SeVaLaLuz.py 文件源码

def scrap_twitlonger(twitlonger):
    ''' 
        Takes a twitlonger post ID, scraps the body of the post
        and then returns a string depending on the contents of 
        the post. If the hour is stated in said post, it's added
        If it's not, then it's implied it's current time.

        Note to self: Implement GMT - whatever our president
        decides to change it to.
    '''
    page = requests.get('http://www.twitlonger.com/show/%s' %twitlonger)
    tree = html.fromstring(page.content)
    texto = tree.xpath('/html/body/div[2]/div[1]/div[3]/div/p[1]/text()')
    hora = re.search('[0-9]+:[0-9]+',texto[0])
    circuitos = texto[0].split(str('detallados a continuación: ').decode('utf-8'))[1].split(str(' #ElNiñoNoEsJuego').decode('utf-8'))[0]
    if hora:
        return "La luz se ira a las " + hora.group(0) + " en " + circuitos
    else:
        hora = re.search('En momentos',texto[0])
        if hora:
            return "La luz se ira a las " + str(datetime.datetime.now().time()) + " en " + circuitos