Obtener correos de gente que puede hacer el Certificado de Eficiencia Energética

cee.py

from web import Web
import re
import urllib3
import bs4
from urllib.parse import urlparse
from urllib.parse import parse_qs
import base64

urllib3.disable_warnings()


class GetMails(Web):
    def __init__(self, *args, **kvargs):
        super().__init__(*args, verify=False, **kvargs)
        self._mails = set()

    def start(self):
        pass

    def next(self):
        pass

    def page(self):
        pass

    def mails(self):
        url = self.start()
        if isinstance(url, str):
            self.get(url)
        while True:
            for m in self.page():
                if m and "@" in m:
                    self._mails.add(m.lower())
            url = self.next()
            if url is None:
                break
            if isinstance(url, bs4.Tag):
                url = url.attrs["href"]
            if isinstance(url, str):
                self.get(url)
        mails = sorted(self._mails)
        print(";".join(mails))
        return mails


class IG(GetMails):
    def start(self):
        url = "https://portal.coiim.es/servicios/certificacion-energetica/listado-de-certificadores/madrid"
        print("Ingenieros industriales")
        print(url)
        return url

    def page(self):
        mails = set()
        for mail in self.soup.select("ul.social-networks2 a"):
            mail = mail.attrs["href"].strip()
            mail = mail.split(":")[-1]
            yield mail
        return mails

    def next(self):
        return self.soup.select_one("li.next a")


class AP(GetMails):
    def start(self):
        url = "https://www.aparejadoresmadrid.es/zona-ciudadanos/listado-expertos-certificacion"
        print("Aparejadores")
        print(url)
        self.get(url)
        f_select = "section form"
        f = self.soup.select_one(f_select)
        f = f.find("input", id=re.compile(r".*valor-POBLACION.*"))
        action, data = self.prepare_submit(f_select)
        data[f.attrs["name"]][-2] = "Madrid"
        self.get(action, **data)

    def page(self):
        for mail in self.soup.select("p.CA_nombre"):
            mail = mail.get_text().strip()
            yield mail.split()[-1]

    def next(self):
        a = self.soup.select_one("div.ir-siguiente-pag")
        if a:
            return a.find_parent("a")


class AR(GetMails):
    def start(self):
        print("Arquitectos")
        print("https://www.coam.org/es/red-arquitectos")
        self.get("https://www.coam.org/es/red-arquitectos/resultado-busqueda", **{
            "especialidad": [20]
        })

    def page(self):
        urls = set()
        for a in self.soup.select("td.nombre a"):
            a = a.attrs["href"]
            if "/ficha/" in a:
                urls.add(a)
        for a in sorted(urls):
            self.get(a)
            for img in self.soup.findAll("img", src=re.compile(r".*/g_Image\.php\?email.*")):
                mail = img.attrs["src"]
                mail = parse_qs(urlparse(mail).query)['email'][0]
                mail = mail.encode('ascii')
                mail = base64.b64decode(mail)
                mail = mail.decode('ascii')
                yield mail


mails = set()
mails = mails.union(IG().mails())
mails = mails.union(AP().mails())
mails = mails.union(AR().mails())
mails = sorted(mails)

print("")
print("Todos")
print(*mails)