Created
March 11, 2020 09:17
-
-
Save kkprakasa/ba5e8426076d85dc9ab3134f5ac8d435 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
ik = idm.find({}).distinct('id_desa') | |
key0 = ['Indeks_komposit','Dimensi','skor','Nilai','Perangkat_Indikator','skor_1','Nilai_1','Indikator_peritem','skor_2','kosong','eksisting_dari_indikator_umum','Kewenangan_pusat','Kewenangan_provinsi','Kewenangan_kabupaten','Kewenangan_desa','Kewenangan_sosial_alami'] | |
for u in idmy.find({},{'_id':0}): #sort descending | |
if u['id_desa'] not in ik : | |
print('mengunduh %s' % u['detail']) | |
url0 = root+u['detail'].split('"')[1] | |
n=ambil(url) | |
kkk=[] | |
try: | |
for i in n.findAll('div',{'class':'row'})[1].findAll('tr')[2:]: | |
kk = [j.text.replace('\n','').strip() for j in i.findAll('td')] | |
if len(kk) <16: | |
kk = kkk[-1][16:(32-len(kk))] + kk # menyelesaikan permasalahan jumlah kolom yang tidak sama | |
kk = kk[:-5] + [j['src'].split('/')[-1].replace('.png','') for j in i.findAll('img')] | |
kk = list(u.values())+kk | |
kkk.append(kk) | |
except: | |
kk = list(u.values()) | |
# kk.insert() | |
kkk.append(kk) | |
key1 = list(u.keys())+key0 #gabungkan list buat bikin key | |
for l in kkk: | |
data = dict(zip(key1,l)) | |
#dt.append(data) | |
#if idm.find_one({'id_desa': data['id_desa']},{'id_desa':1,'_id':0}) is None : | |
tqdm(idm.insert_one(data)) | |
ik.append(u['id_desa']) | |
else: | |
print('data id %s sudah tersedia' % u['id_desa']) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment