crawler-url-parser
Advanced tools
Comparing version 1.4.2 to 1.4.4
@@ -17,3 +17,3 @@ { | ||
"name": "Launch QuickStart", | ||
"program": "${workspaceFolder}\\quickstart.js" | ||
"program": "${workspaceFolder}\\QUICKSTART.js" | ||
}, | ||
@@ -20,0 +20,0 @@ { |
{ | ||
"name": "crawler-url-parser", | ||
"version": "1.4.2", | ||
"version": "1.4.4", | ||
"description": "An `URL` parser for crawling purpose.", | ||
@@ -5,0 +5,0 @@ "main": "crawler-url-parser.js", |
//const cup = require('crawler-url-parser'); | ||
const cup = require('./'); | ||
//// parse(current_url,base_url) | ||
let url = cup.parse("../ddd","http://question.stackoverflow.com/aaa/bbb/ccc/"); | ||
console.log(url.normalized); | ||
console.log(url.host); | ||
console.log(url.domain); | ||
console.log(url.subdomain); | ||
console.log(url.protocol); | ||
console.log(url.path); | ||
console.log(url.normalized);//http://question.stackoverflow.com/aaa/bbb/ddd | ||
console.log(url.host); // question.stackoverflow.com | ||
console.log(url.domain); // stackoverflow.com | ||
console.log(url.subdomain); // question | ||
console.log(url.protocol); // http: | ||
console.log(url.path); // /aaa/bbb/ddd | ||
//// extract(html_str,current_url); | ||
let htmlStr= | ||
@@ -27,3 +29,20 @@ 'html> \ | ||
let currentUrl= "http://www.stackoverflow.com/aaa/bbb/ccc"; | ||
let result = cup.extract(htmlStr,currentUrl); | ||
console.log(result.length); | ||
let urls = cup.extract(htmlStr,currentUrl); | ||
console.log(urls.length); // 6 | ||
//// getlevel(current_url,base_url); | ||
let level = cup.getlevel("sub.domain.com/aaa/bbb/","sub.domain.com/aaa/bbb/ccc"); | ||
console.log(level); //sublevel | ||
level = cup.getlevel("sub.domain.com/aaa/bbb/ccc/ddd","sub.domain.com/aaa/bbb/ccc"); | ||
console.log(level); //uplevel | ||
level = cup.getlevel("sub.domain.com/aaa/bbb/eee","sub.domain.com/aaa/bbb/ccc"); | ||
console.log(level); //samelevel | ||
level = cup.getlevel("sub.domain.com/aaa/bbb/eee","sub.anotherdomain.com/aaa/bbb/ccc"); | ||
console.log(level); //null | ||
//// querycount(url) | ||
let count = cup.querycount("sub.domain.com/aaa/bbb?q1=data1&q2=data2&q3=data3"); | ||
console.log(count); //3 |
@@ -9,3 +9,3 @@ # crawler-url-parser | ||
[![node](https://img.shields.io/node/v/crawler-url-parser.svg)](https://nodejs.org/) | ||
[![status](https://gitlab.com/mehmet.kozan/crawler-url-parser/badges/master/pipeline.svg)](https://gitlab.com/mehmet.kozan/crawler-url-parser/commits/master) | ||
[![status](https://gitlab.com/mehmet.kozan/crawler-url-parser/badges/master/pipeline.svg)](https://gitlab.com/mehmet.kozan/crawler-url-parser/pipelines) | ||
@@ -20,9 +20,11 @@ ## Installation | ||
const cup = require('crawler-url-parser'); | ||
//// parse(current_url,base_url) | ||
let url = cup.parse("../ddd","http://question.stackoverflow.com/aaa/bbb/ccc/"); | ||
console.log(url.normalized); | ||
console.log(url.host); | ||
console.log(url.domain); | ||
console.log(url.subdomain); | ||
console.log(url.protocol); | ||
console.log(url.path); | ||
console.log(url.normalized);//http://question.stackoverflow.com/aaa/bbb/ddd | ||
console.log(url.host); // question.stackoverflow.com | ||
console.log(url.domain); // stackoverflow.com | ||
console.log(url.subdomain); // question | ||
console.log(url.protocol); // http: | ||
console.log(url.path); // /aaa/bbb/ddd | ||
``` | ||
@@ -33,2 +35,4 @@ | ||
const cup = require('crawler-url-parser'); | ||
//// extract(html_str,current_url); | ||
let htmlStr= | ||
@@ -49,4 +53,4 @@ 'html> \ | ||
let currentUrl= "http://www.stackoverflow.com/aaa/bbb/ccc"; | ||
let result = cup.extract(htmlStr,currentUrl); | ||
console.log(result.length); | ||
let urls = cup.extract(htmlStr,currentUrl); | ||
console.log(urls.length); // 6 | ||
``` | ||
@@ -57,2 +61,15 @@ | ||
const cup = require('crawler-url-parser'); | ||
//// getlevel(current_url,base_url); | ||
let level = cup.getlevel("sub.domain.com/aaa/bbb/","sub.domain.com/aaa/bbb/ccc"); | ||
console.log(level); //sublevel | ||
level = cup.getlevel("sub.domain.com/aaa/bbb/ccc/ddd","sub.domain.com/aaa/bbb/ccc"); | ||
console.log(level); //uplevel | ||
level = cup.getlevel("sub.domain.com/aaa/bbb/eee","sub.domain.com/aaa/bbb/ccc"); | ||
console.log(level); //samelevel | ||
level = cup.getlevel("sub.domain.com/aaa/bbb/eee","sub.anotherdomain.com/aaa/bbb/ccc"); | ||
console.log(level); //null | ||
``` | ||
@@ -63,2 +80,6 @@ | ||
const cup = require('crawler-url-parser'); | ||
//// querycount(url) | ||
let count = cup.querycount("sub.domain.com/aaa/bbb?q1=data1&q2=data2&q3=data3"); | ||
console.log(count); //3 | ||
``` | ||
@@ -65,0 +86,0 @@ |
Sorry, the diff of this file is not supported yet
Sorry, the diff of this file is not supported yet
57076
917
87