problem description
Liberal arts scum recently needed to get a broadcast link to a website, wrote a node crawler, and the array of all links can be printed, but I don"t know how to get an array of these links with a variable.
related codes
var http = require("https");
var cheerio = require("cheerio")
var url = "https://www.tagesschau.de/export/podcast/tagesschau_https/";
function get(url) {
return new Promise(function (resolve, reject) {
http.get(url, function (res) {
var html = "";
res.on("data", function (data) {
html += data;
});
res.on("end", function () {
resolve(html);
});
}).on("error", function (e) {
reject(e)
console.log("");
});
})
}
function filterChapter(html) {
var x = []
const $ = cheerio.load(html);
const chapters = $("enclosure");
chapters.each(function (i, item) {
x.push(item.attribs.url)
})
console.log(x)
}
get(url).then(function (data) {
filterChapter(data)
}) filterChapter? If it is returned, it seems to be returned directly to the anonymous function after then, but it is still not available. Another problem with
is getting all the enclosure tags, each with a url= "." This kind of information, I want to get the link how to write? Although I can get the link above, it looks strange. I don"t understand the parameters after each. Thank you!