Last active
September 11, 2016 00:34
-
-
Save souenzzo/4ab9ffc78677a7b30a092f3c96a284a5 to your computer and use it in GitHub Desktop.
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
#!/usr/bin/env python3 | |
from http import client | |
from bs4 import BeautifulSoup | |
def getElems(tr): | |
res = [] | |
for th in tr: | |
if th.string != "\n": | |
res.append(th.string) | |
return res | |
def structuralize(table): | |
struct = [] | |
titles = getElems(table.thead.tr) | |
for elem in table.tbody: | |
if elem != "\n": | |
coisa = getElems(elem) | |
struct.append(dict(zip(titles,coisa))) | |
return struct | |
def getInfo(soup): | |
table = soup.find(id="table_disciplinas") | |
return structuralize(table) | |
def nextPage(soup): | |
pag = soup.find_all("a", "next_page") | |
if pag == []: | |
return False | |
return True | |
def get_data(periodo, curso): | |
conn = client.HTTPSConnection("sistemas.uff.br") | |
BASE='/transparencia/disciplinas_que_mais_reprovam' | |
page = 1 | |
data = { "periodo": periodo, | |
"curso": curso, | |
"disciplinas": [] } | |
while True: | |
PATH="%s?page=%d&periodo=%d&curso=%d"%(BASE,page,periodo,curso) | |
conn.request("GET", PATH) | |
res = conn.getresponse() | |
raw = res.read() | |
soup = BeautifulSoup(raw, "html.parser") | |
info = getInfo(soup) | |
data["disciplinas"].extend(info) | |
page = page + 1 | |
if not nextPage(soup): | |
break | |
return data | |
if __name__ == "__main__": | |
db = { "nome": "disciplinas", | |
"data": [] | |
} | |
for ano in range(1999, 2017): ## anos | |
for semestre in [1,2]: ## Semestres | |
for curso in range(200): ## cursos | |
try: | |
periodo = (ano * 10) + semestre | |
x = get_data(20152, 25) | |
except: | |
pass | |
else: | |
db["data"].append(x) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment