From 95bdf54ad02efdb3ad3a5e3d1e170531064d6501 Mon Sep 17 00:00:00 2001
From: Aleksey Lobanov <alekseylobanov1@gmail.com>
Date: Sun, 21 Feb 2016 02:45:43 +0300
Subject: [PATCH 1/4] Added group_ids_downloader

---
 group_ids_downloader.py | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)
 create mode 100644 group_ids_downloader.py

diff --git a/group_ids_downloader.py b/group_ids_downloader.py
new file mode 100644
index 0000000..cda13fe
--- /dev/null
+++ b/group_ids_downloader.py
@@ -0,0 +1,33 @@
+#!/usr/bin/python3
+# -*- coding: utf-8 -*- 
+'''
+group_ids_downloader.py VK_LOGIN VK_PASSWORD APP_ID INPUT_FILENAME
+where INPUT_FILENAME is file with one id of group per line
+'''
+import sys
+
+import vk_api
+
+def getIdsByGroup(group_id):
+    ids = []
+    res = vk.method("groups.getMembers", {"group_id":group_id,"count":1000})
+    count = res['count'] - 1000
+    ids += res['items']
+    cur_offset = 1000
+    while count > 0:
+        res = vk.method("groups.getMembers", {"group_id":group_id,
+            "count":1000,"offset":cur_offset, "sort":"id_asc"})
+        count = count - 1000
+        cur_offset += 1000
+        ids += res['items']
+    return ids
+
+vk_login, vk_password = sys.argv[1], sys.argv[2]
+vk = vk_api.VkApi(vk_login, vk_password, app_id=sys.argv[3])
+
+vk.authorization()
+
+for group_id in open(sys.argv[4]):
+    group_id = group_id.strip()
+    good_ids = getIdsByGroup(group_id)
+    open('out/' + str(group_id),'w').write('\n'.join([str(i) for i in good_ids]))

From 676f110b481766459dd10b3b967c495f755a408e Mon Sep 17 00:00:00 2001
From: Aleksey Lobanov <alekseylobanov1@gmail.com>
Date: Sun, 21 Feb 2016 02:54:15 +0300
Subject: [PATCH 2/4] Added list with group ids

---
 full_group_list | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)
 create mode 100644 full_group_list

diff --git a/full_group_list b/full_group_list
new file mode 100644
index 0000000..cf672d8
--- /dev/null
+++ b/full_group_list
@@ -0,0 +1,39 @@
+district_kents
+moi_raen_18
+po_rayonu
+public35574958
+nas.rayon
+chanson_best
+club41978736
+publicvor
+ceny_brat
+truephilosophy
+public42291448
+bratva_vsegda_ryadom
+bratzasestry
+justformens
+ceny_life
+philosophy_brother
+oo_brat_oo
+public53664903
+myzhskoi_style
+public102976872
+brat_feed
+pa_canskye
+ygapaem
+zalipaay
+brat_bratka777
+club52395272
+noooool
+yavolna
+duha.pacana
+pacanskie2015
+po.pacansky
+tyt_co_cmislom
+pa.cany
+parnipy
+public41324287
+taz.reshaet
+heartoftheman
+tazysosnooly
+vaz.club
\ No newline at end of file

From d015935a8fcefea588f2a4c921c4325acf035d9e Mon Sep 17 00:00:00 2001
From: Aleksey Lobanov <alekseylobanov1@gmail.com>
Date: Sun, 21 Feb 2016 02:56:12 +0300
Subject: [PATCH 3/4] Added script for union of groups

---
 all_good_ids.py | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)
 create mode 100644 all_good_ids.py

diff --git a/all_good_ids.py b/all_good_ids.py
new file mode 100644
index 0000000..ddcca1f
--- /dev/null
+++ b/all_good_ids.py
@@ -0,0 +1,18 @@
+#!/usr/bin/python
+# -*- coding: utf-8 -*- 
+
+import sys
+import os
+from os.path import join
+
+all_ids = set()
+
+for dirpath, dirnames, filenames in os.walk(sys.argv[1]):
+    for f in filenames:
+        fp = os.path.join(dirpath, f)
+        for uid in open(fp):
+            all_ids.add(int(uid))
+
+f_out = open(sys.argv[2],'w')
+for uid in all_ids:
+    f_out.write(str(uid) + '\n')

From 591478a2c008eef9a8777568867afe7c5fd416f1 Mon Sep 17 00:00:00 2001
From: Aleksey Lobanov <alekseylobanov1@gmail.com>
Date: Sun, 21 Feb 2016 13:06:52 +0300
Subject: [PATCH 4/4] We build json with freqs of ids

---
 all_good_ids.py | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/all_good_ids.py b/all_good_ids.py
index ddcca1f..0f937ff 100644
--- a/all_good_ids.py
+++ b/all_good_ids.py
@@ -2,17 +2,21 @@
 # -*- coding: utf-8 -*- 
 
 import sys
+import json
 import os
 from os.path import join
 
-all_ids = set()
+all_ids = {}
 
 for dirpath, dirnames, filenames in os.walk(sys.argv[1]):
     for f in filenames:
         fp = os.path.join(dirpath, f)
         for uid in open(fp):
-            all_ids.add(int(uid))
+            uid = int(uid)
+            if uid in all_ids:
+                all_ids[uid] += 1
+            else:
+                all_ids[uid] = 1
 
 f_out = open(sys.argv[2],'w')
-for uid in all_ids:
-    f_out.write(str(uid) + '\n')
+f_out.write(json.dumps(all_ids))