compta_online

compta_online.py

import urllib2
from bs4 import BeautifulSoup

url = "https://www.compta-online.com/oubli-de-facturation-facture-faite-posteriori-t72224#NULL"

response = urllib2.urlopen(url)
html = response.read()
soup = BeautifulSoup(html, 'html.parser')

# Find the input element with the name 'text'
input_element = soup.find('input', {'name': 'text'})

# Get its value (which is a URL)
if input_element is not None:
    new_url = input_element.get('value')

    # Now fetch the new URL
    new_response = urllib2.urlopen(new_url)
    new_html = new_response.read()
    new_soup = BeautifulSoup(new_html, 'html.parser')

    # Get all the text from the new page
    full_text = new_soup.get_text()

    # Find the start and end markers in the text
    start_marker = "ImprimerLienAlerter"
    end_marker = "Répondre"

    start = full_text.find(start_marker)
    end = full_text.find(end_marker)

    if start != -1 and end != -1:
        # Extract the text between the markers
        extracted_text = full_text[start+len(start_marker):end]
        print(extracted_text)
    else:
        print("Markers not found in the text.")
else:
    print("No input element with the name 'text' found.")