Set schema for manifest

sherlock/resources/data.json

@@ -1,4 +1,5 @@
 {
+ "$schema": "data.schema.json",
  "1337x": {
  "errorMsg": [
  "<title>Error something went wrong.</title>",
@@ -479,8 +480,7 @@
  "url": "https://codeforces.com/profile/{}",
  "urlMain": "https://codeforces.com/",
  "urlProbe": "https://codeforces.com/api/user.info?handles={}",
- "username_claimed": "tourist",
- "username_unclaimed": "noonewouldeverusethis7"
+ "username_claimed": "tourist"
  },
  "Codepen": {
  "errorType": "status_code",
@@ -977,7 +977,7 @@
  "username_claimed": "naveennamani877"
  },
  "HackerNews": {
- "::::README::::": "First errMsg invalid, second errMsg rate limited. Not ideal. Adjust for better rate limit filtering.",
+ "__comment__": "First errMsg invalid, second errMsg rate limited. Not ideal. Adjust for better rate limit filtering.",
  "errorMsg": [
  "No such user.",
  "Sorry."
@@ -1072,8 +1072,7 @@
  "errorUrl": "https://irc-galleria.net/users/search?username={}",
  "url": "https://irc-galleria.net/user/{}",
  "urlMain": "https://irc-galleria.net/",
- "username_claimed": "appas",
- "username_unclaimed": "noonewouldeverusethis77"
+ "username_claimed": "appas"
  },
  "Icons8 Community": {
  "errorType": "status_code",
@@ -1160,7 +1159,6 @@
  },
  "Jimdo": {
  "errorType": "status_code",
- "noPeriod": "True",
  "regexCheck": "^[a-zA-Z0-9@_-]$",
  "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_unclaimed": "noonewouldeverusethis7"
+ "username_claimed": "Lost_Arrow"
  },
  "Motherless": {
  "errorMsg": "no longer a member",
@@ -2268,7 +2265,7 @@
  "username_claimed": "blue"
  },
  "YandexMusic": {
- "::::README::::": "The first and third errorMsg relate to geo-restrictions and bot detection/captchas.",
+ "__comment__": "The first and third errorMsg relate to geo-restrictions and bot detection/captchas.",
  "errorMsg": [
  "\u041e\u0448\u0438\u0431\u043a\u0430 404",
  "<meta name=\"description\" content=\"\u041e\u0442\u043a\u0440\u044b\u0432\u0430\u0439\u0442\u0435 \u043d\u043e\u0432\u0443\u044e \u043c\u0443\u0437\u044b\u043a\u0443 \u043a\u0430\u0436\u0434\u044b\u0439 \u0434\u0435\u043d\u044c.",

sherlock/resources/data.schema.json

@@ -0,0 +1,80 @@
+{
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "title": "Sherlock Targets",
+ "description": "Social media target to probe for existence of usernames",
+ "type": "object",
+ "properties": {
+ "$schema": { "type": "string" }
+ },
+ "patternProperties": {
+ "^(?!\\$).*?$": {
+ "type": "object",
+ "description": "User-friendly target name",
+ "required": [ "url", "urlMain", "errorType", "username_claimed" ],
+ "properties": {
+ "url": { "type": "string" },
+ "urlMain": { "type": "string" },
+ "urlProbe": { "type": "string" },
+ "username_claimed": { "type": "string" },
+ "regexCheck": { "type": "string" },
+ "isNSFW": { "type": "boolean" },
+ "headers": { "type": "object" },
+ "request_payload": { "type": "object" },
+ "__comment__": {
+ "type": "string",
+ "description": "Used to clarify important target information if (and only if) a commit message would not suffice.\nThis key should not be parsed anywhere within Sherlock."
+ },
+ "tags": {
+ "oneOf": [
+ { "$ref": "#/$defs/tag" },
+ { "type": "array", "items": { "$ref": "#/$defs/tag" } }
+ ]
+ },
+ "request_method": {
+ "type": "string",
+ "enum": [ "GET", "POST", "HEAD", "PUT" ]
+ },
+ "errorType": {
+ "type": "string",
+ "enum": [ "message", "response_url", "status_code" ]
+ },
+ "errorMsg": {
+ "oneOf": [
+ { "type": "string" },
+ { "type": "array", "items": { "type": "string" } }
+ ]
+ },
+ "errorCode": {
+ "oneOf": [
+ { "type": "integer" },
+ { "type": "array", "items": { "type": "integer" } }
+ ]
+ },
+ "errorUrl": { "type": "string" },
+ "response_url": { "type": "string" }
+ },
+ "dependencies": {
+ "errorMsg": {
+ "properties" : { "errorType": { "const": "message" } }
+ },
+ "errorUrl": {
+ "properties": { "errorType": { "const": "response_url" } }
+ },
+ "errorCode": {
+ "properties": { "errorType": { "const": "status_code" } }
+ }
+ },
+ "if": { "properties": { "errorType": { "const": "message" } } },
+ "then": { "required": [ "errorMsg" ] },
+ "else": {
+ "if": { "properties": { "errorType": { "const": "response_url" } } },
+ "then": { "required": [ "errorUrl" ] }
+ },
+ "additionalProperties": false
+ }
+ },
+ "additionalProperties": false,
+ "$defs": {
+ "tag": { "type": "string", "enum": [ "adult", "gaming" ] }
+ }
+}

sherlock/sites.py

@@ -152,6 +152,11 @@ def __init__(self, data_file_path=None):
  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 @@
 
 # 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: