Last active
June 6, 2017 16:19
-
-
Save walison17/c4eabc5930d3350bd12ba3d2b6ad383a to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def pesquisar(self, parametro: str, por_pagina=24, idioma='pt-br', tipo='todos', | |
| exibir_sugestoes=True): | |
| contador = 0 | |
| pagina = self._pagina(por_pagina) | |
| urls = [ | |
| f'{self.URL}/legenda/busca/{parametro}/1/-/{p}/-' for p in range(pagina + 1) | |
| ] | |
| reqs = [requests.get(url=u, headers=self.HEADERS) for u in urls] | |
| def _definir_limite(contador: int, por_pagina: int): | |
| if por_pagina > self.QUANT_LEGENDAS_POR_PAGINA: | |
| return por_pagina - contador | |
| return self.QUANT_LEGENDAS_POR_PAGINA | |
| for r in reqs: | |
| if r.status_code == 200: | |
| s = self._soup(r.text) | |
| resultados_html = s.find_all('a', limit=_definir_limite(contador, por_pagina), | |
| href=re.compile(r'/download/[\d\w_.]*')) | |
| for res in resultados_html: | |
| titulo = res.find_previous('p').text | |
| link = f'{self.URL}{res["href"]}' | |
| cod = re.search(r'download\/(?P<cod>[\d\w]*)', link).group('cod') | |
| legenda = Legenda(cod, titulo, link) | |
| yield legenda | |
| contador += 1 | |
| def _pagina(self, por_pagina: int): | |
| if por_pagina == self.QUANT_LEGENDAS_POR_PAGINA: | |
| return 0 | |
| return int((por_pagina / self.QUANT_LEGENDAS_POR_PAGINA)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment