I am trying to scrape a stock market web page for the titles of href links. I don't get any output. I tried calling the class, id's,etc. I see the tag has a $0 assigned. I typed this in the console command line but it just showed the same thing.
I am trying to get the text "Bulk Deals" from the html. If I can figure how that's done, I can proceed.
Code:
var cheerio = require('cheerio');
var request = require('request');
var url ="http://feeds.feedburner.com/nseindia/CMDailyReport";
request(url, function(err, resp, body){
var $ = cheerio.load(body);
$(".regularitem .itemtitle").each(function(){
var link = $(this);
var text = link.text();
var href = link.attr("href");
console.log(text + href);
});
}); <ul>
<li xmlns:dc="http://purl.org/dc/elements/1.1/" class="regularitem">
<h4 class="itemtitle">
<a href="http://feedproxy.google.com/~r/nseindia/CMDailyReport/~3/P9Aw3__Tm9M/bulk.csv">Bulk Deals</a></h4>
<h5 class="itemposttime"></h5>
<div class="itemcontent" name="decodeable"><div class="feedflare">
<a href="http://feeds.feedburner.com/~ff/nseindia/CMDailyReport?a=P9Aw3__Tm9M:Clpwmq7B-_I:yIl2AUoC8zA">
<img src="http://feeds.feedburner.com/~ff/nseindia/CMDailyReport?d=yIl2AUoC8zA" border="0">
</a>
<a href="http://feeds.feedburner.com/~ff/nseindia/CMDailyReport?a=P9Aw3__Tm9M:Clpwmq7B-_I:F7zBnMyn0Lo">
<img src="http://feeds.feedburner.com/~ff/nseindia/CMDailyReport?i=P9Aw3__Tm9M:Clpwmq7B-_I:F7zBnMyn0Lo" border="0">
</a>
<a href="http://feeds.feedburner.com/~ff/nseindia/CMDailyReport?a=P9Aw3__Tm9M:Clpwmq7B-_I:qj6IDK7rITs">
<img src="http://feeds.feedburner.com/~ff/nseindia/CMDailyReport?d=qj6IDK7rITs" border="0">
</a>
<a href="http://feeds.feedburner.com/~ff/nseindia/CMDailyReport?a=P9Aw3__Tm9M:Clpwmq7B-_I:gIN9vFwOqvQ">
<img src="http://feeds.feedburner.com/~ff/nseindia/CMDailyReport?i=P9Aw3__Tm9M:Clpwmq7B-_I:gIN9vFwOqvQ" border="0">
</a>
</div>
<img src="http://feeds.feedburner.com/~r/nseindia/CMDailyReport/~4/P9Aw3__Tm9M" height="1" width="1" alt="">
</div>
</li>When you do $(".regularitem .itemtitle"), you're getting the <h4> and not the link (<a>) that is inside it.
To get the "Bulk Deals", you can do the following in your browser (or click on the 'Run code snippet' button):
var html = `<li xmlns:dc="http://purl.org/dc/elements/1.1/" class="regularitem">
<h4 class="itemtitle">
<a href="http://feedproxy.google.com/~r/nseindia/CMDailyReport/~3/P9Aw3__Tm9M/bulk.csv">Bulk Deals</a></h4>
<h5 class="itemposttime"></h5>
<div class="itemcontent" name="decodeable"><div class="feedflare">
<a href="http://feeds.feedburner.com/~ff/nseindia/CMDailyReport?a=P9Aw3__Tm9M:Clpwmq7B-_I:yIl2AUoC8zA">
<img src="http://feeds.feedburner.com/~ff/nseindia/CMDailyReport?d=yIl2AUoC8zA" border="0">
</a>
<a href="http://feeds.feedburner.com/~ff/nseindia/CMDailyReport?a=P9Aw3__Tm9M:Clpwmq7B-_I:F7zBnMyn0Lo">
<img src="http://feeds.feedburner.com/~ff/nseindia/CMDailyReport?i=P9Aw3__Tm9M:Clpwmq7B-_I:F7zBnMyn0Lo" border="0">
</a>
<a href="http://feeds.feedburner.com/~ff/nseindia/CMDailyReport?a=P9Aw3__Tm9M:Clpwmq7B-_I:qj6IDK7rITs">
<img src="http://feeds.feedburner.com/~ff/nseindia/CMDailyReport?d=qj6IDK7rITs" border="0">
</a>
<a href="http://feeds.feedburner.com/~ff/nseindia/CMDailyReport?a=P9Aw3__Tm9M:Clpwmq7B-_I:gIN9vFwOqvQ">
<img src="http://feeds.feedburner.com/~ff/nseindia/CMDailyReport?i=P9Aw3__Tm9M:Clpwmq7B-_I:gIN9vFwOqvQ" border="0">
</a>
</div>
<img src="http://feeds.feedburner.com/~r/nseindia/CMDailyReport/~4/P9Aw3__Tm9M" height="1" width="1" alt="">
</div>
</li>`
var parser = new DOMParser();
var doc = parser.parseFromString(html, "text/html");
Array.from(doc.querySelectorAll(".regularitem .itemtitle")).forEach(function(h4) {
var link = h4.getElementsByTagName('a')[0];
console.log(link.innerHTML);
});Hope it helps,
Best regards