parse junos eol

juniper.eol.py

import re, requests
from lxml import html

url = 'https://support.juniper.net/support/eol/software/junos/'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'
}

response = requests.get(url, headers=headers)

htmltext = re.findall(r'<table>.*</table>', response.content.decode('utf-8'))

tree = html.fromstring(htmltext[0])

target_table = None
for table in tree.xpath('//table'):
    headers = [th.text_content().strip() for th in table.xpath('.//th')]
    if 'Product' in headers and 'FRS Date' in headers:
        target_table = table
        break

data = []
for row in target_table.xpath('.//tr'):
    if row.xpath('.//th'):
        continue
    
    cols = row.xpath('.//td/text()')
    data.append(cols)