new version

README.md

@@ -108,6 +108,13 @@ const se_scraper = require('se-scraper');
         search_engine: 'google',
         keywords: ['news', 'se-scraper'],
         num_pages: 1,
+        // add some cool google search settings
+        google_settings: {
+            gl: 'us', // The gl parameter determines the Google country to use for the query.
+            hl: 'en', // The hl parameter determines the Google UI language to return results.
+            start: 0, // Determines the results offset to use, defaults to 0.
+            num: 100, // Determines the number of results to show, defaults to 10. Maximum is 100.
+        },
     };
 
     var scraper = new se_scraper.ScrapeManager(browser_config);
@@ -286,14 +293,13 @@ Use **se-scraper** by calling it with a script such as the one below.
 ```js
 const se_scraper = require('se-scraper');
 
-let config = {
+// those options need to be provided on startup
+// and cannot give to se-scraper on scrape() calls
+let browser_config = {
     // the user agent to scrape with
     user_agent: 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36',
     // if random_user_agent is set to True, a random user agent is chosen
-    random_user_agent: true,
+    random_user_agent: false,
-    // how long to sleep between requests. a random sleep interval within the range [a,b]
-    // is drawn before every request. empty string for no sleeping.
-    sleep_range: '',
     // whether to start the browser in headless mode
     headless: true,
     // whether debug information should be printed
@@ -304,11 +310,6 @@ let config = {
     debug_level: 1,
     // specify flags passed to chrome here
     chrome_flags: [],
-    // path to output file, data will be stored in JSON
-    output_file: 'examples/results/baidu.json',
-    // whether to prevent images, css, fonts from being loaded
-    // will speed up scraping a great deal
-    block_assets: false,
     // path to js module that extends functionality
     // this module should export the functions:
     // get_browser, handle_metadata, close_browser
@@ -323,14 +324,6 @@ let config = {
     // socks5://78.94.172.42:1080
     // http://118.174.233.10:48400
     proxy_file: '',
-    // check if headless chrome escapes common detection techniques
-    // this is a quick test and should be used for debugging
-    test_evasion: false,
-    apply_evasion_techniques: true,
-    // log ip address data
-    log_ip_address: false,
-    // log http headers
-    log_http_headers: false,
     puppeteer_cluster_config: {
         timeout: 10 * 60 * 1000, // max timeout set to 10 minutes
         monitor: false,
@@ -340,18 +333,43 @@ let config = {
 };
 
 (async () => {
+    // scrape config can change on each scrape() call
     let scrape_config = {
         // which search engine to scrape
-        search_engine: 'bing',
+        search_engine: 'google',
         // an array of keywords to scrape
         keywords: ['cat', 'mouse'],
-        // alternatively you can specify a keyword_file. this overwrites the keywords array
-        keyword_file: '',
         // the number of pages to scrape for each keyword
         num_pages: 2,
+
+        // OPTIONAL PARAMS BELOW:
+        google_settings: {
+            gl: 'us', // The gl parameter determines the Google country to use for the query.
+            hl: 'fr', // The hl parameter determines the Google UI language to return results.
+            start: 0, // Determines the results offset to use, defaults to 0.
+            num: 100, // Determines the number of results to show, defaults to 10. Maximum is 100.
+        },
+        // instead of keywords you can specify a keyword_file. this overwrites the keywords array
+        keyword_file: '',
+        // how long to sleep between requests. a random sleep interval within the range [a,b]
+        // is drawn before every request. empty string for no sleeping.
+        sleep_range: '',
+        // path to output file, data will be stored in JSON
+        output_file: 'output.json',
+        // whether to prevent images, css, fonts from being loaded
+        // will speed up scraping a great deal
+        block_assets: false,
+        // check if headless chrome escapes common detection techniques
+        // this is a quick test and should be used for debugging
+        test_evasion: false,
+        apply_evasion_techniques: true,
+        // log ip address data
+        log_ip_address: false,
+        // log http headers
+        log_http_headers: false,
     };
 
-    let results = await se_scraper.scrape(config, scrape_config);
+    let results = await se_scraper.scrape(browser_config, scrape_config);
     console.dir(results, {depth: null, colors: true});
 })();
 ```

TODO.md

@@ -42,7 +42,7 @@
 
 ### 11.6.2019
     - TODO: fix amazon scraping
-    - change api of remaining test cases
+    - change api of remaining test cases [done]
     - TODO: implement custom search engine parameters on scrape()
 
 ### TODO:

examples/quickstart.js

@@ -10,6 +10,13 @@ const se_scraper = require('./../src/node_scraper.js');
         search_engine: 'google',
         keywords: ['news', 'se-scraper'],
         num_pages: 1,
+        // add some cool google search settings
+        google_settings: {
+            gl: 'us', // The gl parameter determines the Google country to use for the query.
+            hl: 'en', // The hl parameter determines the Google UI language to return results.
+            start: 0, // Determines the results offset to use, defaults to 0.
+            num: 100, // Determines the number of results to show, defaults to 10. Maximum is 100.
+        },
     };
 
     var scraper = new se_scraper.ScrapeManager(browser_config);

package.json

@@ -1,6 +1,6 @@
 {
   "name": "se-scraper",
-  "version": "1.3.0",
+  "version": "1.3.1",
   "description": "A module using puppeteer to scrape several search engines such as Google, Duckduckgo, Bing or Baidu",
   "homepage": "https://scrapeulous.com/",
   "main": "index.js",

run.js

@@ -1,13 +1,12 @@
 const se_scraper = require('./index.js');
 
-let config = {
+// those options need to be provided on startup
+// and cannot give to se-scraper on scrape() calls
+let browser_config = {
     // the user agent to scrape with
     user_agent: 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36',
     // if random_user_agent is set to True, a random user agent is chosen
-    random_user_agent: true,
+    random_user_agent: false,
-    // how long to sleep between requests. a random sleep interval within the range [a,b]
-    // is drawn before every request. empty string for no sleeping.
-    sleep_range: '',
     // whether to start the browser in headless mode
     headless: true,
     // whether debug information should be printed
@@ -18,11 +17,6 @@ let config = {
     debug_level: 1,
     // specify flags passed to chrome here
     chrome_flags: [],
-    // path to output file, data will be stored in JSON
-    output_file: 'examples/results/baidu.json',
-    // whether to prevent images, css, fonts from being loaded
-    // will speed up scraping a great deal
-    block_assets: false,
     // path to js module that extends functionality
     // this module should export the functions:
     // get_browser, handle_metadata, close_browser
@@ -37,35 +31,52 @@ let config = {
     // socks5://78.94.172.42:1080
     // http://118.174.233.10:48400
     proxy_file: '',
-    // check if headless chrome escapes common detection techniques
-    // this is a quick test and should be used for debugging
-    test_evasion: false,
-    apply_evasion_techniques: true,
-    // log ip address data
-    log_ip_address: false,
-    // log http headers
-    log_http_headers: false,
     puppeteer_cluster_config: {
         timeout: 10 * 60 * 1000, // max timeout set to 10 minutes
         monitor: false,
         concurrency: 1, // one scraper per tab
-        maxConcurrency: 1, // scrape with 2 tabs
+        maxConcurrency: 1, // scrape with 1 tab
     }
 };
 
 (async () => {
+    // scrape config can change on each scrape() call
     let scrape_config = {
         // which search engine to scrape
-        search_engine: 'bing',
+        search_engine: 'google',
         // an array of keywords to scrape
         keywords: ['cat', 'mouse'],
-        // alternatively you can specify a keyword_file. this overwrites the keywords array
-        keyword_file: '',
         // the number of pages to scrape for each keyword
         num_pages: 2,
+
+        // OPTIONAL PARAMS BELOW:
+        google_settings: {
+            gl: 'us', // The gl parameter determines the Google country to use for the query.
+            hl: 'fr', // The hl parameter determines the Google UI language to return results.
+            start: 0, // Determines the results offset to use, defaults to 0.
+            num: 100, // Determines the number of results to show, defaults to 10. Maximum is 100.
+        },
+        // instead of keywords you can specify a keyword_file. this overwrites the keywords array
+        keyword_file: '',
+        // how long to sleep between requests. a random sleep interval within the range [a,b]
+        // is drawn before every request. empty string for no sleeping.
+        sleep_range: '',
+        // path to output file, data will be stored in JSON
+        output_file: 'examples/results/advanced.json',
+        // whether to prevent images, css, fonts from being loaded
+        // will speed up scraping a great deal
+        block_assets: false,
+        // check if headless chrome escapes common detection techniques
+        // this is a quick test and should be used for debugging
+        test_evasion: false,
+        apply_evasion_techniques: true,
+        // log ip address data
+        log_ip_address: false,
+        // log http headers
+        log_http_headers: false,
     };
 
