MediaWiki version:
≥ 1.11

GET request to find all the links on the provided page(s).

This module can be used as a {{ll|API:Query#Generators|generator}}.

API documentation

Special:ApiHelp/query+links

Examples

Example 1: Fetch all the links in a page

GET request

Get a list of links from the English Wikipedia's page on w:Albert Einstein

Response

{
    "query": {
        "pages": [
            {
                "pageid": 736,
                "ns": 0,
                "title": "Albert Einstein",
                "links": [
                    {
                        "ns": 0,
                        "title": "2dF Galaxy Redshift Survey"
                    },
                    {
                        "ns": 0,
                        "title": "A priori and a posteriori"
                    },
                    {
                        "ns": 0,
                        "title": "Aage Bohr"
                    },
                    ...
                ]
            }
        ]
    }
}

Sample code

Python

#!/usr/bin/python3

"""
    get_links.py

    MediaWiki API Demos
    Demo of `Links` module: Get all links on the given page(s)

    MIT License
"""

import requests

S = requests.Session()

URL = "https://en.wikipedia.org/w/api.php"

PARAMS = {
    "action": "query",
    "format": "json",
    "titles": "Albert Einstein",
    "prop": "links"
}

R = S.get(url=URL, params=PARAMS)
DATA = R.json()

PAGES = DATA["query"]["pages"]

for k, v in PAGES.items():
    for l in v["links"]:
        print(l["title"])

PHP

<?php
/*
    get_links.php

    MediaWiki API Demos
    Demo of `Links` module: Get all links on the given page(s)

    MIT License
*/

$endPoint = "https://en.wikipedia.org/w/api.php";
$params = [
    "action" => "query",
    "format" => "json",
    "titles" => "Albert Einstein",
    "prop" => "links"
];

$url = $endPoint . "?" . http_build_query( $params );

$ch = curl_init( $url );
curl_setopt( $ch, CURLOPT_RETURNTRANSFER, true );
$output = curl_exec( $ch );
curl_close( $ch );

$result = json_decode( $output, true );

foreach( $result["query"]["pages"] as $k => $v ) {
    foreach( $v["links"] as $k => $v ) {
        echo( $v["title"] . "\n" );
    }
}

JavaScript

/*
    get_links.js

    MediaWiki API Demos
    Demo of `Links` module: Get all links on the given page(s)

    MIT License
*/

var url = "https://en.wikipedia.org/w/api.php"; 

var params = {
    action: "query",
    format: "json",
    titles: "Albert Einstein",
    prop: "links"
};

url = url + "?origin=*";
Object.keys(params).forEach(function(key){url += "&" + key + "=" + params[key];});

fetch(url)
    .then(function(response){return response.json();})
    .then(function(response) {
        var pages = response.query.pages;
        for (var p in pages) {
            for (var l of pages[p].links) {
                console.log(l.title);
            }
        }
    })
    .catch(function(error){console.log(error);});

MediaWiki JS

/*
	get_links.js

	MediaWiki API Demos
	Demo of `Links` module: Get all links on the given page(s)

	MIT License
*/

var params = {
		action: 'query',
		format: 'json',
		titles: 'Albert Einstein',
		prop: 'links'
	},
	api = new mw.Api();

api.get( params ).done( function ( data ) {
	var pages = data.query.pages,
		p;
	for ( p in pages ) {
		pages[ p ].links.forEach( function ( l ) {
			console.log( l.title );
		} );
	}
} );

Get request to fetch missing or red links on Wikipedia:Most-wanted_articles. Two steps to do so:

  • Make a GET request to the Action API to return all links embedded on the provided page.
  • From further extraction, obtain those links that are missing and don't yet exist on English Wikipedia.
generator=links query module's submodule links used as a generator module to get a set of links embedded on a page.

