print(netbsd.check(data, "netbsd"))
print(ubuntu_ports.check(data, "ubuntu_ports"))
"""# website to be scrape
site="https://cdimage.ubuntu.com/releases/"

Loading…
Cancel
Save