尝试抓取多个页面,但无法使urlid数组在pjscrape .js文件中工作。
我敢肯定,我可能会犯一个新手错误,但是我希望能获得一些帮助。
谢谢 :)
pjs.config({
timeoutInterval: 6000,
timeoutLimit: 10000,
})
pjs.addSuite({
// single URL or array
url: abolaURLs,
scraper: function(){
var abolaURLs = [366762,366764,366763];
for (var i = 0; i<abolaURLs.length; i++) {
abolaURLs[i] = 'http://abola.pt/nnh/ver.aspx?id=' + abolaURLs[i];
};
var results[];
var cenas1 = $('div#a5g2').text();
var cenas2 = $('span#noticiatext').text();
var cenas3 = $('div#a5x').text();
results.push(cenas1, cenas2, cenas3);
return results;
}
});
最佳答案
这将为您工作:
var abolaURLs = [366762,366764,366763];
for (var i = 0; i < abolaURLs.length; i++) {
abolaURLs[i] = 'http://abola.pt/nnh/ver.aspx?id=' + abolaURLs[i];
};
pjs.addSuite({
url: abolaURLs,
scraper: function() {
var results = []; // !! you have the wrong array declaration result[]
var cenas1 = $('div#a5g2').text();
var cenas2 = $('span#noticiatext').text();
var cenas3 = $('div#a5x').text();
results.push(cenas1, cenas2, cenas3);
return results;
}
});
pjs.config({
timeoutInterval: 6000,
timeoutLimit: 10000,
});
关于javascript - 使用Phantomjs/Pjscrape刮取多个页面,我们在Stack Overflow上找到一个类似的问题:https://stackoverflow.com/questions/13582461/