Created
February 1, 2012 19:28
-
-
Save alexshpilkin/1718782 to your computer and use it in GitHub Desktop.
Turkish elections
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 | |
# --------------------------------------------------------------------------- | |
# download.py - Download Turkish election data | |
# | |
# Written by Alexander Shpilkin <ashpilkin@gmail.com>, Feb 2012 | |
# | |
# To the extent possible under law, the author has dedicated all copyright | |
# and related and neighboring rights to this software to the public domain | |
# worldwide. This software is distributed without any warranty. | |
# | |
# See <http://creativecommons.org/publicdomain/zero/1.0/> for the complete | |
# text of the CC0 Public Domain Dedication. | |
# --------------------------------------------------------------------------- | |
from sys import stdout | |
import os.path | |
from shutil import copyfileobj | |
from bs4 import BeautifulSoup | |
from http.cookiejar import CookieJar | |
import urllib.request | |
from urllib.parse import urlencode | |
def progress(fmt, *args, **named): | |
if hasattr(stdout, 'isatty') and stdout.isatty(): | |
print('\r\033[2K' + fmt.format(*args, **named), end='') | |
else: | |
print(fmt.format(*args, **named), end=('' if fmt.endswith('\n') else None)) | |
stdout.flush() | |
def fnescape(filename): | |
return filename.replace('/', '_SLASH_') | |
PAGE_URL = 'https://sonuc.ysk.gov.tr/module/sonuc.jsf' | |
FORCE = False | |
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(CookieJar())) | |
opener.addheaders.append(('Referer', PAGE_URL)) | |
progress("[*] Fetching district list") | |
with opener.open(PAGE_URL) as response: | |
root_soup = BeautifulSoup(response.read()) | |
districts = ((tag.string.title(), tag['value']) for tag | |
in root_soup.find(id='j_id41:j_id42:j_id62:cmbSecimCevresi')('option')[1:]) | |
empty_terrs = [] | |
for dname, dvalue in districts: | |
params = { | |
'AJAXREQUEST': '_viewRoot', | |
'j_id41': 'j_id41', | |
'j_id41:j_id42:j_id110:inputSandikBas': '', | |
'j_id41:j_id42:j_id119:inputSandikBit': '', | |
'j_id41:j_id42:j_id46:sandikTuruRadio': 0, | |
'j_id41:j_id42:j_id62:cmbSecimCevresi': dvalue, | |
'j_id41:j_id42:j_id62:j_id71': 'j_id41:j_id42:j_id62:j_id71', | |
'j_id41:j_id42:j_id86:cmbMahalle': '', | |
'javax.faces.ViewState': root_soup.find(id='javax.faces.ViewState')['value'] | |
} | |
progress("[*] {0}: Fetching territory list", dname) | |
with opener.open(PAGE_URL, urlencode(params).encode('latin-1')) as response: | |
ajax_soup = BeautifulSoup(response.read()) | |
del params['j_id41:j_id42:j_id62:j_id71'] | |
terrs = ((tag.string.title(), tag['value']) for tag | |
in ajax_soup.find(id='j_id41:j_id42:j_id97:cmbIlceSecimKurulu')('option')[1:]) | |
for tname, tvalue in terrs: | |
filename = '{0} - {1}.xls'.format(fnescape(dname), fnescape(tname)) | |
if not FORCE and os.path.exists(filename): | |
progress("[+] {0}/{1}: Cached in \"{2}\"", dname, tname, filename) | |
continue | |
params['j_id41:j_id42:j_id97:cmbIlceSecimKurulu'] = tvalue | |
params['j_id41:j_id42:j_id97:j_id106'] = 'j_id41:j_id42:j_id97:j_id106' | |
progress("[*] {0}/{1}: (1/3) Selecting territory", dname, tname) | |
with opener.open(PAGE_URL, urlencode(params).encode('latin-1')) as response: | |
response.read() | |
del params['j_id41:j_id42:j_id97:j_id106'] | |
params['j_id41:j_id42:j_id131'] = 'j_id41:j_id42:j_id131' | |
progress("[*] {0}/{1}: (2/3) Fetching results", dname, tname) | |
with opener.open(PAGE_URL, urlencode(params).encode('latin-1')) as response: | |
data_soup = BeautifulSoup(response.read()) | |
del params['j_id41:j_id42:j_id131'] | |
link_elt = data_soup.find(id='j_id41:tabloBilgileriPanel:excelLink') | |
if 'href' in link_elt.attrs: | |
excel_url = 'https://sonuc.ysk.gov.tr' + link_elt['href'] | |
progress("[*] {0}/{1}: (3/3) Downloading Excel report", dname, tname) | |
with opener.open(excel_url) as response, open(filename, 'wb') as output: | |
copyfileobj(response, output) | |
progress("[+] {0}/{1}: Saved to \"{2}\"\n", dname, tname, filename) | |
else: | |
empty_terrs.append("{0}/{1}".format(dname, tname)) | |
progress("[-] {0}/{1}: Warning: No data available\n", dname, tname) | |
progress("[+] {0}: Download complete\n", dname) | |
progress("[+] Download complete\n") | |
for terr in empty_terrs: | |
progress("[-] Warning: No data for {0}\n".format(terr)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment