This is a Python rewrite of the code at #83. Co-authored-by: Nemo <commits@captnemo.in> Co-authored-by: Marc Wrobel <marc.wrobel@gmail.com>
46 lines
1.6 KiB
Python
46 lines
1.6 KiB
Python
import re
|
|
import urllib.request
|
|
from bs4 import BeautifulSoup
|
|
from datetime import datetime
|
|
import json
|
|
|
|
dbs = {
|
|
"mysql": "https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/MySQL.Concepts.VersionMgmt.html",
|
|
"postgresql": "https://docs.aws.amazon.com/AmazonRDS/latest/PostgreSQLReleaseNotes/postgresql-release-calendar.html",
|
|
}
|
|
|
|
|
|
def parse_date(d):
|
|
return datetime.strptime(d, "%d %B %Y").strftime("%Y-%m-%d")
|
|
|
|
|
|
for db, url in dbs.items():
|
|
print(f"::group::{db}")
|
|
releases = {}
|
|
|
|
with urllib.request.urlopen(url, data=None, timeout=5) as contents:
|
|
html = contents.read().decode("utf-8")
|
|
soup = BeautifulSoup(html, features="html5lib")
|
|
|
|
for table in soup.find_all("table"):
|
|
for row in table.find_all("tr"):
|
|
columns = row.find_all("td")
|
|
|
|
# Must match both the 'Supported XXX minor versions' and
|
|
# 'Supported XXX major versions' to have correct release dates
|
|
if len(columns) > 3:
|
|
r = r"(?P<v>\d+(?:\.\d+)*)" # https://regex101.com/r/BY1vwV/1
|
|
m = re.search(r, columns[0].text.strip(), flags=re.IGNORECASE)
|
|
if m:
|
|
version = m.group("v")
|
|
date = parse_date(columns[2].text.strip())
|
|
print(f"{version} : {date}")
|
|
releases[version] = date
|
|
|
|
print("::endgroup::")
|
|
with open(f"releases/amazon-rds-{db.lower()}.json", "w") as f:
|
|
json.dump(dict(
|
|
# sort by date then version (desc)
|
|
sorted(releases.items(), key=lambda x: (x[1], x[0]), reverse=True)
|
|
), f, indent=2)
|