y266shen
/
mirror-checker
forked from public/mirror-checker
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

changed linuxmint, ubuntu_ports_releases, xubuntu_releases

This commit is contained in:
Tom 2021-10-17 22:23:55 -07:00
parent 8244ba0cfd
commit e8265a2802
6 changed files with 140 additions and 177 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
data.json
View File

@ -275,7 +275,7 @@
"file": "lastsync"
},
"pkgsrc": {
"out_of_sync_since": 1634524215,
"out_of_sync_since": null,
"out_of_sync_interval": 86400,
"csc": "pkgsrc/",
"upstream": "http://ftp.netbsd.org/pub/pkgsrc/",
@ -345,7 +345,7 @@
"file": "tdf/TIMESTAMP"
},
"trisquel": {
"out_of_sync_since": 1634524215,
"out_of_sync_since": null,
"out_of_sync_interval": 86400,
"csc": "trisquel/",
"upstream": "http://rsync.trisquel.info/trisquel/dists/",

2
main.py
View File

@ -27,7 +27,7 @@ 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 == "cran" or project == "ctan" or project == "gentooportage":
if project in ["CPAN", "ubuntu", "ubuntu_releases", "manjaro", "mxlinux", "cran", "ctan", "gentooportage"]:
checker_result = project_class.check(data, project, current_time)
if checker_result:
print(f"Success: {project} up-to-date")

95
projects/linuxmint.py
View File

@ -1,26 +1,40 @@
from bs4 import BeautifulSoup
import requests
import datefinder # another date finding library
import re
from datetime import datetime
from datetime import timedelta
import time
import pandas as pd
import datefinder # another date finding library
from project import Project
from shared import CSC_MIRROR
# this function is brute force looping through the whole directory and checking dates
# it may sound horrible, but for certain distros, i believe it's indeed the best solution
# lists
urls=[]
class linuxmint(Project):
"""linuxmint 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, urls, site):
def scrape(cls, compare, folders, site1, site2, directory):
if cls.checker(site1+directory, "sha256sum.txt") != False:
# print (site1+directory)
# print (cls.checker(site1+directory, "sha256sum.txt"))
if cls.checker(site2+directory, "sha256sum.txt") != False:
# print (site2+directory)
# print (cls.checker(site2+directory, "sha256sum.txt"))
compare.append(cls.checker(site1+directory, "sha256sum.txt") <= cls.checker(site2+directory, "sha256sum.txt"))
return
compare.append(False)
return
# getting the request from url
r = requests.get(site)
r = requests.get(site1 + directory)
# converting the text
s = BeautifulSoup(r.text,"html.parser")
@ -28,58 +42,25 @@ class linuxmint(Project):
for i in s.find_all("a"): # for a href directories
href = i.attrs['href']
if href.endswith("/") and href != "../" and href != "/":
site_next = site+href
if site_next not in urls:
urls.append(site_next)
# print(site_next)
# calling it self
cls.scrape(urls, site_next)
@staticmethod
def get_latest_date(web_dir):
page = requests.get(web_dir).text
str_dates = re.findall(r'(\d{2}-\w{3}-\d{4} \d{2}:\d{2})', page)
# if you want to match 1+ patterns, like r'(\d{2}-\w{3}-\d{4} \d{2}:\d{2})|(\d{4}-\d{2}-\d{2} \d{2}:\d{2})', note that findall will return a tuple of two groups!!!
# print(str_dates[0])
if len(str_dates) == 0:
return datetime(1000, 1, 1) # return ridiculously old date to discard this entry, since it has no dates
# for date in str_dates:
# print(date)
dates = [list(datefinder.find_dates(date))[0] for date in str_dates]
# for date in dates:
# print(date)
return(max(dates))
@classmethod
def max_date(cls, urls):
latest_date = cls.get_latest_date(urls[0])
# get_latest_date(urls[0])
for dir in urls:
latest_date2 = cls.get_latest_date(dir)
if (latest_date2 >= latest_date):
latest_date = latest_date2
# print(latest_date)
return latest_date
if href.endswith("/") and href != "../" and href != "/" and not href.startswith("/"):
dir_next = directory+href
# print(dir_next)
# calling it self
if dir_next not in folders:
folders.append(dir_next)
cls.scrape(compare, folders, site1, site2, dir_next)
@classmethod
def check(cls, data, project):
"""Check if project packages are up-to-date"""
# lists
urls1=[]
urls2=[]
compare=[]
folders=[]
csc_url = CSC_MIRROR + data[project]["csc"] + data[project]["file"]
upstream_url = data[project]["upstream"] + data[project]["file"]
# calling function
cls.scrape(urls1, csc_url)
cls.scrape(urls2, upstream_url)
cls.scrape(compare, folders, upstream_url, csc_url, "")
# print(len(urls1), len(urls2))
return cls.max_date(urls1) == cls.max_date(urls2)
return all(compare)

103
projects/ubuntu_ports_releases.py
View File

@ -1,26 +1,50 @@
from bs4 import BeautifulSoup
import requests
import datefinder # another date finding library
import re
from datetime import datetime
from datetime import timedelta
import time
import pandas as pd
import datefinder # another date finding library
from project import Project
from shared import CSC_MIRROR
# this function is brute force looping through the whole directory and checking dates
# it may sound horrible, but for certain distros, i believe it's indeed the best solution
# lists
urls=[]
class ubuntu_ports_releases(Project):
"""ubuntu_ports_releases 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, urls, site):
def scrape(cls, compare, folders, site1, site2, directory):
if cls.checker(site1+directory, "MD5SUMS") != False:
# print (site1+directory)
# print (cls.checker(site1+directory, "MD5SUMS"))
if cls.checker(site2+directory, "MD5SUMS") != False:
# print (site2+directory)
# print (cls.checker(site2+directory, "MD5SUMS"))
compare.append(cls.checker(site1+directory, "MD5SUMS") <= cls.checker(site2+directory, "MD5SUMS"))
return
compare.append(False)
return
elif cls.checker(site1+directory, "SHA256SUMS") != False:
# print (site1+directory)
# print (cls.checker(site1+directory, "SHA256SUMS"))
if cls.checker(site2+directory, "SHA256SUMS") != False:
# print (site2+directory)
# print (cls.checker(site2+directory, "SHA256SUMS"))
compare.append(cls.checker(site1+directory, "SHA256SUMS") <= cls.checker(site2+directory, "SHA256SUMS"))
return
compare.append(False)
return
# getting the request from url
r = requests.get(site)
r = requests.get(site1 + directory)
# converting the text
s = BeautifulSoup(r.text,"html.parser")
@ -29,57 +53,24 @@ class ubuntu_ports_releases(Project):
href = i.attrs['href']
if href.endswith("/") and href != "../" and href != "/" and not href.startswith("/") and not href.startswith("http://"):
site_next = site+href
if site_next not in urls:
urls.append(site_next)
# print(site_next)
# calling it self
cls.scrape(urls, site_next)
@staticmethod
def get_latest_date(web_dir):
page = requests.get(web_dir).text
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)
# if you want to match 1+ patterns, like r'(\d{2}-\w{3}-\d{4} \d{2}:\d{2})|(\d{4}-\d{2}-\d{2} \d{2}:\d{2})', note that findall will return a tuple of two groups!!!
# print(str_dates[0])
if len(str_dates) == 0:
return datetime(1000, 1, 1) # return ridiculously old date to discard this entry, since it has no dates
# for date in str_dates:
# print(date)
dates = [list(datefinder.find_dates("".join(date)))[0] for date in str_dates]
# for date in dates:
# print(date)
return(max(dates))
@classmethod
def max_date(cls, urls):
latest_date = cls.get_latest_date(urls[0])
# get_latest_date(urls[0])
for dir in urls:
latest_date2 = cls.get_latest_date(dir)
if (latest_date2 >= latest_date):
latest_date = latest_date2
# print(latest_date)
return latest_date
dir_next = directory+href
# print(dir_next)
# calling it self
if dir_next not in folders:
folders.append(dir_next)
cls.scrape(compare, folders, site1, site2, dir_next)
@classmethod
def check(cls, data, project):
"""Check if project packages are up-to-date"""
# lists
urls1=[]
urls2=[]
compare=[]
folders=[]
csc_url = CSC_MIRROR + data[project]["csc"] + data[project]["file"]
upstream_url = data[project]["upstream"] + data[project]["file"]
# calling function
cls.scrape(urls1, csc_url)
cls.scrape(urls2, upstream_url)
cls.scrape(compare, folders, upstream_url, csc_url, "")
# print(len(urls1), len(urls2))
return cls.max_date(urls1) == cls.max_date(urls2)
return all(compare)

