Skip to content

Ahora también extrae los requisitos de los cursos y los guarda en un JSON. También agrega unos pocos fixs para poder hacer crawl fuera de periodo de pucmatico #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
dmerrill6 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Ahora también extrae los requisitos de los cursos y los guarda en un JSON. También agrega unos pocos fixs para poder hacer crawl fuera de periodo de pucmatico #1

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
88 changes: 59 additions & 29 deletions crawler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,13 +6,16 @@
#aa='http://dsrd.uc.cl/dara/libcursos/periodo21/ua6_0.html'

N_cursos = 100
url_root = 'http://dsrd.uc.cl/dara/libcursos/periodo22/'
url_root = 'http://dsrd.uc.cl/dara/libcursos/periodo21/'
file_root = 'ua'
titles = ['N','sigla','seccion','creditos','nombre','min','opt','ofg','profesores','horario','actividad','salas','campus','titulos']
titlesFueraPeriodo = ['N','sigla','seccion','creditos','nombre','vac', 'profesores', 'horario', 'actividad', 'salas', 'campus', 'titulos']
#titles = ['N','sigla','seccion','creditos','nombre','vac','profesores','horario','actividad','salas','campus','titulos']
multiples = ['profesores','horario','actividad','salas']
otherUA = []#['bachhu','bachcs']
courses = []
requisitos = {}
esTemporadaInscripcion = False

def get_course(sigla):
for c in courses:
Expand All @@ -22,7 +25,6 @@ def get_course(sigla):

def start():
for ua in otherUA + range(1,N_cursos + 1):

page = 0
aux = 0
if(ua == 9):
Expand All @@ -31,7 +33,6 @@ def start():
else:
offset = 0
lastN = 30

if(ua in otherUA):
offset = -1

Expand All @@ -40,10 +41,10 @@ def start():
url = '%s%s%s'%(url_root,ua,'.html')
else:
url = '%s%s%s%s%s%s'%(url_root,file_root,ua,'_',page,'.html')

f = urllib.urlopen(url)
response_code = f.getcode()

print url
if(response_code != 200 or lastN < 25):
break

Expand All @@ -61,13 +62,11 @@ def start():

def parse(html,offset):
soup = bs4.BeautifulSoup(html)
f = soup.find_all('tr')
if(len(f) < 11):
courses = soup.find_all('tr', recursive=False)[:-3]
if(len(courses) < 11):
return 0
table = f[10+offset]
courses = table.find_all('tr')[1:]
i = 0
for course in courses[1:]:
for course in courses:
parseCourse(course)
i = i + 1
return i
Expand All @@ -77,21 +76,26 @@ def parseCourse(soup):
i = 0
aux = {}
raw = {}
title_array = titles
if(esTemporadaInscripcion == False):
title_array = titlesFueraPeriodo
for td in soup.find_all('td'):
data = td.text
if(titles[i] in multiples):
if(title_array[i] in multiples):
data = td.find_all(text=True)
aux[titles[i]] = data
aux[title_array[i]] = data
i = i + 1
continue
raw[titles[i]] = data
raw[title_array[i]] = data
i = i + 1
#print(raw)
seccion = {}
#seccion['vac'] = raw['vac']
seccion['min'] = raw['min']
seccion['opt'] = raw['opt']
seccion['ofg'] = raw['ofg']
if(esTemporadaInscripcion):
seccion['min'] = raw['min']
seccion['opt'] = raw['opt']
seccion['ofg'] = raw['ofg']
else:
seccion['vac'] = raw['vac']
seccion['seccion'] = raw['seccion']
seccion['campus'] = raw['campus']

Expand Down Expand Up @@ -152,7 +156,7 @@ def startDesc():
curso = {}
curso['sigla'] = sigla
courses.append(curso)
curso['descripcion'] = str(p)
curso['descripcion'] = p.text
#cursos.append(curso)
#print('encontrados %d cursos')%(len(cursos))
i = i + 1
Expand All @@ -162,15 +166,40 @@ def startDesc():
#######################################################

def startReq():
f = open('req/output2.json').read()
reqs = json.loads(f)
f = open('output2.json').read()
courses = json.loads(f)
print "Procesando requisitos, esto puede tomar varios minutos..."
root_url = "https://www2.puc.cl/ControlPrerrequisitos/jsp/RequisitosAsign.jsp?SIGLA="
i = 0
for c in courses:
if i % 100 == 0:
print str(i) + "/" + str(len(courses)) + " cursos procesados."
url = '%s%s'%(root_url, c['sigla'])
html = urllib.urlopen(url).read()
soup = bs4.BeautifulSoup(html)
tds = soup.find_all("td", {"class" : "td"})
course_reqs = []
for td in tds:
if (td.contents[0]['class'][0] != u"html_tipo_requisito"):
continue
curr_req = {}
tipo_requisito = td.find_all("font", {"class" : "html_tipo_requisito"})[0].text
if tipo_requisito == "Requisitos que todos los alumnos deben cumplir.":
tipo_requisito = "Todos"
curr_req["alumnos"] = tipo_requisito
texts = td.find_all("font", {"class" : "html_texto_azul"})
curr_req["requisitos"] = texts[0].text
curr_req["requisitos_especiales"] = texts[-1].text
course_reqs.append(curr_req)

requisitos[c['sigla']] = course_reqs
i = i + 1


#######################################################
#####################Flujo Programa####################
#######################################################

for r in reqs:
sigla = r['sigla']
curso = get_course(sigla)
if curso == None:
continue
curso['requisitos'] = r['req']

start()
print 'Total cursos: \t\t%s'%(len(courses))
Expand All @@ -182,11 +211,12 @@ def startReq():
print 'Total cursos: \t\t%s'%(len(courses))
f = open('output2.json','w')
f.write(json.dumps(courses,sort_keys=True))
startReq()
f.close()

startReq()
print 'Total cursos: \t\t%s'%(len(courses))
f = open('output3.json','w')
f.write(json.dumps(courses,sort_keys=True))
f = open('requisitos.json','w')
f.write(json.dumps(requisitos,sort_keys=True))
f.close()

f = open('output3.json','r')
Expand Down