Add basic schema

sherlock/resources/data.json

@@ -1,4 +1,5 @@
 {
+  "$schema": "data.schema.json",
   "1337x": {
     "errorMsg": [
       "<title>Error something went wrong.</title>",
@@ -479,8 +480,7 @@
     "url": "https://codeforces.com/profile/{}",
     "urlMain": "https://codeforces.com/",
     "urlProbe": "https://codeforces.com/api/user.info?handles={}",
-    "username_claimed": "tourist",
+    "username_claimed": "tourist"
-    "username_unclaimed": "noonewouldeverusethis7"
   },
   "Codepen": {
     "errorType": "status_code",
@@ -1072,8 +1072,7 @@
     "errorUrl": "https://irc-galleria.net/users/search?username={}",
     "url": "https://irc-galleria.net/user/{}",
     "urlMain": "https://irc-galleria.net/",
-    "username_claimed": "appas",
+    "username_claimed": "appas"
-    "username_unclaimed": "noonewouldeverusethis77"
   },
   "Icons8 Community": {
     "errorType": "status_code",
@@ -1160,7 +1159,6 @@
   },
   "Jimdo": {
     "errorType": "status_code",
-    "noPeriod": "True",
     "regexCheck": "^[a-zA-Z0-9@_-]$",
     "url": "https://{}.jimdosite.com",
     "urlMain": "https://jimdosite.com/",
@@ -1334,8 +1332,7 @@
     "url": "https://monkeytype.com/profile/{}",
     "urlMain": "https://monkeytype.com/",
     "urlProbe": "https://api.monkeytype.com/users/{}/profile",
-    "username_claimed": "Lost_Arrow",
+    "username_claimed": "Lost_Arrow"
-    "username_unclaimed": "noonewouldeverusethis7"
   },
   "Motherless": {
     "errorMsg": "no longer a member",

sherlock/resources/data.schema.json

@@ -0,0 +1,60 @@
+{
+    "$schema": "https://json-schema.org/draft/2020-12/schema",
+    "title": "Sherlock Targets",
+    "description": "Social media target to probe for existence of usernames",
+    "type": "object",
+    "patternProperties": {
+        "^(?!\\$).*?$": {
+            "type": "object",
+            "required": [ "url", "urlMain", "errorType", "username_claimed" ],
+            "properties": {
+                "url": { "type": "string" },
+                "urlMain": { "type": "string" },
+                "urlProbe": { "type": "string" },
+                "username_claimed": { "type": "string" },
+                "regexCheck": { "type": "string" },
+                "isNSFW": { "type": "boolean" },
+                "headers": { "type": "object" },
+                "request_payload": { "type": "object" },
+                "tags": {
+                    "oneOf": [
+                        {
+                            "type": "string",
+                            "enum": [ "adult", "gaming" ]
+                        },
+                        {
+                            "type": "array",
+                            "items": {
+                                "type": "string",
+                                "enum": [ "adult", "gaming" ]
+                            }
+                        }
+                    ]
+                },
+                "request_method": {
+                    "type": "string",
+                    "enum": [ "GET", "POST", "HEAD" ]
+                },
+                "errorType": {
+                    "type": "string",
+                    "enum": [ "message", "response_url", "status_code" ]
+                },
+                "errorMsg": {
+                    "oneOf": [
+                        { "type": "string" },
+                        { "type": "array", "items": { "type": "string" } }
+                    ]
+                },
+                "errorCode": {
+                    "oneOf": [
+                        { "type": "integer" },
+                        { "type": "array", "items": { "type": "integer" } }
+                    ]
+                },
+                "errorUrl": { "type": "string" },
+                "response_url": { "type": "string" }
+            },
+            "additionalProperties": false
+        }
+    }
+}

sherlock/sites.py

@@ -152,6 +152,11 @@ class SitesInformation:
                 raise FileNotFoundError(f"Problem while attempting to access "
                                         f"data file '{data_file_path}'."
                                         )
+        
+        try:
+            site_data.pop('$schema')
+        except:
+            pass
 
         self.sites = {}
 

site_list.py

@@ -5,10 +5,14 @@ import json
 
 # Read the data.json file
 with open("sherlock/resources/data.json", "r", encoding="utf-8") as data_file:
-    data = json.load(data_file)
+    data: dict = json.load(data_file)
+
+# Removes schema-specific keywords for proper processing
+social_networks: dict = dict(data)
+social_networks.pop('$schema')
 
 # Sort the social networks in alphanumeric order
-social_networks = sorted(data.items())
+social_networks: list = sorted(social_networks.items())
 
 # Write the list of supported sites to sites.md
 with open("sites.md", "w") as site_file: