class Crawler:
""" Classe para crawler. """
def __init__(self, url, character, downloader):
self.downloader = downloader
self.url = url
self.parser = Parser()
self.get_url_information(character)
def get_url_information(self, character):
""" Monta a URL para recuperar as informações. """
url = urljoin(self.url, 'community/?subtopic=characters')
params = self.config_params(character)
response = self.downloader.post(url, data=params)
if self.parser.character_not_found(response.text):
parsed = self.parser.parse(response.text)
self.save_data(parsed.__dict__)
return parsed
@staticmethod
def config_params(character):
""" Cria dicionário para guardar informações do submit. """
return {'name': character, 'x': 0, 'y': 0}
@staticmethod
def save_data(data):
""" Salva informações coletadas em arquivo json. """
name = data.get('name').lower().replace(' ', '_')
with open(f'./proj/database/{name}.json', 'w', encoding='utf-8') as f:
json.dump(data, f)
print(f'Personagem {name} foi salvo com sucesso!')
def __init__(self, url, character, downloader):
self.downloader = downloader
self.url = url
self.parser = Parser()
self.get_url_information(character)
def test_not_found(snapshot, not_found_html):
confirmation = Parser().character_not_found(not_found_html)
assert not confirmation
def test_extract_account_status(snapshot, resume_html):
parsed = BeautifulSoup(resume_html, 'html.parser')
text = Parser().extract_value(parsed, 'Account Status:')
snapshot.assert_match(text)
def test_extract_deaths(snapshot, resume_html):
parsed = BeautifulSoup(resume_html, 'html.parser')
deaths = Parser().extract_deaths(parsed)
for death in deaths:
snapshot.assert_match(death)
def test_extract_last_login(snapshot, resume_html):
parsed = BeautifulSoup(resume_html, 'html.parser')
# Usou método específico.
text = Parser().extract_last_login(parsed, 'Last Login:')
snapshot.assert_match(text)
def test_extract_residence(snapshot, resume_html):
parsed = BeautifulSoup(resume_html, 'html.parser')
text = Parser().extract_value(parsed, 'Residence:')
snapshot.assert_match(text)
def test_extract_achievement(snapshot, resume_html):
parsed = BeautifulSoup(resume_html, 'html.parser')
text = Parser().extract_value(parsed, 'Achievement Points:')
snapshot.assert_match(text)
def test_extract_vocation(snapshot, resume_html):
parsed = BeautifulSoup(resume_html, 'html.parser')
text = Parser().extract_value(parsed, 'Vocation:')
snapshot.assert_match(text)
def test_extract_former_name(snapshot, resume_html):
parsed = BeautifulSoup(resume_html, 'html.parser')
text = Parser().extract_value(parsed, 'Former Names:')
snapshot.assert_match(text)