Created
November 23, 2016 10:31
-
-
Save javierhonduco/96533fbd69a5a4a3b48e758045bc07e9 to your computer and use it in GitHub Desktop.
classroom_stats.py
This file contains 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
import requests | |
import json | |
from bs4 import BeautifulSoup | |
config = { | |
'login_url': 'https://carpa.aig.uc3m.es/validacion.asp', | |
'user': '', | |
'password': '' | |
} | |
classrooms = { | |
'biblio': 'https://carpa.aig.uc3m.es/OcupacionTR/OcupacionTR.asp?campus=B&edificio=Po&nombrecampus=Biblioteca&nombreedificio=Polit%E9cnica&nombreaula=Todas&descrip=Ocupaci%F3n+de+las+aulas', | |
'juan_benet': 'https://carpa.aig.uc3m.es/OcupacionTR/OcupacionTR.asp?campus=L&edificio=07&nombrecampus=Legan%E9s&nombreedificio=Juan%20Benet&nombreaula=Todas&descrip=Ocupaci%F3n+de+las+aulas', | |
'torres_quevedo': 'https://carpa.aig.uc3m.es/OcupacionTR/OcupacionTR.asp?campus=L&edificio=04&nombrecampus=Legan%E9s&nombreedificio=Torres%20Quevedo&nombreaula=Todas&descrip=Ocupaci%F3n+de+las+aulas', | |
'betancourt': 'https://carpa.aig.uc3m.es/OcupacionTR/OcupacionTR.asp?campus=L&edificio=01&nombrecampus=Legan%E9s&nombreedificio=Agust%EDn%20de%20Betancourt&nombreaula=Todas&descrip=Ocupaci%F3n+de+las+aulas', | |
'aggr': 'https://carpa.aig.uc3m.es/EstadisticaDiaria/estadistica_diaria.asp?mes=5&anio=2015&nombrecampus=Todos&nombreedificio=Todos&nombreaula=Todas&descrip=Estad%EDstica+diaria+de+uso' | |
} | |
payload = {'Usuario': config['user'], 'Clave': config['password']} | |
class Occupation: | |
def __init__(self, payload): | |
self.s = requests.Session() | |
self.s.post(config['login_url'], data=payload) | |
def retrieve_occupation(self, url): | |
response = self.s.get(url) | |
return response.text | |
def parse_table(self, html): | |
table = [] | |
soup = BeautifulSoup(html.encode('iso-8859-1'), 'html.parser') | |
for tables in soup.find_all('table'): | |
trs_t = [] | |
for trs in tables.find_all('tr'): | |
tds_t = [] | |
for tds in trs.find_all('td'): | |
if not tds.text.startswith('\n'): | |
tds_t.append(tds.text) | |
trs_t.append(filter(None, tds_t)) | |
table.append(filter(None, trs_t)) | |
return filter(None, table) | |
def hashify(self, table): | |
aulas = table[1][1:] | |
datos = [] | |
for aula in aulas: | |
datos.append({ | |
aula[0]: { | |
'libres': int(aula[1]), | |
'total': int(aula[1])+int(aula[2]) | |
} | |
}) | |
hash = { | |
'campus': table[0][1][0], | |
'edificio': table[0][1][1], | |
'aula': table[0][1][2], | |
'aulas': datos | |
} | |
return hash | |
if __name__ == '__main__': | |
oc = Occupation(payload) | |
result = oc.retrieve_occupation(classrooms['torres_quevedo']) | |
parsed_table = oc.parse_table(result) | |
hash = oc.hashify(parsed_table) | |
print json.dumps(hash) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment