Some Assembla crawling stuff

AssemblaCrawl.js

var fs = require('fs'),
  request = require('request'),
  spaces = [],
  AssemblaApiSecret = "<API Secret>",
  AssemblaApiKey = "<API Key>";

var options = {
  url: 'https://api.assembla.com/v1/spaces/',
  headers: {
    "X-Api-Secret": AssemblaApiSecret,
    "X-Api-Key": AssemblaApiKey
  }
};

console.log("Getting list of spaces");
request(options, function(error, response, body) {
  if (!error && response.statusCode == 200) {
    spaces = JSON.parse(body);
    var endLength = spaces.length - 1;
    console.log("Getting Repositories");
    for (var i = 0; i <= endLength; i++) {
      getRepos(i, i === endLength);
    }
  }
});

function getRepos(i, final) {
  var spaceId = spaces[i].id;
  var spaceName = spaces[i].name;
  var options = {
    url: 'https://api.assembla.com/v1/spaces/' + spaceId +
      '/space_tools/repo',
    headers: {
      "X-Api-Secret": AssemblaApiSecret,
      "X-Api-Key": AssemblaApiKey
    }
  };
  request(options, function(error, response, body) {
    if (!error && response.statusCode == 200) {
      var repos = JSON.parse(body);
      spaces[i].repos = repos;
      console.log(spaceName, repos.length);
      fs.writeFileSync('./results.json', JSON.stringify(spaces), 'utf8');
    } else if (response.statusCode === 204) {
      console.log("No repositories associated with the space", spaceName);
    } else {
      console.log("Error getting info for space", spaceName);
    }
    if (final) {
      console.log("Finished getting repositories, generating report");
      var reportTxt = "";
      for (var j = 0; j < spaces.length; j++) {
        var result = spaces[j];
        reportTxt += result.name.trim() + ':\n';
        if (result.repos) {
          for (var k = 0; k < result.repos.length; k++) {
            reportTxt += '\t' + result.repos[k].url + '\n';
          }
        } else {
          reportTxt += '\t_no repositories_\n';
        }
        reportTxt += '\n';
      }
      fs.writeFileSync('./report.txt', reportTxt, 'utf8');
      console.log("report.tx created");
    }
  });
}

once we have a list of repos, I'm using the shell script at https://gist.github.com/markrickert/2919901 to archive each one off, it can then be saved to AWS or dropbox or whatever, and restored at a later date.