Examples of URL - both Valid and Invalid, plus some more info about URL validation. Someday i'll build the perfect URL validation, then from it, the amazing "makeValidThisURL()"

aboutURL.json

{
  "rules": {
    "domain": [
      ".com .net .org and .info domain names cannot exceed 67 characters",
      ".info and .biz must have at least 3 characters not including .info and .biz",
      "Other domain names cannot exceed 22 characters not including the extension",
      "2 letter domains are not allowed."
    ],
    "edge-cases": [
      "'http://url.com/path///////otherpath' is technically valid per RFC 3986 and 9110. Most servers normalize or collapse them ('/path///////otherpath' and '/path/otherpath' yield the same resource), others don't (several empty segments (\"\") between 'path' and 'otherpath').",
      "'http://url.com/path' and 'http://url.com/path/' are distinct URIs. One refers to a resource literally named 'path', the other to a resource inside a collection named 'path/'. Most web servers issue a redirect (301 → /path/). Relative link resolution differs: '../' from '/path/' climbs to '/', but from '/path' it depends on whether the client normalized it first.",
      "https://例子.公司 → this is valid per RFC 3986 (Unicode allowed in IRIs), but invalid if you restrict to ASCII URLs."
    ]
  },
  "reference": [
    "https://publicsuffix.org/list/public_suffix_list.dat",
    "https://mathiasbynens.be/demo/url-regex",
    "https://gist.github.com/j3j5/8336b0224167636bed462950400ff2df",
    "https://gist.github.com/GuillaumeLestringant/36c11afcc35c8c5b9123",
    "https://url.spec.whatwg.org/",
    "http://www.ietf.org/rfc/rfc2732.txt",
    "https://news.ycombinator.com/item?id=7928968"
  ],
  "urlExamples": {
    "valid": [
      { "url":  "http://[1080:0:0:0:8:800:200C:417A]/index.html",
        "desc": "some IP and Hex/Decimal/Octal bullshit"
      },
      { "url":  "http://0xadc229b7",
        "desc": "some IP and Hex/Decimal/Octal bullshit"
      },
      { "url":  "http://2915183031",
        "desc": "some IP and Hex/Decimal/Octal bullshit"
      },
      { "url":  "http://025560424667.",
        "desc": "some IP and Hex/Decimal/Octal bullshit"
      },
      { "url":  "http://www.hotmail.co",
        "desc": "real live example"
      },
      { "url":  "https://www.eltiempo.com",
        "desc": "real live example"
      },
      { "url":  "https://www.nytimes.com",
        "desc": "real live example"
      },
      { "url":  "https://www.wikipedia.org",
        "desc": "real live example"
      },
      { "url": "http://example.com",
        "desc": "basic example of an URL"
      },
      { "url": "https://api.example.io/v2/users/123/profile",
        "desc": "common url found in the interwebs"
      },
      { "url": "https://store.example.com/products?id=42&sort=price",
        "desc": "another common type of url"
      },
      { "url": "http://example.com:0/",
        "desc": "RFC 3986 allows port zero. Some old APIs interpret it as 'use default port', though no TCP listener ever binds to it."
      },
      { "url": "https://www.example.org/index.html",
        "desc": "basic with resource"
      },
      { "url": "https://sub.domain.example.co.uk/path/to/resource",
        "desc": "basic with path"
      },
      { "url": "https://example.net:8080/test?q=1&r=2",
        "desc": "basic with port and search"
      },
      { "url": "https://192.168.0.12/admin",
        "desc": "ip instead of domain with single path"
      },
      { "url": "https://user:pass@example.com/login",
        "desc": "prefixed with authentication"
      },
      { "url": "https://example.com?query=param",
        "desc": "basic with search param"
      },
      { "url": "https://example.com/path#section2",
        "desc": "basic with hash"
      },
      { "url": "https://例子.公司.cn/关于",
        "desc": "internationalized domain name (IDN)"
      },
      { "url": "http://example.com:0/",
        "desc": "port 0 (edge case)"
      },
      { "url": "https://xn--fsq.com/…",
        "desc": "IDN + weird char"
      },
      { "url": "ftp://files.server.net/downloads/file.zip",
        "desc": "non-HTTP scheme"
      },
      { "url": "https://例子.公司",
        "desc": "Unicode host (if restricting to punycode/ASCII)"
      },
      { "url": "http://api.safebox.360.cn/Interface/getToolsDataApi/guid/{B7800CD1-75EE-41D3-9CFC-7E9B051B84AD}",
        "desc": "check next url"
      },
      { "url": "https://gist.github.com/dperini/729294?permalink_comment_id=3905413#gistcomment-3905413",
        "desc": "long live internet discussions"
      },
      { "url":  "https://www.samsung.",
        "desc": "took from juanluisbaptiste's url-validator repository (commit 'c0903add6d0fa85fb7dd42b8cfaa1c2da4889d77', file '/test_files/urls.txt') in github"
      },
      { "url":  "https:www.ford.com",
        "desc": "took from juanluisbaptiste's url-validator repository (commit 'c0903add6d0fa85fb7dd42b8cfaa1c2da4889d77', file '/test_files/urls.txt') in github"
      },
      { "url":  "www.amazon.com",
        "desc": "took from juanluisbaptiste's url-validator repository (commit 'c0903add6d0fa85fb7dd42b8cfaa1c2da4889d77', file '/test_files/urls.txt') in github"
      },
      { "url":  "www.apple.com",
        "desc": "took from juanluisbaptiste's url-validator repository (commit 'c0903add6d0fa85fb7dd42b8cfaa1c2da4889d77', file '/test_files/urls.txt') in github"
      },


