问题
I've written a script in node
using two different functions getPosts()
and getContent()
supplying callback within them in order to print the result calling a standalone function getResult()
. The selectors defined within my script is flawless.
However, when I execute my script, It prints nothing. It doesn't throw any error either. I tried to mimic the logic provied by Neil in this post.
How can I make it a go?
I've written so far:
var request = require('request');
var cheerio = require('cheerio');
const url = 'https://stackoverflow.com/questions/tagged/web-scraping';
function getPosts(callback){
request(url, function (error,response, html) {
if (!error && response.statusCode == 200){
var $ = cheerio.load(html);
$('.summary .question-hyperlink').each(function(){
var items = $(this).text();
var links = $(this).attr("href");
callback(items,links);
});
}
});
}
function getContent(item,link,callback){
request(link, function (error,response, html) {
if (!error && response.statusCode == 200){
var $ = cheerio.load(html);
var proLink = $('.user-details > a').eq(0).attr("href");
callback({item,link,proLink});
}
});
}
function getResult() {
getPosts(function(item,link) {
getContent(item,link,function(output){
console.log(output);
});
});
}
getResult();
回答1:
The link
value that you receive from getPosts
is a relative link which means that the request fails. You can extract the hostname inside its own variable and create the full URL from the hostname + the relative link.
const host = 'https://stackoverflow.com';
const url = '/questions/tagged/web-scraping';
// ...
function getContent(item,link,callback){
// Here we use the absolute URL
request(host + link, function (error,response, html) {
if (!error && response.statusCode == 200){
var $ = cheerio.load(html);
var proLink = $('.user-details > a').eq(0).attr("href");
callback({item,link,proLink});
}
});
}
来源:https://stackoverflow.com/questions/55597383/unable-to-fetch-results-using-callback