Some time ago I wrote a blog called
Web scrapping with Julia and PhantomJS...then I wrote another blog called
Web scrapping with Haskell and PhantomJS...
This time...it's
Go's time -;)
The concept is the same...we create a PhantomJS script that will read a "user" Twitter page and get the hashtags of the first 5 pages...here's the PhantomJS script...
| Hashtags.js |
|---|
var system = require('system');
var webpage = require('webpage').create();
webpage.viewportSize = { width: 1280, height: 800 };
webpage.scrollPosition = { top: 0, left: 0 };
var userid = system.args[1];
var profileUrl = "http://www.twitter.com/" + userid;
webpage.open(profileUrl, function(status) {
if (status === 'fail') {
console.error('webpage did not open successfully');
phantom.exit(1);
}
var i = 0,
top,
queryFn = function() {
return document.body.scrollHeight;
};
setInterval(function() {
top = webpage.evaluate(queryFn);
i++;
webpage.scrollPosition = { top: top + 1, left: 0 };
if (i >= 5) {
var twitter = webpage.evaluate(function () {
var twitter = [];
forEach = Array.prototype.forEach;
var tweets = document.querySelectorAll('[data-query-source="hashtag_click"]');
forEach.call(tweets, function(el) {
twitter.push(el.innerText);
});
return twitter;
});
twitter.forEach(function(t) {
console.log(t);
});
phantom.exit();
}
}, 3000);
});
|
If we run the script we're going to see the following output...
Now...what I want to do with this information...is to send it to Go...and get the most used hashtags...so I will summarize them and then get rid of the ones that only appear less than 5 times...
Let's see the Go code...
| TwitterHashtags.go |
|---|
package main
import ( "os/exec"
"strings"
"fmt" )
func main() {
cmd := exec.Command("phantomjs","--ssl-protocol=any","Hashtags.js", "Blag")
out, err := cmd.Output()
if err != nil {
println(err.Error())
return
}
Tweets := strings.Split(string(out), "\n")
charmap := make(map[string]int)
for _, value := range Tweets {
if value != "" {
charmap[value] += 1
}
}
for key, value := range charmap {
if value >= 5 {
fmt.Print("(", key, ", ")
fmt.Println(value, ")")
}
}
}
|
The only problem with this script is that there's not an easy way to sort a map[string]int...so I will simply leave it like that -:)
Here's the result...
If someone knows an easy way to sort this...please let me know -:)
Greetings,
Blag.
Development Culture.
