f6a8349c46
It may not be the best place for that (gha.py would have been better), but it's the shorter / faster way to do it for now. Moreover it now uses logging for writing the group. The logger format has been updated for this to work. This was done to fix issues on GitHub Action logs, where groups were declared after the logs.
46 lines
1.9 KiB
Python
46 lines
1.9 KiB
Python
import datetime
|
|
import re
|
|
|
|
from bs4 import BeautifulSoup
|
|
from common import dates, endoflife, http
|
|
|
|
MILESTONE_PATTERN = re.compile(r'COS \d+ LTS')
|
|
VERSION_PATTERN = re.compile(r"^(cos-\d+-\d+-\d+-\d+)")
|
|
|
|
|
|
def parse_date(date_text: str) -> datetime:
|
|
date_text = date_text.strip().replace('Date: ', '')
|
|
date_text = re.sub(r'Sep[a-zA-Z]+', 'Sep', date_text)
|
|
return dates.parse_date(date_text)
|
|
|
|
|
|
product = endoflife.Product("cos")
|
|
main = http.fetch_url("https://cloud.google.com/container-optimized-os/docs/release-notes/")
|
|
main_soup = BeautifulSoup(main.text, features="html5lib")
|
|
milestones = [cell.text.split(' ')[1] for cell in main_soup.find_all('td', string=MILESTONE_PATTERN)]
|
|
|
|
milestones_urls = [f"{main.url}m{milestone}" for milestone in milestones]
|
|
for milestone in http.fetch_urls(milestones_urls):
|
|
milestone_soup = BeautifulSoup(milestone.text, features="html5lib")
|
|
for article in milestone_soup.find_all('article', class_='devsite-article'):
|
|
for heading in article.find_all(['h2', 'h3']): # headings contains the date, which we parse
|
|
version_str = heading.get('data-text')
|
|
version_match = VERSION_PATTERN.match(version_str)
|
|
if not version_match:
|
|
continue
|
|
|
|
try: # 1st row is the header, so pick the first td in the 2nd row
|
|
date_str = heading.find_next('tr').find_next('tr').find_next('td').text
|
|
except AttributeError: # In some older releases, it is mentioned as Date: [Date]
|
|
date_str = heading.find_next('i').text
|
|
|
|
try:
|
|
date = parse_date(date_str)
|
|
except ValueError: # for some h3, the date is in the previous h2
|
|
date_str = heading.find_previous('h2').get('data-text')
|
|
date = parse_date(date_str)
|
|
|
|
product.declare_version(version_match.group(1), date)
|
|
|
|
product.write()
|