import requests
from bs4 import BeautifulSoup
url = "https://ucr.gov/enforcement/1712583"
url_get = requests.get(url)
soup = BeautifulSoup(url_get.content, "html.parser")
print(soup)

import requests
from bs4 import BeautifulSoup
import time

def get_json(query):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:65.0) Gecko/20100101 Firefox/65.0',
        'Accept': 'application/json, text/plain, */*',
        'Accept-Language': 'en-US,en;q=0.5',
        'Referer': 'https://ucr.gov/enforcement/{}'.format(query),
        'Cache-Control': 'no-cache,no-store,must-revalidate,max-age=0,private',
        'UCR-UI-Version': '19.2.1',
        'Origin': 'https://ucr.gov',
        'Connection': 'keep-alive',
    }
 
    s = requests.Session()
     
    params = (
        ('pageNumber', '0'),
        ('itemsPerPage', '15'),
    )

    url = 'https://admin.ucr.gov/api/enforcement/{}'.format(query)
    response = s.get(url, headers=headers, params=params)
    return response.json()


if __name__ == '__main__':
    dots = [192123, 1921, 192, 1712583]
    for query in dots:
        data = get_json(query=query)
        print('DOT: {}'.format(query))
        if data.get('carrier'):
            for registration in data['history']['registrations']:
                print('Year: {year}, Status: {status}'.format(**registration))
        else:
            print('Not valid DOT')
        print('\n-----------\n')
        
        # implement 0.5 delay between requests
        time.sleep(0.5)

Output:
DOT: 192123
Year: 2019, Status: unregistered
Year: 2018, Status: unregistered
Year: 2017, Status: unregistered

-----------

DOT: 1921
Year: 2019, Status: unregistered
Year: 2018, Status: unregistered
Year: 2017, Status: unregistered

-----------

DOT: 192
Not valid DOT

-----------

DOT: 1712583
Year: 2019, Status: unregistered
Year: 2018, Status: unregistered
Year: 2017, Status: unregistered

-----------

(Feb-06-2019, 06:35 PM)hoff1022 Wrote: How did you figure out that the JS was using a json type api?

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
import time
from bs4 import BeautifulSoup

#--| Setup
options = Options()
options.add_argument("--headless")
browser = webdriver.Chrome(executable_path=r'C:\cmder\bin\chromedriver.exe', options=options)
#--| Parse or automation
browser.get('https://ucr.gov/enforcement/1712583')
soup = BeautifulSoup(browser.page_source, 'lxml')
status = soup.find('div', class_="sc-epnACN fEroud")
print(status.text)

Output:
UNREGISTERED