Drupal 7: Setting up bulk WordPress to Drupal migration redirects

README.md

Drupal 7: Setting up bulk WordPress to Drupal migration redirects

When would I use this?

If you have a database of WordPress URLs that need to be redirected in Drupal 7.

What do I do?

1. Install Redirect module.
2. Install path_redirect_import module.
3. Export 2 CSVs from the database: aliased and unaliased URLs.
4. Import both CSVs into separate sheets in Google Docs.
5. Create a script in the Google Spreadsheet.
6. Paste in the scripts and save.
7. Run the createDestinationURL() script on the sheet that imported the post_name column.
8. Run the createOriginURL() script on the sheet that imported the guid column.
9. Export both sheets to CSV.
10. In Drupal, go to admin/config/search/redirect/import and import both CSVs exported from Google Docs.

howlround_googledoc_scripts.js

/**
 * https://developers.google.com/apps-script/service_spreadsheet
 */
function createDestinationUrl() {
  var sheet = SpreadsheetApp.getActiveSheet();
  var rows = sheet.getDataRange();
  var numRows = rows.getNumRows();
  var values = rows.getValues();

  for (var i = 0; i <= numRows - 1; i++) {
    var cell = rows.getCell(i+1, 2);
    cell.clearContent();
    // Replace with desired destination URL.
    cell.setValue('http://journalism.howlround.com/' + rows.getCell(i+1, 1).getValue());
//    Logger.log(row);
  }
};


function createOriginUrl() {
  var sheet = SpreadsheetApp.getActiveSheet();
  var rows = sheet.getDataRange();
  var numRows = rows.getNumRows();
  rows.copyTo(sheet.getRange(1, 2)); 

  for (var i = 0; i <= numRows - 1; i++) {
    var cell = rows.getCell(i+1, 1);
    var value = cell.getValue();
    // Replace with origin URL. This should match the contents of the CSV.
    value = value.replace('http://www.howlround.com/', '');
    cell.setValue(value);
  }
}


/**
 * Adds a custom menu to the active spreadsheet, containing a single menu item
 * for invoking the readRows() function specified above.
 * The onOpen() function, when defined, is automatically invoked whenever the
 * spreadsheet is opened.
 * For more information on using the Spreadsheet API, see
 * https://developers.google.com/apps-script/service_spreadsheet
 */
function onOpen() {
  var sheet = SpreadsheetApp.getActiveSpreadsheet();
  var entries = [{
    name : "Create destination URL",
    functionName : "createDestinationUrl"
  },
  {
    name : "Create origin URL",
    functionName : "createOriginUrl"
  }
  ];
  sheet.addMenu("Scripts", entries);
};

howlround_wordpress_export.sql

--- These are the queries that you need for exporting from WordPress.

--- This query returns the post_name column.
--- Depending on the WordPress URL alias setting, this can help with exporting all the URL aliases.
SELECT `post_name`
FROM  `wp_posts` 
WHERE  `guid` NOT REGEXP  '.*(revision|autosave|wp-content|post_type=slideshow).*'
AND  `post_name` NOT REGEXP  '.*(autosave|revision).*'
AND  `post_status` =  'publish'
ORDER BY  `wp_posts`.`post_name` ASC 

--- This query returns the guid column.
--- It will include entries containing "?p=" and "?page_id=", which is what we want.
SELECT `guid`
FROM  `wp_posts` 
WHERE  `guid` NOT REGEXP  '.*(revision|autosave|wp-content|post_type=slideshow).*'
AND  `post_name` NOT REGEXP  '.*(autosave|revision).*'
AND  `post_status` =  'publish'
ORDER BY  `wp_posts`.`post_name` ASC