Skip to content

John McEleney / casperjs

Go to a project
Toggle navigation
Toggle navigation pinning
Commit 76e0b5c1 76e0b5c18b247e92230cffe6ee1dfbc0307c9c96 by Nicolas Perriault
Options

fixes #178 - added Casper.getPageContent() 

Extracts and returns the raw body contents for latest retrived page.

Sample script:

```javascript
var casper = require('casper').create();

casper.start().then(function() {
    this.open('http://search.twitter.com/search.json?q=casperjs', {
        method: 'get',
        headers: {
            'Accept': 'application/json'
        }
    });
});

casper.then(function() {
    require('utils').dump(JSON.parse(this.getPageContent()));
});

casper.run(function() {
    this.exit();
});
```
1 parent b2bce681
Inline Side-by-side
Showing 2 changed files with 25 additions and 1 deletions
......@@ -4,8 +4,9 @@ CasperJS Changelog
XXXX-XX-XX, v1.0.0
------------------
- fixed [#178](https://github.com/n1k0/casperjs/issues/178) - added `Casper.getPageContent()` to access raw page body contents on non-html received content-types.
- fixed [#164](https://github.com/n1k0/casperjs/issues/164) - ability to force CLI parameters as strings (see [related documentation](http://casperjs.org/cli.html#raw)).
- fixed [#153](https://github.com/n1k0/casperjs/issues/153) - erroneous mouse event results when event.preventDefault() was used
- fixed [#153](https://github.com/n1k0/casperjs/issues/153) - erroneous mouse event results when event.preventDefault() was used.
2012-06-26, v1.0.0-RC1
----------------------
......
......@@ -695,6 +695,29 @@ Casper.prototype.getColorizer = function getColorizer() {
};
/**
* Retrieves current page contents, dealing with exotic other content types than HTML.
*
* @return String
*/
Casper.prototype.getPageContent = function getPageContent() {
"use strict";
if (!this.started) {
throw new CasperError("Casper not started, can't getPageContent()");
}
var contentType = utils.getPropertyPath(this, 'currentResponse.contentType');
if (!utils.isString(contentType)) {
return this.page.content;
}
// for some reason webkit/qtwebkit will always enclose body contents within html tags
var match = (new RegExp('^<html><head></head><body><pre.+?>(.*)</pre></body></html>$')).exec(this.page.content);
if (!match) {
// Non-HTML response
return this.page.content;
}
return match[1];
};
/**
* Retrieves current document url.
*
* @return String
......