      { "json-should-allow": "trailing-commas" }
    ],
    "wrong": [
      { "url": "http://- -",
        "desc": "nonsense host with spaces/hyphen"
      },
      { "url": "example.com",
        "desc": "missing scheme"
      },
      { "url": "http:///example.com",
        "desc": "too many slashes"
      },
      { "url": "http:// example.com",
        "desc": "space after double /."
      },
      { "url": "http://exa mple.com",
        "desc": "space in host"
      },
      { "url": "http://-example.com",
        "desc": "leading hyphen in domain label"
      },
      { "url": "http://example..com",
        "desc": "empty label (double dot)"
      },
      { "url": "http://.com",
        "desc": "only TLD"
      },
      { "url": "http://.example.com",
        "desc": "leading dot"
      },
      { "url": "http://example.com:99999/",
        "desc": "port > 65535"
      },
      { "url": "http://example.com:port/",
        "desc": "non-numeric port"
      },
      { "url": "http://user@:80/",
        "desc": "userinfo but no host"
      },
      { "url": "http://?q=1",
        "desc": "no host, only query"
      },
      { "url": "http://[::1",
        "desc": "unclosed IPv6 bracket"
      },
      { "url": "http://[::1]/path]",
        "desc": "stray closing bracket"
      },
      { "url": "http://192.168.1.999/",
        "desc": "invalid IPv4 octet"
      },
      { "url": "http://256.256.256.256",
        "desc": "invalid IPv4"
      },
      { "url": "http://exa_mple.com",
        "desc": "underscore in domain label"
      },
      { "url": "http://example.com/space in/path",
        "desc": "unescaped space in path"
      },
      { "url": "https://%GG.com",
        "desc": "invalid percent-encoding"
      },
      { "url": "ftp//example.com",
        "desc": "missing colon after scheme"
      },
      { "url": ": //example.com",
        "desc": "missing scheme (just punctuation & spaces)"
      },
      { "url": "http:///",
        "desc": "scheme + slashes only"
      },
      { "url": "data:text/plain,Hello world",
        "desc": "non-hierarchical scheme (if you expect http/https)"
      },
      { "url": "mailto:user@@example.com",
        "desc": "double @ in mailto"
      },
      { "url": "http://example.com // comment wtf",
        "desc": "plain text after"
      },
      { "url": "Use only http://example.com",
        "desc": "plain text before"
      },
      { "url": "the http://example.com of url",
        "desc": "plain text around"
      },
      { "url": "#http://example.com",
        "desc": "shell comment"
      },
      { "url": "'http://example.com'",
        "desc": "single string"
      },
      { "url": "\"http://example.com\"",
        "desc": "double string"
      },
      { "url": "`http://example.com`",
        "desc": "backtick string"
      },
      { "url": "[http://example.com]",
        "desc": "array element"
      },
      { "url": "http://example..com./",
        "desc": "double dot plus trailing dot is technically valid, but this is ugly and should not exist."
      },


      { "json-should-allow": "trailing-commas" }
    ],

    "json-should-allow": "trailing-commas"
  },

  "json-should-allow": "trailing-commas"
}