-    let results = await se_scraper.scrape(config, scrape_config);
+    let results = await se_scraper.scrape(browser_config, scrape_config);
     console.dir(results, {depth: null, colors: true});
 })();
 

src/node_scraper.js

@@ -251,7 +251,7 @@ class ScrapeManager {
 
             this.cluster.on('taskerror', (err, data) => {
                 console.log(`Error while scraping ${data}: ${err.message}`);
-                console.log(err)
+                console.log(err);
             });
 
         }
@@ -261,9 +261,13 @@ class ScrapeManager {
      * Scrapes the keywords specified by the config.
      */
     async scrape(scrape_config = {}) {
-        this.config.keywords = scrape_config.keywords;
+
-        this.config.num_pages = scrape_config.num_pages;
+        if (!scrape_config.keywords && !scrape_config.keyword_file) {
-        this.config.search_engine = scrape_config.search_engine;
+            console.error('Either keywords or keyword_file must be supplied to scrape()')
+            return;
+        }
+
+        Object.assign(this.config, scrape_config);
 
         var results = {};
         var num_requests = 0;
@@ -283,7 +287,7 @@ class ScrapeManager {
             //     const page = await this.browser.newPage();
             //     this.scraper = getScraper(this.config.search_engine, {
             //         config: this.config,
-            //         context: context,
+            //         context: {},
             //         pluggable: pluggable,
             //         page: page,
             //     });
@@ -382,14 +386,9 @@ class ScrapeManager {
         }
 
         return {
-            headers: {
-                'Content-Type': 'text/json',
-            },
             results: results,
             metadata: metadata || {},
-            statusCode: 200
         };
-
     }
 
     /*
@@ -436,7 +435,6 @@ function parseEventData(config) {
 }
 
 
-
 module.exports = {
     ScrapeManager: ScrapeManager,
 };

test/test_amazon.js

@@ -30,8 +30,6 @@ async function normal_search_test() {
 
 // we test with a callback function to our handler
 function normal_search_test_case(response) {
-    assert.equal(response.headers['Content-Type'], 'text/json', 'content type is not text/json');
-    assert.equal(response.statusCode, 200, 'status code must be 200');
     assert.equal(response.metadata.num_requests, 2);
 
     for (let query in response.results) {
@@ -113,8 +111,6 @@ async function no_results_test() {
 
 // we test with a callback function to our handler
 function test_case_no_results(response) {
-    assert.equal(response.headers['Content-Type'], 'text/json', 'content type is not text/json');
-    assert.equal(response.statusCode, 200, 'status code must be 200');
     assert.equal(response.metadata.num_requests, 1);
 
     results = response.results;

test/test_baidu.js

@@ -30,8 +30,6 @@ async function normal_search_test() {
 
 // we test with a callback function to our handler
 function normal_search_test_case(response) {
-    assert.equal(response.headers['Content-Type'], 'text/json', 'content type is not text/json');
-    assert.equal(response.statusCode, 200, 'status code must be 200');
     assert.equal(response.metadata.num_requests, 4);
 
     for (let query in response.results) {

test/test_bing.js

@@ -35,8 +35,6 @@ async function normal_search_test() {
 
 // we test with a callback function to our handler
 function normal_search_test_case(response) {
-    assert.equal(response.headers['Content-Type'], 'text/json', 'content type is not text/json');
-    assert.equal(response.statusCode, 200, 'status code must be 200');
     assert.equal(response.metadata.num_requests, 6);
 
     for (let query in response.results) {
@@ -113,8 +111,6 @@ async function no_results_test() {
 
 // we test with a callback function to our handler
 function test_case_no_results(response) {
-    assert.equal(response.headers['Content-Type'], 'text/json', 'content type is not text/json');
-    assert.equal(response.statusCode, 200, 'status code must be 200');
     assert.equal(response.metadata.num_requests, 1);
 
     results = response.results;
@@ -164,8 +160,6 @@ async function effective_query_test() {
 
