Last active
September 9, 2019 04:15
-
-
Save kui/6c17e82d733f1d95ffe7 to your computer and use it in GitHub Desktop.
a web scraping script with Dart and html5lib
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
import 'dart:io'; | |
import 'dart:async'; | |
import 'package:html5lib/parser.dart'; | |
import 'package:html5lib/dom.dart'; | |
main() { | |
final url = 'http://comic-walker.com/'; | |
getHtml(url).then((document) { | |
// page title | |
print(document.querySelector('title').text); | |
// Newer comics | |
document.querySelectorAll('#bookList > li').forEach((e) { | |
print(e.querySelector('.list_bookName').text); | |
}); | |
}); | |
} | |
/// fetch and parse the HTML from [url] | |
Future<Document> getHtml(String url) => | |
new HttpClient() | |
.getUrl(Uri.parse(url)) | |
.then((req) => req.close()) | |
.then((res) => res | |
.asyncExpand((bytes) => new Stream.fromIterable(bytes)) | |
.toList()) | |
.then((bytes) => parse(bytes, sourceUrl: url)); |
Does this provide client side scraping
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Package
html5lib
is now olnyhtml
(source)