Last active
March 22, 2021 18:39
-
-
Save destroytoday/6706265 to your computer and use it in GitHub Desktop.
Bookmarklet to scrape Amazon book pages
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
var imgRegexp = new RegExp("(http://ecx\.images-amazon\.com\/images\/[A-Z]\/[A-Za-z0-9%]+)\..+(\.jpg)"); | |
var doc = document | |
, obj = { meta: [], taxonomy: [] }; | |
// ------------------ | |
// cover asset | |
// ------------------ | |
var img = doc.querySelector('#main-image, #imgBlkFront'); | |
if (img) obj.assets = [img.src.replace(imgRegexp, "$1$2")]; | |
// ------------------ | |
// title | |
// ------------------ | |
var title = doc.querySelector('#btAsinTitle, h1#title'); | |
if (title) obj.title = title.innerText; | |
// ------------------ | |
// author | |
// ------------------ | |
var author = doc.querySelector('.contributorNameTrigger, .contributorNameID, .author'); | |
if (author) obj.taxonomy.push({ key: 'Author', values: [author.innerText.replace('(Author)', '').replace(/^\s+|\s+$/g, '')] }); | |
// ------------------ | |
// body | |
// ------------------ | |
var body = doc.getElementById('bookDesc_iframe') || doc.getElementById('postBodyPS'); | |
if (body && body.contentDocument) { | |
obj.body = body.contentDocument.getElementById('iframeContent').innerText; | |
} else if (body) { | |
obj.body = body.innerText; | |
}; | |
// ------------------ | |
// link meta | |
// ------------------ | |
obj.meta.push({ key: 'link', value: window.location.origin + window.location.pathname }); | |
// ------------------ | |
// tags | |
// ------------------ | |
var raw_tags = doc.querySelectorAll('#SalesRank li b'); | |
var tags = []; | |
[].forEach.call(raw_tags, function (tag) { | |
tags.push(tag.innerText.replace(/^\s+|\s+$/g, '')); | |
}); | |
obj.taxonomy.push({ key: 'Tags', values: tags }); | |
// --------------------- | |
// serialize URL params | |
// --------------------- | |
serialize = function(obj) { | |
var str = []; | |
var valueName, value; | |
for(var prop in obj) { | |
if (prop == 'meta' || prop == 'taxonomy') { | |
[].forEach.call(obj[prop], function (item) { | |
if (prop == 'taxonomy') { | |
valueName = 'values'; | |
value = item.values.join(","); | |
} else { | |
valueName = 'value'; | |
value = item.value; | |
} | |
str.push(prop + "[][key]=" + encodeURIComponent(item.key)); | |
str.push(prop + "[][" + valueName + "]=" + encodeURIComponent(value)); | |
}); | |
} else if (prop == 'assets') { | |
str.push(prop + "[]=" + encodeURIComponent(obj[prop][0])); | |
} else { | |
str.push(prop + "=" + encodeURIComponent(obj[prop])); | |
} | |
} | |
return str.join("&"); | |
} | |
window.open("http://manage.siteleaf.dev:1337/pages/5245dbf3ef75ac50e900000c/posts/new?" + serialize(obj)); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment