google-img-scrap 1.0.3 → 1.0.4

package/CHANGELOG.md

@@ -1,5 +1,10 @@
 # Changelog
 
+### v1.0.4
+
+- New option ```urlMatch```. You know get image when an url match a string (example: "cdn")
+- New option ```filterByTitles```. Filter images by titles
+
 ### v1.0.3
 - New option ```execute```. allow you to execute a function to remove "gstatic.com" domains for example
 

package/README.md

@@ -1,5 +1,6 @@
-# Google-img-scrap v1.0.3
-Scrap images from google image with lot of options
+# Google-img-scrap v1.0.4
+
+Scrap images from google image with lot of tools and options.
 
 ## Update
 
@@ -38,7 +39,9 @@ const { GOOGLE_IMG_SCRAP , GOOGLE_QUERY } = require('./src/google-img-scrap');
 - "excludeDomains" (Array of String) exclude some domains
 - "safeSearch" (Boolean) active safe search or not for nsfw for example
 - "custom" (String) add extra query
-- "query" (Object) set a query (can be [TYPE, DATE, COLOR, SIZE, LICENCE, EXTENSION]) (use GOOGLE_QUERY items, you can see example behind)
+- "urlMatch" (Array of Array) get image when an url match a string (example: "cdn") | ```example below```
+- "filterByTitles" (Array of Array) filter images by titles | ```example below```
+- "query" (Object) set a query (can be [TYPE, DATE, COLOR, SIZE, LICENCE, EXTENSION]) (use GOOGLE_QUERY items | ```example below```
 
 ## Result
 
@@ -87,11 +90,11 @@ console.log(GOOGLE_QUERY);
             LICENCE: GOOGLE_QUERY.LICENCE.COMMERCIAL_AND_OTHER,
             EXTENSION: GOOGLE_QUERY.EXTENSION.JPG
         },
-        domains: ["alamy.com", "istockphoto.com", "vecteezy.com", "gstatic.com"],
+        domains: ["alamy.com", "istockphoto.com", "vecteezy.com"],
         excludeWords: ["black", "white"], //If you don't like black and white cats
         custom: "name=content&name2=content2",
         safeSearch: false,
-        // excludeDomains: ["gstatic.com", "istockphoto.com", "alamy.com"]
+        // excludeDomains: ["istockphoto.com", "alamy.com"]
     });
 
     console.log(test, test.result.length);
@@ -134,6 +137,30 @@ const { GOOGLE_IMG_SCRAP , GOOGLE_QUERY } = require('google-img-scrap');
 })();
 ```
 
+## How urlMatch and filterByTitles work ?
+
+- urlMatch work like filterByTiles
+
+```js
+const { GOOGLE_IMG_SCRAP } = require('google-img-scrap');
+
+(async function(){
+    const test = await GOOGLE_IMG_SCRAP({
+        search: "cats",
+        //will build something like this "(draw and white) or (albino and white)"
+        filterByTitles: [
+            ["draw", "white"],
+            ["albino", "white"]
+        ],
+        execute: function(element){
+            if(!element.url.match('gstatic.com')) return element;
+        }
+    });
+
+    console.log(test, test.result.length);
+})();
+```
+
 ## Google query
 
 ```js

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "google-img-scrap",
-  "version": "1.0.3",
+  "version": "1.0.4",
   "description": "Scrap images from google images with a lot of options",
   "main": "./src/google-img-scrap.js",
   "directories": {

package/src/google-img-scrap.js

@@ -89,8 +89,38 @@ async function GOOGLE_IMG_SCRAP(config = {}){
     const EXCLUDE_WORDS = [];
     if(config.excludeWords) config.excludeWords.forEach((word) => EXCLUDE_WORDS.push(`-"${word}"`));
 
+    //filter by titles
+    const FILTER_TITLE = [];
+    if(config.filterByTitles) config.filterByTitles.forEach((titleFilter) => {
+
+        const value = titleFilter.map((title) => {
+            return `intitle:"${title}"`;
+        });
+
+        FILTER_TITLE.push(`(${value.join(' AND ')})`);
+
+    });
+
+    //url match words
+    const URL_MATCH = [];
+    if(config.urlMatch) config.urlMatch.forEach((urlMatch) => {
+
+        const value = urlMatch.map((content) => {
+            return `inurl:${content}`;
+        });
+
+        URL_MATCH.push(`(${value.join(' AND ')})`);
+
+    });
+
     //building url
-    const SEARCH_TERM = config.search + " " + EXCLUDE_WORDS.join(" ") + " " + EXCLUDE_DOMAINS.join(" ") + " " + DOMAINS.join(' OR ');
+    const SEARCH_TERM = config.search + 
+    " " + URL_MATCH.join(" OR ") +
+    " " + FILTER_TITLE.join(" OR ") +
+    " " + EXCLUDE_WORDS.join(" ") + 
+    " " + EXCLUDE_DOMAINS.join(" ") + 
+    " " + DOMAINS.join(" OR ");
+
     const SEARCH = encodeURIComponent(SEARCH_TERM.trim())
     const QUERY = Object.assign(GOOGLE_CONSTANT.forceGoogleImage, {
         [GOOGLE_CONSTANT.queryParam]: Object.values(config.query || {}).join(','),

package/test/test-filter-titles.js

@@ -0,0 +1,16 @@
+const { GOOGLE_IMG_SCRAP } = require('../src/google-img-scrap');
+
+(async function(){
+    const test = await GOOGLE_IMG_SCRAP({
+        search: "cats",
+        filterByTitles: [
+            ["draw", "white"],
+            ["albino", "white"]
+        ],
+        execute: function(element){
+            if(!element.url.match('gstatic.com')) return element;
+        }
+    });
+
+    console.log(test, test.result.length);
+})();

package/test/test-url-match.js

@@ -0,0 +1,16 @@
+const { GOOGLE_IMG_SCRAP } = require('../src/google-img-scrap');
+
+(async function(){
+    const test = await GOOGLE_IMG_SCRAP({
+        search: "cats",
+        urlMatch: [
+            ["cdn"],
+            ["istockphoto"]
+        ],
+        execute: function(element){
+            if(!element.url.match('gstatic.com')) return element;
+        }
+    });
+
+    console.log(test, test.result.length);
+})();