 // we test with a callback function to our handler
 function test_case_effective_query(response) {
-    assert.equal(response.headers['Content-Type'], 'text/json', 'content type is not text/json');
-    assert.equal(response.statusCode, 200, 'status code must be 200');
     assert.equal(response.metadata.num_requests, 1);
 
     results = response.results;

test/test_duckduckgo.js

@@ -32,8 +32,6 @@ async function normal_search_test() {
 
 // we test with a callback function to our handler
 function normal_search_test_case(response) {
-    assert.equal(response.headers['Content-Type'], 'text/json', 'content type is not text/json');
-    assert.equal(response.statusCode, 200, 'status code must be 200');
     assert.equal(response.metadata.num_requests, 2);
 
     for (let query in response.results) {
@@ -105,8 +103,6 @@ async function effective_query_test() {
 
 // we test with a callback function to our handler
 function test_case_effective_query(response) {
-    assert.equal(response.headers['Content-Type'], 'text/json', 'content type is not text/json');
-    assert.equal(response.statusCode, 200, 'status code must be 200');
     assert.equal(response.metadata.num_requests, 1);
 
     results = response.results;

test/test_google.js

@@ -32,8 +32,6 @@ async function normal_search_test() {
 
 // we test with a callback function to our handler
 function normal_search_test_case(response) {
-    assert.equal(response.headers['Content-Type'], 'text/json', 'content type is not text/json');
-    assert.equal(response.statusCode, 200, 'status code must be 200');
     assert.equal(response.metadata.num_requests, 6);
 
     for (let query in response.results) {
@@ -108,8 +106,6 @@ async function no_results_test() {
 
 // we test with a callback function to our handler
 function test_case_no_results(response) {
-    assert.equal(response.headers['Content-Type'], 'text/json', 'content type is not text/json');
-    assert.equal(response.statusCode, 200, 'status code must be 200');
     assert.equal(response.metadata.num_requests, 1);
 
     results = response.results;
@@ -159,8 +155,6 @@ async function effective_query_test() {
 
 // we test with a callback function to our handler
 function test_case_effective_query(response) {
-    assert.equal(response.headers['Content-Type'], 'text/json', 'content type is not text/json');
-    assert.equal(response.statusCode, 200, 'status code must be 200');
     assert.equal(response.metadata.num_requests, 1);
 
     results = response.results;

test/test_googleimage.js

@@ -34,8 +34,6 @@ function normal_image_search_test_case(err, response) {
     if (err) {
         console.error(err);
     } else {
-        assert.equal(response.headers['Content-Type'], 'text/json', 'content type is not text/json');
-        assert.equal(response.statusCode, 200, 'status code must be 200');
         assert.equal(response.metadata.num_requests, 2);
 
         for (let query in response.results) {

test/test_queryargs_google.js

@@ -35,8 +35,6 @@ function queryargs_search_test_case(err, response) {
     if (err) {
         console.error(err);
     } else {
-        assert.equal(response.headers['Content-Type'], 'text/json', 'content type is not text/json');
-        assert.equal(response.statusCode, 200, 'status code must be 200');
         assert.equal(response.metadata.num_requests, 2);
 
         for (let query in response.results) {

test/test_ticker_search.js

@@ -34,8 +34,6 @@ function reuters_search_test_case(err, response) {
     if (err) {
         console.error(err);
     } else {
-        assert.equal(response.headers['Content-Type'], 'text/json', 'content type is not text/json');
-        assert.equal(response.statusCode, 200, 'status code must be 200');
 
         for (let query in response.results) {
             let total_rank = 1;
@@ -103,8 +101,6 @@ function cnbc_search_test_case(err, response) {
     if (err) {
         console.error(err);
     } else {
-        assert.equal(response.headers['Content-Type'], 'text/json', 'content type is not text/json');
-        assert.equal(response.statusCode, 200, 'status code must be 200');
 
         for (let query in response.results) {
             let total_rank = 1;
@@ -170,8 +166,6 @@ function marketwatch_search_test_case(err, response) {
     if (err) {
         console.error(err);
     } else {
-        assert.equal(response.headers['Content-Type'], 'text/json', 'content type is not text/json');
-        assert.equal(response.statusCode, 200, 'status code must be 200');
 
         for (let query in response.results) {
             let total_rank = 1;