GET request

Response

Response
{
  "batchcomplete": "", 
  "continue": {
    "continue": "gplcontinue||", 
    "gplcontinue": "297177|0|1965_in_sumo"
  }, 
  "query": {
    "pages": {
      "-1": {
        "missing": "", 
        "ns": 0, 
        "title": "(viii)"
      }, 
      "-10": {
        "missing": "", 
        "ns": 0, 
        "title": "1954 in sumo"
      }
      ...
    }
  }
}

Sample code

get_red_links.py

Python

#!/usr/bin/python3

"""
    get_red_links.py

    MediaWiki API Demos
    Demo of `Links` module to identify red or missing links on a page.

    MIT License
"""

import requests

S = requests.Session()

URL = "https://en.wikipedia.org/w/api.php"

PARAMS = {
    "action": "query",
    "titles": "Wikipedia:Most-wanted_articles",
    "gpllimit": "20",
    "format": "json",
    "generator": "links"
}

R = S.get(url=URL, params=PARAMS)
DATA = R.json()

PAGES = DATA['query']['pages']

for page in PAGES.values():
    if 'missing' in page:
        print(page['title'])

PHP

<?php
/*
    get_red_links.php

    MediaWiki API Demos
    Demo of `Links` module to identify red or missing links on a page.

    MIT License
*/

$endPoint = "https://en.wikipedia.org/w/api.php";
$params = [
    "action" => "query",
    "generator" => "links",
    "titles" => "Wikipedia:Most-wanted_articles",
    "gpllimit" => "20",
    "format" => "json"
];

$url = $endPoint . "?" . http_build_query( $params );

$ch = curl_init( $url );
curl_setopt( $ch, CURLOPT_RETURNTRANSFER, true );
$output = curl_exec( $ch );
curl_close( $ch );

$result = json_decode( $output, true );

foreach( $result["query"]["pages"] as $page ){
    if( array_key_exists("missing",$page ) ){
        echo( $page["title"] . "\n" );
    }
}

JavaScript

/*
    get_red_links.js

    MediaWiki API Demos
    Demo of `Links` module to identify red or missing links on a page.

    MIT License
*/

var url = "https://en.wikipedia.org/w/api.php"; 

var params = {
    action: "query",
    generator: "links",
    titles: "Wikipedia:Most-wanted_articles",
    gpllimit: "20",
    format: "json"
};

url = url + "?origin=*";
Object.keys(params).forEach(function(key){url += "&" + key + "=" + params[key];});

fetch(url)
    .then(function(response){return response.json();})
    .then(function(response) {
        var pages = response.query.pages;
        for (var p in pages) {
            if(pages[p].hasOwnProperty("missing")){
                console.log(pages[p].title);
            }
        }
    })
    .catch(function(error){console.log(error);});

MediaWiki JS

/*
	get_red_links.js

	MediaWiki API Demos
	Demo of `Links` module to identify red or missing links on a page.

	MIT License
*/

var params = {
		action: 'query',
		generator: 'links',
		titles: 'Wikipedia:Most-wanted_articles',
		gpllimit: '20',
		format: 'json'
	},
	api = new mw.Api();

api.get( params ).done( function ( data ) {
	var pages = data.query.pages,
		p;
	for ( p in pages ) {
		if( pages[ p ].hasOwnProperty('missing') ){
			console.log( pages[ p ].title );
		}
	}
} );

Parameter history

  • v1.19: Introduced pldir
  • v1.17: Introduced pltitles
  • v1.13: Introduced pllimit, plcontinue

See also

  • API:Linkshere - API:Properties submodule that finds pages which include a link to the given page.
  • API:Backlinks - API:Lists submodule that gets a list of pages which link to a given page.
  • API:Iwlinks - Find interwiki links on a given page (i.e, meta pages, special pages).
  • API:Iwbacklinks - Get a list of pages which are linked from a given interwiki link.
  • API:Extlinks - Find all external links on a given page.
  • API:Exturlusage - Get all pages that link to an external URL.
  • API:Langlinks - Get a list of language links from the given page. Language links represent translations.
  • API:Langbacklinks - Get a list of pages that contains a given language link.
This article is issued from Mediawiki. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.