Difference between revisions of "Sourcerer Implementation Notes"

Revision as of 14:32, 17 February 2015

Using MediaWiki api.php

Some Basic Tasks

Help Page

http://wiki.xkcd.com/wgh/api.php

JSON Page Content Dump

http://wiki.xkcd.com/wgh/api.php?format=json&action=query&titles=User:Sourcerer&prop=revisions&rvprop=content

List first twenty of Consecutive geohash achievement

http://wiki.xkcd.com/wgh/api.php?action=query&list=categorymembers&cmtitle=Category:Consecutive_geohash_achievement&cmlimit=20

List twenty more of Consecutive geohash achievement

http://wiki.xkcd.com/wgh/api.php?action=query&list=categorymembers&cmtitle=Category:Consecutive_geohash_achievement&cmcontinue=page%7C323030392d30332d31362035322030%7C17773&cmlimit=20

PHP Code - List first twenty of Consecutive geohash achievement - Command line application

<?php
   $html = file_get_contents('http://wiki.xkcd.com/wgh/api.php?action=query&list=categorymembers&cmtitle=Category:Consecutive_geohash_achievement&cmlimit=20');
   echo $html;
?>

PHP Code - As above but use JSON

<?php
  $json     = file_get_contents('http://wiki.xkcd.com/wgh/api.php?action=query&format=json&list=categorymembers&cmtitle=Category:Consecutive_geohash_achievement&cmlimit=20');
  $readable = json_decode($json, true);
  print_r($readable);
?>

PHP Expedition as JSON

<?php
  $json     = file_get_contents('http://wiki.xkcd.com/wgh/api.php?format=json&action=query&titles=2015-02-07_52_1&prop=revisions&rvprop=content');
  $readable = json_decode($json, true);
  print_r($readable);
?>

@@ Line 1: / Line 1: @@
-== Plan of Campaign ==
+__NOTOC__{{SourcererImplementationNav}}
-My plan is to create some analysis tools for this wiki. This page might help others to implement their tools.
+== Some Basic Tasks ==
-I'm using a standard Windows PHP 5.3.5 installation and running the examples from the command line. Linux or other PHPs should work the same.
-# Get some page content ("Hello World!").
-# Write some PHP command line code to do the same. Make sure this does not overload the wiki.
-# Download lists of pages and different kinds of page.
-# Do some simple statistics on the downloaded data.
-# Create reports in wiki markup.
-# If it works, upload the reports to the wiki.
-=== Various Downloads ===
 '''Help Page'''
@@ Line 25: / Line 14: @@
 '''List twenty more of Consecutive geohash achievement'''
 : http://wiki.xkcd.com/wgh/api.php?action=query&list=categorymembers&cmtitle=Category:Consecutive_geohash_achievement&cmcontinue=page|323030392d30332d31362035322030|17773&cmlimit=20
-[[Category:Implementations]]
 === PHP Code - List first twenty of Consecutive geohash achievement - Command line application ===
@@ Line 49: / Line 36: @@
    $readable = json_decode($json, true);
    print_r($readable);
-?></nowiki>
-=== PHP Get every page title for a specified category ===
-This fetches 100 page titles at a time with 5 second pauses between fetches to avoid loading the wiki too much.
- <nowiki><?php
-  // =======================================================================
-  // === These constant values must be set before running the script =======
-  // =======================================================================
-  define("API_URL", 'http://wiki.xkcd.com/wgh/api.php');    // Search any wiki page source for "api.php" to find this path on other MediaWiki sites
-  // =======================================================================
-  // Return an array containing the cmcontinue value followed by page titles
-  // Index [0] contains cmcontinue needed to get the next page
-  // Index [1] up to [cmlimit] contains the page titles, could be zero items
-  // =======================================================================
-  function getTitlesInCategory($cmtitle, $cmlimit = 10, $cmcontinue = "")
-  {
-    if ($cmcontinue == "") { $continue = ""; } else { $continue = "&cmcontinue=$cmcontinue"; }
-    $url         = API_URL . "?action=query&format=json&list=categorymembers&cmtitle=$cmtitle&cmlimit=$cmlimit$continue";
-    $json        = file_get_contents($url);
-    $decodedjson = json_decode($json, true);
-    echo $url . "\n";
-    $titles = array();
-    if (isset($decodedjson['query-continue']))
-    {
-      $titles[] = $decodedjson['query-continue']['categorymembers']['cmcontinue'];  // Next page if there is one
-    }
-    else
-    {
-      $titles[] = "";
-    }
-    foreach($decodedjson['query']['categorymembers'] as $value)
-    {
-      $titles[] = $value['title'];
-    }
-    return $titles;
-  }
-  // =======================================================================
-  // =======================================================================
-  // Return an array containing ALL page titles for the category
-  // =======================================================================
-  function getAllTitlesInCategory($cmtitle)
-  {
-    $allTitles = array();
-    $titles = getTitlesInCategory($cmtitle, 100);
-    // print_r($titles);
-    $cmcontinue = $titles[0];
-    unset($titles[0]);
-    $allTitles = array_merge($allTitles, $titles);
-    while($cmcontinue != "")
-    {
-      sleep(5);
-      $titles = getTitlesInCategory($cmtitle, 100, $cmcontinue);
-      // print_r($titles);
-      $cmcontinue = $titles[0];
-      unset($titles[0]);
-      $allTitles = array_merge($allTitles, $titles);
-    }
-    return $allTitles;
-  }
-  // =======================================================================
-  // =======================================================================
-  // main program
-  // =======================================================================
-  print_r(getAllTitlesInCategory("Category:Consecutive_geohash_achievement"));
 ?></nowiki>
 [[Category:Implementations]]