我正在尝试使用 nodeJS 构建一个网络抓取工具,它在网站的 HTML 中搜索图像,缓存图像源 URL,然后搜索最大尺寸的图像。
我遇到的问题是 deliverLargestImage()
在循环遍历图像源 URL 数组以获取其文件大小之前触发。我正在尝试同时使用 async.series
和 async.each
以使其正常工作。
如何强制 deliverLargestImage()
等到 getFileSizes()
中的 async.each
完成?
JS
var async, request, cheerio, gm;
async = require('async');
request = require('request');
cheerio = require('cheerio');
gm = require('gm').subClass({ imageMagick: true });
function imageScraper () {
var imgSources, largestImage;
imgSources = [];
largestImage = {
url: '',
size: 0
};
async.series([
function getImageUrls (callback) {
request('http://www.example.com/', function (error, response, html) {
if (!error && response.statusCode === 200) {
var $ = cheerio.load(html);
$('img').each(function (i, elem) {
if ( $(this).attr('src').indexOf('http://') > -1 ) {
var src = $(this).attr('src');
imgSources.push(src);
}
});
}
callback();
});
},
function getFileSizes (callback) {
async.each(imgSources, function (img, _callback) {
gm(img).filesize(function (err, value) {
checkSize(img, value);
_callback();
});
});
callback();
},
function deliverLargestImage (callback) {
callback();
return largestImage;
}
]);
function checkSize (imgUrl, value) {
var r, raw;
if (value !== undefined) {
r = /\d+/;
raw = value.match(r)[0];
if (raw >= largestImage.size) {
largestImage.url = imgUrl;
largestImage.size = raw;
}
}
}
}
imageScraper();
最佳答案
尝试将 callback()
移到这里:
function getFileSizes (callback) {
async.each(imgSources, function (img, _callback) {
gm(img).filesize(function (err, value) {
checkSize(img, value);
_callback();
});
}, function(err){ callback(err); }); /* <-- put here */
/* callback(); <-- wrong here */
},
each
接受回调作为 third parameter当每个元素的内部循环完成时执行:
Arguments
arr
- An array to iterate over.iterator(item, callback)
- A function to apply to each item inarr
. The iterator is passed acallback(err)
which must be called once it has completed. If no error has occured, thecallback
should be run without arguments or with an explicitnull
argument.callback(err)
- A callback which is called when alliterator
functions have finished, or an error occurs.
关于javascript - async.series 和 async.each 没有按预期工作,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/22998494/