103
projects/xubuntu_releases.py
View File

@ -1,26 +1,50 @@
from bs4 import BeautifulSoup
import requests
import datefinder # another date finding library
import re
from datetime import datetime
from datetime import timedelta
import time
import pandas as pd
import datefinder # another date finding library
from project import Project
from shared import CSC_MIRROR
# this function is brute force looping through the whole directory and checking dates
# it may sound horrible, but for certain distros, i believe it's indeed the best solution
# lists
urls=[]
class xubuntu_releases(Project):
"""xubuntu_releases 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, urls, site):
def scrape(cls, compare, folders, site1, site2, directory):
if cls.checker(site1+directory, "MD5SUMS") != False:
# print (site1+directory)
# print (cls.checker(site1+directory, "MD5SUMS"))
if cls.checker(site2+directory, "MD5SUMS") != False:
# print (site2+directory)
# print (cls.checker(site2+directory, "MD5SUMS"))
compare.append(cls.checker(site1+directory, "MD5SUMS") <= cls.checker(site2+directory, "MD5SUMS"))
return
compare.append(False)
return
elif cls.checker(site1+directory, "SHA256SUMS") != False:
# print (site1+directory)
# print (cls.checker(site1+directory, "SHA256SUMS"))
if cls.checker(site2+directory, "SHA256SUMS") != False:
# print (site2+directory)
# print (cls.checker(site2+directory, "SHA256SUMS"))
compare.append(cls.checker(site1+directory, "SHA256SUMS") <= cls.checker(site2+directory, "SHA256SUMS"))
return
compare.append(False)
return
# getting the request from url
r = requests.get(site)
r = requests.get(site1 + directory)
# converting the text
s = BeautifulSoup(r.text,"html.parser")
@ -29,57 +53,24 @@ class xubuntu_releases(Project):
href = i.attrs['href']
if href.endswith("/") and href != "../" and href != "/" and not href.startswith("/") and not href.startswith("http://"):
site_next = site+href
if site_next not in urls:
urls.append(site_next)
# print(site_next)
# calling it self
cls.scrape(urls, site_next)
@staticmethod
def get_latest_date(web_dir):
page = requests.get(web_dir).text
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)
# if you want to match 1+ patterns, like r'(\d{2}-\w{3}-\d{4} \d{2}:\d{2})|(\d{4}-\d{2}-\d{2} \d{2}:\d{2})', note that findall will return a tuple of two groups!!!
# print(str_dates[0])
if len(str_dates) == 0:
return datetime(1000, 1, 1) # return ridiculously old date to discard this entry, since it has no dates
# for date in str_dates:
# print(date)
dates = [list(datefinder.find_dates("".join(date)))[0] for date in str_dates]
# for date in dates:
# print(date)
return(max(dates))
@classmethod
def max_date(cls, urls):
latest_date = cls.get_latest_date(urls[0])
# get_latest_date(urls[0])
for dir in urls:
latest_date2 = cls.get_latest_date(dir)
if (latest_date2 >= latest_date):
latest_date = latest_date2
# print(latest_date)
return latest_date
dir_next = directory+href
# print(dir_next)
# calling it self
if dir_next not in folders:
folders.append(dir_next)
cls.scrape(compare, folders, site1, site2, dir_next)
@classmethod
def check(cls, data, project):
"""Check if project packages are up-to-date"""
# lists
urls1=[]
urls2=[]
compare=[]
folders=[]
csc_url = CSC_MIRROR + data[project]["csc"] + data[project]["file"]
upstream_url = data[project]["upstream"] + data[project]["file"]
# calling function
cls.scrape(urls1, csc_url)
cls.scrape(urls2, upstream_url)
cls.scrape(compare, folders, upstream_url, csc_url, "")
# print(len(urls1), len(urls2))
return cls.max_date(urls1) == cls.max_date(urls2)
return all(compare)

4
test.py
View File

@ -2,12 +2,12 @@
Test Client for individual classes in projects
"""
from projects import mxlinux_iso
from projects import xubuntu_releases
import json # import json to read project info stored in json file
# main function
if __name__ =="__main__":
with open("data.json", "r", encoding="utf-8") as file:
data = json.load(file)
print(mxlinux_iso.check(data, "mxlinux_iso"))
print(xubuntu_releases.check(data, "xubuntu_releases"))