Function 'check_proxy_list' which checks anonimity of each proxy contained in a list of named tuples. Proxies are checked by using the 'check_proxy' function.

load_proxies.py

@@ -2,6 +2,7 @@ import csv
 import requests
 import time
 from collections import namedtuple
+from colorama import Fore, Style
 
 """
 A function which loads proxies from a .csv file, to a list.
@@ -42,4 +43,54 @@ def check_proxy(proxy_ip, proxy_port, protocol):
         else:
             return False
     except Exception:
-        return False
+        return False
+
+
+"""
+A function which takes in one mandatory argument -> a proxy list in
+the format returned by the function 'load_proxies_from_csv'.
+    
+It also takes an optional argument 'max_proxies', if the user wishes to
+cap the number of validated proxies.
+
+Each proxy is tested by the check_proxy function. Since each test is done on 
+'wikipedia.org', in order to be considerate to Wikipedia servers, we are not using any async modules, 
+but are sending successive requests each separated by at least 1 sec.
+
+Outputs: list containing proxies stored in named tuples. 
+"""
+
+
+from colorama import Fore, Style
+
+def check_proxy_list(proxy_list, max_proxies=None):
+    print((Style.BRIGHT + Fore.GREEN + "[" +
+           Fore.YELLOW + "*" +
+           Fore.GREEN + "] Started checking proxies."))
+    working_proxies = []
+
+    # If the user has limited the number of proxies we need,
+    # the function will stop when the working_proxies
+    # loads the max number of requested proxies.
+    if max_proxies != None:
+        for proxy in proxy_list:
+            if len(working_proxies) < max_proxies:
+                time.sleep(1)
+                if check_proxy(proxy.ip,proxy.port,proxy.protocol) == True:
+                    working_proxies.append(proxy)
+            else:
+                break
+    else:
+        for proxy in proxy_list:
+            time.sleep(1)
+            if check_proxy(proxy.ip,proxy.port,proxy.protocol) == True:
+                working_proxies.append(proxy)
+
+    if len(working_proxies) > 0:
+        print((Style.BRIGHT + Fore.GREEN + "[" +
+               Fore.YELLOW + "*" +
+               Fore.GREEN + "] Finished checking proxies."))
+        return working_proxies
+
+    else:
+        raise Exception("Found no working proxies.")