riobus.py

import requests

if __name__ == "__main__":
    payload = {
        'texto_consulta': 154
    }

    #r = requests.post('http://vadeonibus.com.br/vadeonibus/' +
    #'index.php?d=abrangencia&lang=pt-br',
    #                 data=payload)
    #url = 'http://www.vadeonibus.com.br/vadeonibus/abrangencia_dados.php?ac=con_l&lang=pt-br&consulta=%d'

    index_url = 'http://www.vadeonibus.com.br/vadeonibus/abrangencia_dados.php?ac=con_l&lang=pt-br'
    r = requests.get(index_url)

    from bs4 import BeautifulSoup
    soup = BeautifulSoup(r.text)

    urls = [s['href'] for s in soup.find_all('a')]

    f = open('content.txt', 'wt')
    for u in urls:
        f.write(u+'\n')
    f.close()

    r = requests.get('http://www.vadeonibus.com.br/vadeonibus/' + urls[0])

    trajeto = BeautifulSoup(r.text)
   
    ruas = [rua for rua in trajeto.table.find_all('tr')]

    for r in ruas:
        v = r.find_all('td')
        if len(v) > 1:
            print r.find_all('td')[1]