72 lines
2.8 KiB
Python
72 lines
2.8 KiB
Python
"""
|
|
Scraper JUCERN — Junta Comercial do Estado do Rio Grande do Norte
|
|
URL: http://www.jucern.rn.gov.br/Conteudo.asp?TRAN=ITEM&TARG=8695&ACT=&PAGE=0&PARM=&LBL=Leiloeiros
|
|
Método: httpx (HTTP sem TLS — site usa HTTP apenas)
|
|
Nota: URL com parâmetros de query é a página correta de leiloeiros.
|
|
Usar HTTP (não HTTPS). Referenciado em FENAJU e InnLei como ativo.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
from typing import List
|
|
|
|
from .base_scraper import AbstractJuntaScraper, Leiloeiro
|
|
|
|
|
|
class JucernScraper(AbstractJuntaScraper):
|
|
estado = "RN"
|
|
junta = "JUCERN"
|
|
url = "http://www.jucern.rn.gov.br/Conteudo.asp?TRAN=ITEM&TARG=8695&ACT=&PAGE=0&PARM=&LBL=Leiloeiros"
|
|
|
|
async def parse_leiloeiros(self) -> List[Leiloeiro]:
|
|
soup = await self.fetch_page()
|
|
if not soup:
|
|
# Tenta domínio sem www
|
|
soup = await self.fetch_page(url="http://jucern.rn.gov.br/Conteudo.asp?TRAN=ITEM&TARG=8695&ACT=&PAGE=0&PARM=&LBL=Leiloeiros")
|
|
if not soup:
|
|
soup = await self.fetch_page_js(wait_ms=3000)
|
|
if not soup:
|
|
return []
|
|
|
|
results: List[Leiloeiro] = []
|
|
|
|
for table in soup.find_all("table"):
|
|
rows = table.find_all("tr")
|
|
if len(rows) < 2:
|
|
continue
|
|
headers = [self.clean(th.get_text()) for th in rows[0].find_all(["th", "td"])]
|
|
col = {(h or "").lower(): i for i, h in enumerate(headers)}
|
|
|
|
def gcol(cells, frags):
|
|
for k, i in col.items():
|
|
if any(f in k for f in frags) and i < len(cells):
|
|
return self.clean(cells[i].get_text())
|
|
return None
|
|
|
|
for row in rows[1:]:
|
|
cells = row.find_all(["td", "th"])
|
|
if not cells:
|
|
continue
|
|
nome = gcol(cells, ["nome", "leiloeiro"]) or self.clean(cells[0].get_text())
|
|
if not nome or len(nome) < 3:
|
|
continue
|
|
results.append(self.make_leiloeiro(
|
|
nome=nome,
|
|
matricula=gcol(cells, ["matr", "registro", "nº"]),
|
|
situacao=gcol(cells, ["situ", "status"]),
|
|
municipio=gcol(cells, ["munic", "cidade"]) or "Natal",
|
|
telefone=gcol(cells, ["tel", "fone"]),
|
|
email=gcol(cells, ["email"]),
|
|
endereco=gcol(cells, ["ender", "logr"]),
|
|
data_registro=gcol(cells, ["data", "posse"]),
|
|
))
|
|
if results:
|
|
break
|
|
|
|
if not results:
|
|
for el in soup.select("td, li, p"):
|
|
text = self.clean(el.get_text())
|
|
if text and len(text) > 10 and any(c.isupper() for c in text[:20]):
|
|
results.append(self.make_leiloeiro(nome=text, municipio="Natal"))
|
|
|
|
return results
|