From a3ebe357a45a41c962e845d29727596d9978b0ff Mon Sep 17 00:00:00 2001 From: Thomas Date: Thu, 18 Apr 2019 15:23:01 +0200 Subject: [PATCH 1/3] Add html_output fonctionality Pagination support for html output Change return value to keep it compliant to the current version of se-scrapper --- src/modules/se_scraper.js | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/src/modules/se_scraper.js b/src/modules/se_scraper.js index 59fd1f0..dc3cf82 100644 --- a/src/modules/se_scraper.js +++ b/src/modules/se_scraper.js @@ -33,6 +33,7 @@ module.exports = class Scraper { this.PROXY_TIMEOUT = 15000; this.SOLVE_CAPTCHA_TIME = 45000; + this.html_output = {}; this.results = {}; this.result_rank = 1; // keep track of the requests done @@ -69,7 +70,15 @@ module.exports = class Scraper { await this.scraping_loop(); - return this.results; + let response = this.results; + if (this.config.html_output) { + response = { + 'results': this.results, + 'html_output': this.html_output + }; + } + + return response; } /** @@ -155,6 +164,7 @@ module.exports = class Scraper { this.num_keywords++; this.keyword = keyword; this.results[keyword] = {}; + this.html_output[keyword] = {}; this.result_rank = 1; if (this.pluggable && this.pluggable.before_keyword_scraped) { @@ -189,6 +199,7 @@ module.exports = class Scraper { } let html = await this.page.content(); + this.html_output[keyword][page_num] = html; let parsed = this.parse(html); this.results[keyword][page_num] = parsed ? parsed : await this.parse_async(html); @@ -484,4 +495,4 @@ async function evadeChromeHeadlessDetection(page) { } catch (e) { console.error(e); } -} \ No newline at end of file +} From a0e63aa4b00f5d0c842f1bb2810770329b88cba9 Mon Sep 17 00:00:00 2001 From: Thomas Date: Fri, 26 Apr 2019 15:13:51 +0200 Subject: [PATCH 2/3] Use bing_setting.bing_domain if defined for startUrl --- src/modules/bing.js | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/src/modules/bing.js b/src/modules/bing.js index d536761..a888c8f 100644 --- a/src/modules/bing.js +++ b/src/modules/bing.js @@ -47,6 +47,21 @@ class BingScraper extends Scraper { async load_start_page() { let startUrl = this.build_start_url('https://www.bing.com/search?') || 'https://www.bing.com/'; + if (this.config.bing_settings) { + startUrl = `https://www.${this.config.bing_settings.bing_domain}/search?`; + if (this.config.bing_settings.bing_domain) { + startUrl = `https://www.${this.config.bing_settings.bing_domain}/search?`; + } else { + startUrl = `https://www.bing.com/search?`; + } + + for (var key in this.config.bing_settings) { + if (key !== 'bing_domain') { + startUrl += `${key}=${this.config.bing_settings[key]}&` + } + } + } + try { await this.page.goto(startUrl); await this.page.waitForSelector('input[name="q"]', { timeout: this.STANDARD_TIMEOUT }); @@ -171,4 +186,4 @@ class BingNewsScraper extends Scraper { module.exports = { BingNewsScraper: BingNewsScraper, BingScraper: BingScraper, -}; \ No newline at end of file +}; From d9ac9f416281575522c73e71976f51108bc5f0cd Mon Sep 17 00:00:00 2001 From: HugoPoi Date: Wed, 26 Jun 2019 12:03:42 +0200 Subject: [PATCH 3/3] Add test for html_output, refactor the results return --- package-lock.json | 874 +++++++++++++++++++++++++++++++++++++- package.json | 6 +- src/modules/se_scraper.js | 19 +- src/node_scraper.js | 14 +- test/test_google.js | 52 ++- 5 files changed, 930 insertions(+), 35 deletions(-) diff --git a/package-lock.json b/package-lock.json index d8484a0..6571583 100644 --- a/package-lock.json +++ b/package-lock.json @@ -1,6 +1,6 @@ { "name": "se-scraper", - "version": "1.3.0", + "version": "1.3.8", "lockfileVersion": 1, "requires": true, "dependencies": { @@ -30,10 +30,41 @@ "es6-promisify": "^5.0.0" } }, + "ansi-colors": { + "version": "3.2.3", + "resolved": "https://registry.npmjs.org/ansi-colors/-/ansi-colors-3.2.3.tgz", + "integrity": "sha512-LEHHyuhlPY3TmuUYMh2oz89lTShfvgbmzaBcxve9t/9Wuy7Dwf4yoAKcND7KFT1HAQfqZ12qtc+DUrBMeKF9nw==", + "dev": true + }, + "ansi-regex": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-3.0.0.tgz", + "integrity": "sha1-7QMXwyIGT3lGbAKWa922Bas32Zg=", + "dev": true + }, + "ansi-styles": { + "version": "3.2.1", + "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-3.2.1.tgz", + "integrity": "sha512-VT0ZI6kZRdTh8YyJw3SMbYm/u+NqfsAxEpWO0Pf9sq8/e94WxxOpPKx9FR1FlyCtOVDNOQ+8ntlqFxiRc+r5qA==", + "dev": true, + "requires": { + "color-convert": "^1.9.0" + } + }, + "argparse": { + "version": "1.0.10", + "resolved": "https://registry.npmjs.org/argparse/-/argparse-1.0.10.tgz", + "integrity": "sha512-o5Roy6tNG4SL/FOkCAN6RzjiakZS25RLYFrcMttJqbdd8BWrnA+fGz57iN5Pb06pvBGvl5gQ0B48dJlslXvoTg==", + "dev": true, + "requires": { + "sprintf-js": "~1.0.2" + } + }, "assertion-error": { "version": "1.1.0", "resolved": "https://registry.npmjs.org/assertion-error/-/assertion-error-1.1.0.tgz", - "integrity": "sha512-jgsaNduz+ndvGyFt3uSuWqvy4lCnIJiovtouQN5JZHOKCS2QuhEdbcQHFhVksz2N2U9hXJo8odG7ETyWlEeuDw==" + "integrity": "sha512-jgsaNduz+ndvGyFt3uSuWqvy4lCnIJiovtouQN5JZHOKCS2QuhEdbcQHFhVksz2N2U9hXJo8odG7ETyWlEeuDw==", + "dev": true }, "async-limiter": { "version": "1.0.0", @@ -64,6 +95,12 @@ "concat-map": "0.0.1" } }, + "browser-stdout": { + "version": "1.3.1", + "resolved": "https://registry.npmjs.org/browser-stdout/-/browser-stdout-1.3.1.tgz", + "integrity": "sha512-qhAVI1+Av2X7qelOfAIYwXONood6XlZE/fXaBSmW/T5SzLAmCgzi+eiWE7fUvbHaeNBQH13UftjpXxsfLkMpgw==", + "dev": true + }, "buffer-from": { "version": "1.1.1", "resolved": "https://registry.npmjs.org/buffer-from/-/buffer-from-1.1.1.tgz", @@ -83,10 +120,17 @@ "responselike": "^1.0.2" } }, + "camelcase": { + "version": "5.3.1", + "resolved": "https://registry.npmjs.org/camelcase/-/camelcase-5.3.1.tgz", + "integrity": "sha512-L28STB170nwWS63UjtlEOE3dldQApaJXZkOI1uMFfzf3rRuPegHaHesyee+YxQ+W6SvRDQV6UrdOdRiR153wJg==", + "dev": true + }, "chai": { "version": "4.2.0", "resolved": "https://registry.npmjs.org/chai/-/chai-4.2.0.tgz", "integrity": "sha512-XQU3bhBukrOsQCuwZndwGcCVQHyZi53fQ6Ys1Fym7E4olpIqqZZhhoFJoaKVvV17lWQoXYwgWN2nF5crA8J2jw==", + "dev": true, "requires": { "assertion-error": "^1.1.0", "check-error": "^1.0.2", @@ -96,10 +140,39 @@ "type-detect": "^4.0.5" } }, + "chai-string": { + "version": "1.5.0", + "resolved": "https://registry.npmjs.org/chai-string/-/chai-string-1.5.0.tgz", + "integrity": "sha512-sydDC3S3pNAQMYwJrs6dQX0oBQ6KfIPuOZ78n7rocW0eJJlsHPh2t3kwW7xfwYA/1Bf6/arGtSUo16rxR2JFlw==", + "dev": true + }, + "chalk": { + "version": "2.4.2", + "resolved": "https://registry.npmjs.org/chalk/-/chalk-2.4.2.tgz", + "integrity": "sha512-Mti+f9lpJNcwF4tWV8/OrTTtF1gZi+f8FqlyAdouralcFWFQWF2+NgCHShjkCb+IFBLq9buZwE1xckQU4peSuQ==", + "dev": true, + "requires": { + "ansi-styles": "^3.2.1", + "escape-string-regexp": "^1.0.5", + "supports-color": "^5.3.0" + }, + "dependencies": { + "supports-color": { + "version": "5.5.0", + "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-5.5.0.tgz", + "integrity": "sha512-QjVjwdXIt408MIiAqCX4oUKsgU2EqAGzs2Ppkm4aQYbjm+ZEWEcW4SfFNTr4uMNZma0ey4f5lgLrkB0aX0QMow==", + "dev": true, + "requires": { + "has-flag": "^3.0.0" + } + } + } + }, "check-error": { "version": "1.0.2", "resolved": "https://registry.npmjs.org/check-error/-/check-error-1.0.2.tgz", - "integrity": "sha1-V00xLt2Iu13YkS6Sht1sCu1KrII=" + "integrity": "sha1-V00xLt2Iu13YkS6Sht1sCu1KrII=", + "dev": true }, "cheerio": { "version": "1.0.0-rc.2", @@ -114,6 +187,17 @@ "parse5": "^3.0.1" } }, + "cliui": { + "version": "4.1.0", + "resolved": "https://registry.npmjs.org/cliui/-/cliui-4.1.0.tgz", + "integrity": "sha512-4FG+RSG9DL7uEwRUZXZn3SS34DiDPfzP0VOiEwtUWlE+AR2EIg+hSyvrIgUUfhdgR/UkAeW2QHgeP+hWrXs7jQ==", + "dev": true, + "requires": { + "string-width": "^2.1.1", + "strip-ansi": "^4.0.0", + "wrap-ansi": "^2.0.0" + } + }, "clone-response": { "version": "1.0.2", "resolved": "https://registry.npmjs.org/clone-response/-/clone-response-1.0.2.tgz", @@ -122,6 +206,27 @@ "mimic-response": "^1.0.0" } }, + "code-point-at": { + "version": "1.1.0", + "resolved": "https://registry.npmjs.org/code-point-at/-/code-point-at-1.1.0.tgz", + "integrity": "sha1-DQcLTQQ6W+ozovGkDi7bPZpMz3c=", + "dev": true + }, + "color-convert": { + "version": "1.9.3", + "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-1.9.3.tgz", + "integrity": "sha512-QfAUtd+vFdAtFQcC8CCyYt1fYWxSqAiK2cSD6zDB8N3cpsEBAvRxp9zOGg6G/SHHJYAT88/az/IuDGALsNVbGg==", + "dev": true, + "requires": { + "color-name": "1.1.3" + } + }, + "color-name": { + "version": "1.1.3", + "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.3.tgz", + "integrity": "sha1-p9BVi9icQveV3UIyj3QIMcpTvCU=", + "dev": true + }, "commander": { "version": "2.19.0", "resolved": "https://registry.npmjs.org/commander/-/commander-2.19.0.tgz", @@ -134,7 +239,7 @@ }, "concat-stream": { "version": "1.6.2", - "resolved": "https://registry.npmjs.org/concat-stream/-/concat-stream-1.6.2.tgz", + "resolved": "http://registry.npmjs.org/concat-stream/-/concat-stream-1.6.2.tgz", "integrity": "sha512-27HBghJxjiZtIk3Ycvn/4kbJk/1uZuJFfuPEns6LaEvpvG1f0hTea8lilrouyo9mVc2GWdcEZ8OLoGmSADlrCw==", "requires": { "buffer-from": "^1.0.0", @@ -145,7 +250,7 @@ "dependencies": { "readable-stream": { "version": "2.3.6", - "resolved": "https://registry.npmjs.org/readable-stream/-/readable-stream-2.3.6.tgz", + "resolved": "http://registry.npmjs.org/readable-stream/-/readable-stream-2.3.6.tgz", "integrity": "sha512-tQtKA9WIAhBF3+VLAseyMqZeBjW0AHJoxOtYqSUZNJxauErmLbVm2FW1y+J/YA9dUrAC39ITejlZWhVIwawkKw==", "requires": { "core-util-is": "~1.0.0", @@ -159,7 +264,7 @@ }, "string_decoder": { "version": "1.1.1", - "resolved": "https://registry.npmjs.org/string_decoder/-/string_decoder-1.1.1.tgz", + "resolved": "http://registry.npmjs.org/string_decoder/-/string_decoder-1.1.1.tgz", "integrity": "sha512-n/ShnvDi6FHbbVfviro+WojiFzv+s8MPMHBczVePfUpDJLwoLT0ht1l4YwBCbi8pJAveEEdnkHyPyTP/mzRfwg==", "requires": { "safe-buffer": "~5.1.0" @@ -172,6 +277,19 @@ "resolved": "https://registry.npmjs.org/core-util-is/-/core-util-is-1.0.2.tgz", "integrity": "sha1-tf1UIgqivFq1eqtxQMlAdUUDwac=" }, + "cross-spawn": { + "version": "6.0.5", + "resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-6.0.5.tgz", + "integrity": "sha512-eTVLrBSt7fjbDygz805pMnstIs2VTBNkRm0qxZd+M7A5XDdxVRWO5MxGBXZhjY4cqLYLdtrGqRf8mBPmzwSpWQ==", + "dev": true, + "requires": { + "nice-try": "^1.0.4", + "path-key": "^2.0.1", + "semver": "^5.5.0", + "shebang-command": "^1.2.0", + "which": "^1.2.9" + } + }, "css-select": { "version": "1.2.0", "resolved": "http://registry.npmjs.org/css-select/-/css-select-1.2.0.tgz", @@ -196,6 +314,12 @@ "ms": "^2.1.1" } }, + "decamelize": { + "version": "1.2.0", + "resolved": "https://registry.npmjs.org/decamelize/-/decamelize-1.2.0.tgz", + "integrity": "sha1-9lNNFRSCabIDUue+4m9QH5oZEpA=", + "dev": true + }, "decompress-response": { "version": "3.3.0", "resolved": "https://registry.npmjs.org/decompress-response/-/decompress-response-3.3.0.tgz", @@ -208,6 +332,7 @@ "version": "3.0.1", "resolved": "https://registry.npmjs.org/deep-eql/-/deep-eql-3.0.1.tgz", "integrity": "sha512-+QeIQyN5ZuO+3Uk5DYh6/1eKO0m0YmJFGNmFHGACpf1ClL1nmlV/p4gNgbl2pJGxgXb4faqo6UE+M5ACEMyVcw==", + "dev": true, "requires": { "type-detect": "^4.0.0" } @@ -217,6 +342,21 @@ "resolved": "https://registry.npmjs.org/defer-to-connect/-/defer-to-connect-1.0.2.tgz", "integrity": "sha512-k09hcQcTDY+cwgiwa6PYKLm3jlagNzQ+RSvhjzESOGOx+MNOuXkxTfEvPrO1IOQ81tArCFYQgi631clB70RpQw==" }, + "define-properties": { + "version": "1.1.3", + "resolved": "https://registry.npmjs.org/define-properties/-/define-properties-1.1.3.tgz", + "integrity": "sha512-3MqfYKj2lLzdMSf8ZIZE/V+Zuy+BgD6f164e8K2w7dgnpKArBDerGYpM46IYYcjnkdPNMjPk9A6VFB8+3SKlXQ==", + "dev": true, + "requires": { + "object-keys": "^1.0.12" + } + }, + "diff": { + "version": "3.5.0", + "resolved": "https://registry.npmjs.org/diff/-/diff-3.5.0.tgz", + "integrity": "sha512-A46qtFgd+g7pDZinpnwiRJtxbC1hpgf0uzP3iG89scHk0AUC7A1TGxf5OiiOUv/JMZR8GOt8hL900hV0bOy5xA==", + "dev": true + }, "dom-serializer": { "version": "0.1.0", "resolved": "https://registry.npmjs.org/dom-serializer/-/dom-serializer-0.1.0.tgz", @@ -260,6 +400,12 @@ "resolved": "https://registry.npmjs.org/duplexer3/-/duplexer3-0.1.4.tgz", "integrity": "sha1-7gHdHKwO08vH/b6jfcCo8c4ALOI=" }, + "emoji-regex": { + "version": "7.0.3", + "resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-7.0.3.tgz", + "integrity": "sha512-CwBLREIQ7LvYFB0WyRvwhq5N5qPhc6PMjD6bYggFlI5YyDgl+0vxq5VHbMOFqLg7hfWzmu8T5Z1QofhmTIhItA==", + "dev": true + }, "end-of-stream": { "version": "1.4.1", "resolved": "https://registry.npmjs.org/end-of-stream/-/end-of-stream-1.4.1.tgz", @@ -273,6 +419,31 @@ "resolved": "https://registry.npmjs.org/entities/-/entities-1.1.2.tgz", "integrity": "sha512-f2LZMYl1Fzu7YSBKg+RoROelpOaNrcGmE9AZubeDfrCEia483oW4MI4VyFd5VNHIgQ/7qm1I0wUHK1eJnn2y2w==" }, + "es-abstract": { + "version": "1.13.0", + "resolved": "https://registry.npmjs.org/es-abstract/-/es-abstract-1.13.0.tgz", + "integrity": "sha512-vDZfg/ykNxQVwup/8E1BZhVzFfBxs9NqMzGcvIJrqg5k2/5Za2bWo40dK2J1pgLngZ7c+Shh8lwYtLGyrwPutg==", + "dev": true, + "requires": { + "es-to-primitive": "^1.2.0", + "function-bind": "^1.1.1", + "has": "^1.0.3", + "is-callable": "^1.1.4", + "is-regex": "^1.0.4", + "object-keys": "^1.0.12" + } + }, + "es-to-primitive": { + "version": "1.2.0", + "resolved": "https://registry.npmjs.org/es-to-primitive/-/es-to-primitive-1.2.0.tgz", + "integrity": "sha512-qZryBOJjV//LaxLTV6UC//WewneB3LcXOL9NP++ozKVXsIIIpm/2c13UDiD9Jp2eThsecw9m3jPqDwTyobcdbg==", + "dev": true, + "requires": { + "is-callable": "^1.1.4", + "is-date-object": "^1.0.1", + "is-symbol": "^1.0.2" + } + }, "es6-promise": { "version": "4.2.8", "resolved": "https://registry.npmjs.org/es6-promise/-/es6-promise-4.2.8.tgz", @@ -280,12 +451,39 @@ }, "es6-promisify": { "version": "5.0.0", - "resolved": "https://registry.npmjs.org/es6-promisify/-/es6-promisify-5.0.0.tgz", + "resolved": "http://registry.npmjs.org/es6-promisify/-/es6-promisify-5.0.0.tgz", "integrity": "sha1-UQnWLz5W6pZ8S2NQWu8IKRyKUgM=", "requires": { "es6-promise": "^4.0.3" } }, + "escape-string-regexp": { + "version": "1.0.5", + "resolved": "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-1.0.5.tgz", + "integrity": "sha1-G2HAViGQqN/2rjuyzwIAyhMLhtQ=", + "dev": true + }, + "esprima": { + "version": "4.0.1", + "resolved": "https://registry.npmjs.org/esprima/-/esprima-4.0.1.tgz", + "integrity": "sha512-eGuFFw7Upda+g4p+QHvnW0RyTX/SVeJBDM/gCtMARO0cLuT2HcEKnTPvhjV6aGeqrCB/sbNop0Kszm0jsaWU4A==", + "dev": true + }, + "execa": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/execa/-/execa-1.0.0.tgz", + "integrity": "sha512-adbxcyWV46qiHyvSp50TKt05tB4tK3HcmF7/nxfAdhnox83seTDbwnaqKO4sXRy7roHAIFqJP/Rw/AuEbX61LA==", + "dev": true, + "requires": { + "cross-spawn": "^6.0.0", + "get-stream": "^4.0.0", + "is-stream": "^1.1.0", + "npm-run-path": "^2.0.0", + "p-finally": "^1.0.0", + "signal-exit": "^3.0.0", + "strip-eof": "^1.0.0" + } + }, "extract-zip": { "version": "1.6.7", "resolved": "https://registry.npmjs.org/extract-zip/-/extract-zip-1.6.7.tgz", @@ -320,15 +518,46 @@ "pend": "~1.2.0" } }, + "find-up": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/find-up/-/find-up-3.0.0.tgz", + "integrity": "sha512-1yD6RmLI1XBfxugvORwlck6f75tYL+iR0jqwsOrOxMZyGYqUuDhJ0l4AXdO1iX/FTs9cBAMEk1gWSEx1kSbylg==", + "dev": true, + "requires": { + "locate-path": "^3.0.0" + } + }, + "flat": { + "version": "4.1.0", + "resolved": "https://registry.npmjs.org/flat/-/flat-4.1.0.tgz", + "integrity": "sha512-Px/TiLIznH7gEDlPXcUD4KnBusa6kR6ayRUVcnEAbreRIuhkqow/mun59BuRXwoYk7ZQOLW1ZM05ilIvK38hFw==", + "dev": true, + "requires": { + "is-buffer": "~2.0.3" + } + }, "fs.realpath": { "version": "1.0.0", "resolved": "https://registry.npmjs.org/fs.realpath/-/fs.realpath-1.0.0.tgz", "integrity": "sha1-FQStJSMVjKpA20onh8sBQRmU6k8=" }, + "function-bind": { + "version": "1.1.1", + "resolved": "https://registry.npmjs.org/function-bind/-/function-bind-1.1.1.tgz", + "integrity": "sha512-yIovAzMX49sF8Yl58fSCWJ5svSLuaibPxXQJFLmBObTuCr0Mf1KiPopGM9NiFjiYBCbfaa2Fh6breQ6ANVTI0A==", + "dev": true + }, + "get-caller-file": { + "version": "2.0.5", + "resolved": "https://registry.npmjs.org/get-caller-file/-/get-caller-file-2.0.5.tgz", + "integrity": "sha512-DyFP3BM/3YHTQOCUL/w0OZHR0lpKeGrxotcHWcqNEdnltqFwXVfhEBQ94eIo34AfQpo0rGki4cyIiftY06h2Fg==", + "dev": true + }, "get-func-name": { "version": "2.0.0", "resolved": "https://registry.npmjs.org/get-func-name/-/get-func-name-2.0.0.tgz", - "integrity": "sha1-6td0q+5y4gQJQzoGY2YCPdaIekE=" + "integrity": "sha1-6td0q+5y4gQJQzoGY2YCPdaIekE=", + "dev": true }, "get-stream": { "version": "4.1.0", @@ -369,6 +598,39 @@ "url-parse-lax": "^3.0.0" } }, + "growl": { + "version": "1.10.5", + "resolved": "https://registry.npmjs.org/growl/-/growl-1.10.5.tgz", + "integrity": "sha512-qBr4OuELkhPenW6goKVXiv47US3clb3/IbuWF9KNKEijAy9oeHxU9IgzjvJhHkUzhaj7rOUD7+YGWqUjLp5oSA==", + "dev": true + }, + "has": { + "version": "1.0.3", + "resolved": "https://registry.npmjs.org/has/-/has-1.0.3.tgz", + "integrity": "sha512-f2dvO0VU6Oej7RkWJGrehjbzMAjFp5/VKPp5tTpWIV4JHHZK1/BxbFRtf/siA2SWTe09caDmVtYYzWEIbBS4zw==", + "dev": true, + "requires": { + "function-bind": "^1.1.1" + } + }, + "has-flag": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/has-flag/-/has-flag-3.0.0.tgz", + "integrity": "sha1-tdRU3CGZriJWmfNGfloH87lVuv0=", + "dev": true + }, + "has-symbols": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/has-symbols/-/has-symbols-1.0.0.tgz", + "integrity": "sha1-uhqPGvKg/DllD1yFA2dwQSIGO0Q=", + "dev": true + }, + "he": { + "version": "1.2.0", + "resolved": "https://registry.npmjs.org/he/-/he-1.2.0.tgz", + "integrity": "sha512-F/1DnUGPopORZi0ni+CvrCgHQ5FyEAHRLSApuYWMmrbSwoN2Mn/7k+Gl38gJnR7yyDZk6WLXwiGod1JOWNDKGw==", + "dev": true + }, "htmlparser2": { "version": "3.10.0", "resolved": "https://registry.npmjs.org/htmlparser2/-/htmlparser2-3.10.0.tgz", @@ -420,11 +682,81 @@ "resolved": "https://registry.npmjs.org/inherits/-/inherits-2.0.3.tgz", "integrity": "sha1-Yzwsg+PaQqUC9SRmAiSA9CCCYd4=" }, + "invert-kv": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/invert-kv/-/invert-kv-2.0.0.tgz", + "integrity": "sha512-wPVv/y/QQ/Uiirj/vh3oP+1Ww+AWehmi1g5fFWGPF6IpCBCDVrhgHRMvrLfdYcwDh3QJbGXDW4JAuzxElLSqKA==", + "dev": true + }, + "is-buffer": { + "version": "2.0.3", + "resolved": "https://registry.npmjs.org/is-buffer/-/is-buffer-2.0.3.tgz", + "integrity": "sha512-U15Q7MXTuZlrbymiz95PJpZxu8IlipAp4dtS3wOdgPXx3mqBnslrWU14kxfHB+Py/+2PVKSr37dMAgM2A4uArw==", + "dev": true + }, + "is-callable": { + "version": "1.1.4", + "resolved": "https://registry.npmjs.org/is-callable/-/is-callable-1.1.4.tgz", + "integrity": "sha512-r5p9sxJjYnArLjObpjA4xu5EKI3CuKHkJXMhT7kwbpUyIFD1n5PMAsoPvWnvtZiNz7LjkYDRZhd7FlI0eMijEA==", + "dev": true + }, + "is-date-object": { + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/is-date-object/-/is-date-object-1.0.1.tgz", + "integrity": "sha1-mqIOtq7rv/d/vTPnTKAbM1gdOhY=", + "dev": true + }, + "is-fullwidth-code-point": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/is-fullwidth-code-point/-/is-fullwidth-code-point-2.0.0.tgz", + "integrity": "sha1-o7MKXE8ZkYMWeqq5O+764937ZU8=", + "dev": true + }, + "is-regex": { + "version": "1.0.4", + "resolved": "https://registry.npmjs.org/is-regex/-/is-regex-1.0.4.tgz", + "integrity": "sha1-VRdIm1RwkbCTDglWVM7SXul+lJE=", + "dev": true, + "requires": { + "has": "^1.0.1" + } + }, + "is-stream": { + "version": "1.1.0", + "resolved": "https://registry.npmjs.org/is-stream/-/is-stream-1.1.0.tgz", + "integrity": "sha1-EtSj3U5o4Lec6428hBc66A2RykQ=", + "dev": true + }, + "is-symbol": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/is-symbol/-/is-symbol-1.0.2.tgz", + "integrity": "sha512-HS8bZ9ox60yCJLH9snBpIwv9pYUAkcuLhSA1oero1UB5y9aiQpRA8y2ex945AOtCZL1lJDeIk3G5LthswI46Lw==", + "dev": true, + "requires": { + "has-symbols": "^1.0.0" + } + }, "isarray": { "version": "1.0.0", "resolved": "https://registry.npmjs.org/isarray/-/isarray-1.0.0.tgz", "integrity": "sha1-u5NdSFgsuhaMBoNJV6VKPgcSTxE=" }, + "isexe": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/isexe/-/isexe-2.0.0.tgz", + "integrity": "sha1-6PvzdNxVb/iUehDcsFctYz8s+hA=", + "dev": true + }, + "js-yaml": { + "version": "3.13.1", + "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-3.13.1.tgz", + "integrity": "sha512-YfbcO7jXDdyj0DGxYVSlSeQNHbD7XPWvrVWeVUujrQEoZzWJIRrCPoyk6kL6IAjAG2IolMK4T0hNUe0HOUs5Jw==", + "dev": true, + "requires": { + "argparse": "^1.0.7", + "esprima": "^4.0.0" + } + }, "json-buffer": { "version": "3.0.0", "resolved": "https://registry.npmjs.org/json-buffer/-/json-buffer-3.0.0.tgz", @@ -438,21 +770,75 @@ "json-buffer": "3.0.0" } }, + "lcid": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/lcid/-/lcid-2.0.0.tgz", + "integrity": "sha512-avPEb8P8EGnwXKClwsNUgryVjllcRqtMYa49NTsbQagYuT1DcXnl1915oxWjoyGrXR6zH/Y0Zc96xWsPcoDKeA==", + "dev": true, + "requires": { + "invert-kv": "^2.0.0" + } + }, + "locate-path": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/locate-path/-/locate-path-3.0.0.tgz", + "integrity": "sha512-7AO748wWnIhNqAuaty2ZWHkQHRSNfPVIsPIfwEOWO22AmaoVrWavlOcMR5nzTLNYvp36X220/maaRsrec1G65A==", + "dev": true, + "requires": { + "p-locate": "^3.0.0", + "path-exists": "^3.0.0" + } + }, "lodash": { "version": "4.17.11", "resolved": "https://registry.npmjs.org/lodash/-/lodash-4.17.11.tgz", "integrity": "sha512-cQKh8igo5QUhZ7lg38DYWAxMvjSAKG0A8wGSVimP07SIUEK2UO+arSRKbRZWtelMtN5V0Hkwh5ryOto/SshYIg==" }, + "log-symbols": { + "version": "2.2.0", + "resolved": "https://registry.npmjs.org/log-symbols/-/log-symbols-2.2.0.tgz", + "integrity": "sha512-VeIAFslyIerEJLXHziedo2basKbMKtTw3vfn5IzG0XTjhAVEJyNHnL2p7vc+wBDSdQuUpNw3M2u6xb9QsAY5Eg==", + "dev": true, + "requires": { + "chalk": "^2.0.1" + } + }, "lowercase-keys": { "version": "1.0.1", "resolved": "https://registry.npmjs.org/lowercase-keys/-/lowercase-keys-1.0.1.tgz", "integrity": "sha512-G2Lj61tXDnVFFOi8VZds+SoQjtQC3dgokKdDG2mTm1tx4m50NUHBOZSBwQQHyy0V12A0JTG4icfZQH+xPyh8VA==" }, + "map-age-cleaner": { + "version": "0.1.3", + "resolved": "https://registry.npmjs.org/map-age-cleaner/-/map-age-cleaner-0.1.3.tgz", + "integrity": "sha512-bJzx6nMoP6PDLPBFmg7+xRKeFZvFboMrGlxmNj9ClvX53KrmvM5bXFXEWjbz4cz1AFn+jWJ9z/DJSz7hrs0w3w==", + "dev": true, + "requires": { + "p-defer": "^1.0.0" + } + }, + "mem": { + "version": "4.3.0", + "resolved": "https://registry.npmjs.org/mem/-/mem-4.3.0.tgz", + "integrity": "sha512-qX2bG48pTqYRVmDB37rn/6PT7LcR8T7oAX3bf99u1Tt1nzxYfxkgqDwUwolPlXweM0XzBOBFzSx4kfp7KP1s/w==", + "dev": true, + "requires": { + "map-age-cleaner": "^0.1.1", + "mimic-fn": "^2.0.0", + "p-is-promise": "^2.0.0" + } + }, "mime": { "version": "2.4.4", "resolved": "https://registry.npmjs.org/mime/-/mime-2.4.4.tgz", "integrity": "sha512-LRxmNwziLPT828z+4YkNzloCFC2YM4wrB99k+AV5ZbEyfGNWfG8SO1FUXLmLDBSo89NrJZ4DIWeLjy1CHGhMGA==" }, + "mimic-fn": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/mimic-fn/-/mimic-fn-2.1.0.tgz", + "integrity": "sha512-OqbOk5oEQeAZ8WXWydlu9HJjz9WVdEIvamMCcXmuqUYjTknH/sqsWvhQ3vgwKFRR1HpjvNBKQ37nbJgYzGqGcg==", + "dev": true + }, "mimic-response": { "version": "1.0.1", "resolved": "https://registry.npmjs.org/mimic-response/-/mimic-response-1.0.1.tgz", @@ -468,27 +854,108 @@ }, "minimist": { "version": "0.0.8", - "resolved": "https://registry.npmjs.org/minimist/-/minimist-0.0.8.tgz", + "resolved": "http://registry.npmjs.org/minimist/-/minimist-0.0.8.tgz", "integrity": "sha1-hX/Kv8M5fSYluCKCYuhqp6ARsF0=" }, "mkdirp": { "version": "0.5.1", - "resolved": "https://registry.npmjs.org/mkdirp/-/mkdirp-0.5.1.tgz", + "resolved": "http://registry.npmjs.org/mkdirp/-/mkdirp-0.5.1.tgz", "integrity": "sha1-MAV0OOrGz3+MR2fzhkjWaX11yQM=", "requires": { "minimist": "0.0.8" } }, + "mocha": { + "version": "6.1.4", + "resolved": "https://registry.npmjs.org/mocha/-/mocha-6.1.4.tgz", + "integrity": "sha512-PN8CIy4RXsIoxoFJzS4QNnCH4psUCPWc4/rPrst/ecSJJbLBkubMiyGCP2Kj/9YnWbotFqAoeXyXMucj7gwCFg==", + "dev": true, + "requires": { + "ansi-colors": "3.2.3", + "browser-stdout": "1.3.1", + "debug": "3.2.6", + "diff": "3.5.0", + "escape-string-regexp": "1.0.5", + "find-up": "3.0.0", + "glob": "7.1.3", + "growl": "1.10.5", + "he": "1.2.0", + "js-yaml": "3.13.1", + "log-symbols": "2.2.0", + "minimatch": "3.0.4", + "mkdirp": "0.5.1", + "ms": "2.1.1", + "node-environment-flags": "1.0.5", + "object.assign": "4.1.0", + "strip-json-comments": "2.0.1", + "supports-color": "6.0.0", + "which": "1.3.1", + "wide-align": "1.1.3", + "yargs": "13.2.2", + "yargs-parser": "13.0.0", + "yargs-unparser": "1.5.0" + }, + "dependencies": { + "debug": { + "version": "3.2.6", + "resolved": "https://registry.npmjs.org/debug/-/debug-3.2.6.tgz", + "integrity": "sha512-mel+jf7nrtEl5Pn1Qx46zARXKDpBbvzezse7p7LqINmdoIk8PYP5SySaxEmYv6TZ0JyEKA1hsCId6DIhgITtWQ==", + "dev": true, + "requires": { + "ms": "^2.1.1" + } + }, + "glob": { + "version": "7.1.3", + "resolved": "https://registry.npmjs.org/glob/-/glob-7.1.3.tgz", + "integrity": "sha512-vcfuiIxogLV4DlGBHIUOwI0IbrJ8HWPc4MU7HzviGeNho/UJDfi6B5p3sHeWIQ0KGIU0Jpxi5ZHxemQfLkkAwQ==", + "dev": true, + "requires": { + "fs.realpath": "^1.0.0", + "inflight": "^1.0.4", + "inherits": "2", + "minimatch": "^3.0.4", + "once": "^1.3.0", + "path-is-absolute": "^1.0.0" + } + } + } + }, "ms": { "version": "2.1.1", "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.1.tgz", "integrity": "sha512-tgp+dl5cGk28utYktBsrFqA7HKgrhgPsg6Z/EfhWI4gl1Hwq8B/GmY/0oXZ6nF8hDVesS/FpnYaD/kOWhYQvyg==" }, + "nice-try": { + "version": "1.0.5", + "resolved": "https://registry.npmjs.org/nice-try/-/nice-try-1.0.5.tgz", + "integrity": "sha512-1nh45deeb5olNY7eX82BkPO7SSxR5SSYJiPTrTdFUVYwAl8CKMA5N9PjTYkHiRjisVcxcQ1HXdLhx2qxxJzLNQ==", + "dev": true + }, + "node-environment-flags": { + "version": "1.0.5", + "resolved": "https://registry.npmjs.org/node-environment-flags/-/node-environment-flags-1.0.5.tgz", + "integrity": "sha512-VNYPRfGfmZLx0Ye20jWzHUjyTW/c+6Wq+iLhDzUI4XmhrDd9l/FozXV3F2xOaXjvp0co0+v1YSR3CMP6g+VvLQ==", + "dev": true, + "requires": { + "object.getownpropertydescriptors": "^2.0.3", + "semver": "^5.7.0" + } + }, "normalize-url": { "version": "3.3.0", "resolved": "https://registry.npmjs.org/normalize-url/-/normalize-url-3.3.0.tgz", "integrity": "sha512-U+JJi7duF1o+u2pynbp2zXDW2/PADgC30f0GsHZtRh+HOcXHnw137TrNlyxxRvWW5fjKd3bcLHPxofWuCjaeZg==" }, + "npm-run-path": { + "version": "2.0.2", + "resolved": "https://registry.npmjs.org/npm-run-path/-/npm-run-path-2.0.2.tgz", + "integrity": "sha1-NakjLfo11wZ7TLLd8jV7GHFTbF8=", + "dev": true, + "requires": { + "path-key": "^2.0.0" + } + }, "nth-check": { "version": "1.0.2", "resolved": "https://registry.npmjs.org/nth-check/-/nth-check-1.0.2.tgz", @@ -497,6 +964,40 @@ "boolbase": "~1.0.0" } }, + "number-is-nan": { + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/number-is-nan/-/number-is-nan-1.0.1.tgz", + "integrity": "sha1-CXtgK1NCKlIsGvuHkDGDNpQaAR0=", + "dev": true + }, + "object-keys": { + "version": "1.1.1", + "resolved": "https://registry.npmjs.org/object-keys/-/object-keys-1.1.1.tgz", + "integrity": "sha512-NuAESUOUMrlIXOfHKzD6bpPu3tYt3xvjNdRIQ+FeT0lNb4K8WR70CaDxhuNguS2XG+GjkyMwOzsN5ZktImfhLA==", + "dev": true + }, + "object.assign": { + "version": "4.1.0", + "resolved": "https://registry.npmjs.org/object.assign/-/object.assign-4.1.0.tgz", + "integrity": "sha512-exHJeq6kBKj58mqGyTQ9DFvrZC/eR6OwxzoM9YRoGBqrXYonaFyGiFMuc9VZrXf7DarreEwMpurG3dd+CNyW5w==", + "dev": true, + "requires": { + "define-properties": "^1.1.2", + "function-bind": "^1.1.1", + "has-symbols": "^1.0.0", + "object-keys": "^1.0.11" + } + }, + "object.getownpropertydescriptors": { + "version": "2.0.3", + "resolved": "https://registry.npmjs.org/object.getownpropertydescriptors/-/object.getownpropertydescriptors-2.0.3.tgz", + "integrity": "sha1-h1jIRvW0B62rDyNuCYbxSwUcqhY=", + "dev": true, + "requires": { + "define-properties": "^1.1.2", + "es-abstract": "^1.5.1" + } + }, "once": { "version": "1.4.0", "resolved": "https://registry.npmjs.org/once/-/once-1.4.0.tgz", @@ -505,11 +1006,64 @@ "wrappy": "1" } }, + "os-locale": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/os-locale/-/os-locale-3.1.0.tgz", + "integrity": "sha512-Z8l3R4wYWM40/52Z+S265okfFj8Kt2cC2MKY+xNi3kFs+XGI7WXu/I309QQQYbRW4ijiZ+yxs9pqEhJh0DqW3Q==", + "dev": true, + "requires": { + "execa": "^1.0.0", + "lcid": "^2.0.0", + "mem": "^4.0.0" + } + }, "p-cancelable": { "version": "1.0.0", "resolved": "https://registry.npmjs.org/p-cancelable/-/p-cancelable-1.0.0.tgz", "integrity": "sha512-USgPoaC6tkTGlS831CxsVdmZmyb8tR1D+hStI84MyckLOzfJlYQUweomrwE3D8T7u5u5GVuW064LT501wHTYYA==" }, + "p-defer": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/p-defer/-/p-defer-1.0.0.tgz", + "integrity": "sha1-n26xgvbJqozXQwBKfU+WsZaw+ww=", + "dev": true + }, + "p-finally": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/p-finally/-/p-finally-1.0.0.tgz", + "integrity": "sha1-P7z7FbiZpEEjs0ttzBi3JDNqLK4=", + "dev": true + }, + "p-is-promise": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/p-is-promise/-/p-is-promise-2.1.0.tgz", + "integrity": "sha512-Y3W0wlRPK8ZMRbNq97l4M5otioeA5lm1z7bkNkxCka8HSPjR0xRWmpCmc9utiaLP9Jb1eD8BgeIxTW4AIF45Pg==", + "dev": true + }, + "p-limit": { + "version": "2.2.0", + "resolved": "https://registry.npmjs.org/p-limit/-/p-limit-2.2.0.tgz", + "integrity": "sha512-pZbTJpoUsCzV48Mc9Nh51VbwO0X9cuPFE8gYwx9BTCt9SF8/b7Zljd2fVgOxhIF/HDTKgpVzs+GPhyKfjLLFRQ==", + "dev": true, + "requires": { + "p-try": "^2.0.0" + } + }, + "p-locate": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/p-locate/-/p-locate-3.0.0.tgz", + "integrity": "sha512-x+12w/To+4GFfgJhBEpiDcLozRJGegY+Ei7/z0tSLkMmxGZNybVMSfWj9aJn8Z5Fc7dBUNJOOVgPv2H7IwulSQ==", + "dev": true, + "requires": { + "p-limit": "^2.0.0" + } + }, + "p-try": { + "version": "2.2.0", + "resolved": "https://registry.npmjs.org/p-try/-/p-try-2.2.0.tgz", + "integrity": "sha512-R4nPAVTAU0B9D35/Gk3uJf/7XYbQcyohSKdvAxIRSNghFl4e71hVoGnBNQz9cWaXxO2I10KTC+3jMdvvoKw6dQ==", + "dev": true + }, "parse5": { "version": "3.0.3", "resolved": "https://registry.npmjs.org/parse5/-/parse5-3.0.3.tgz", @@ -518,15 +1072,28 @@ "@types/node": "*" } }, + "path-exists": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/path-exists/-/path-exists-3.0.0.tgz", + "integrity": "sha1-zg6+ql94yxiSXqfYENe1mwEP1RU=", + "dev": true + }, "path-is-absolute": { "version": "1.0.1", - "resolved": "https://registry.npmjs.org/path-is-absolute/-/path-is-absolute-1.0.1.tgz", + "resolved": "http://registry.npmjs.org/path-is-absolute/-/path-is-absolute-1.0.1.tgz", "integrity": "sha1-F0uSaHNVNP+8es5r9TpanhtcX18=" }, + "path-key": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/path-key/-/path-key-2.0.1.tgz", + "integrity": "sha1-QRyttXTFoUDTpLGRDUDYDMn0C0A=", + "dev": true + }, "pathval": { "version": "1.1.0", "resolved": "https://registry.npmjs.org/pathval/-/pathval-1.1.0.tgz", - "integrity": "sha1-uULm1L3mUwBe9rcTYd74cn0GReA=" + "integrity": "sha1-uULm1L3mUwBe9rcTYd74cn0GReA=", + "dev": true }, "pend": { "version": "1.2.0", @@ -635,6 +1202,18 @@ "util-deprecate": "^1.0.1" } }, + "require-directory": { + "version": "2.1.1", + "resolved": "https://registry.npmjs.org/require-directory/-/require-directory-2.1.1.tgz", + "integrity": "sha1-jGStX9MNqxyXbiNE/+f3kqam30I=", + "dev": true + }, + "require-main-filename": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/require-main-filename/-/require-main-filename-2.0.0.tgz", + "integrity": "sha512-NKN5kMDylKuldxYLSUfrbo5Tuzh4hd+2E8NPPX02mZtn1VuREQToYe/ZdlJy+J3uCpfaiGF05e7B8W0iXbQHmg==", + "dev": true + }, "responselike": { "version": "1.0.2", "resolved": "https://registry.npmjs.org/responselike/-/responselike-1.0.2.tgz", @@ -656,6 +1235,55 @@ "resolved": "https://registry.npmjs.org/safe-buffer/-/safe-buffer-5.1.2.tgz", "integrity": "sha512-Gd2UZBJDkXlY7GbJxfsE8/nvKkUEU1G38c1siN6QP6a9PT9MmHB8GnpscSmMJSoF8LOIrt8ud/wPtojys4G6+g==" }, + "semver": { + "version": "5.7.0", + "resolved": "https://registry.npmjs.org/semver/-/semver-5.7.0.tgz", + "integrity": "sha512-Ya52jSX2u7QKghxeoFGpLwCtGlt7j0oY9DYb5apt9nPlJ42ID+ulTXESnt/qAQcoSERyZ5sl3LDIOw0nAn/5DA==", + "dev": true + }, + "set-blocking": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/set-blocking/-/set-blocking-2.0.0.tgz", + "integrity": "sha1-BF+XgtARrppoA93TgrJDkrPYkPc=", + "dev": true + }, + "shebang-command": { + "version": "1.2.0", + "resolved": "https://registry.npmjs.org/shebang-command/-/shebang-command-1.2.0.tgz", + "integrity": "sha1-RKrGW2lbAzmJaMOfNj/uXer98eo=", + "dev": true, + "requires": { + "shebang-regex": "^1.0.0" + } + }, + "shebang-regex": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/shebang-regex/-/shebang-regex-1.0.0.tgz", + "integrity": "sha1-2kL0l0DAtC2yypcoVxyxkMmO/qM=", + "dev": true + }, + "signal-exit": { + "version": "3.0.2", + "resolved": "https://registry.npmjs.org/signal-exit/-/signal-exit-3.0.2.tgz", + "integrity": "sha1-tf3AjxKH6hF4Yo5BXiUTK3NkbG0=", + "dev": true + }, + "sprintf-js": { + "version": "1.0.3", + "resolved": "https://registry.npmjs.org/sprintf-js/-/sprintf-js-1.0.3.tgz", + "integrity": "sha1-BOaSb2YolTVPPdAVIDYzuFcpfiw=", + "dev": true + }, + "string-width": { + "version": "2.1.1", + "resolved": "https://registry.npmjs.org/string-width/-/string-width-2.1.1.tgz", + "integrity": "sha512-nOqH59deCq9SRHlxq1Aw85Jnt4w6KvLKqWVik6oA9ZklXLNIOlqg4F2yrT1MVaTjAqvVwdfeZ7w7aCvJD7ugkw==", + "dev": true, + "requires": { + "is-fullwidth-code-point": "^2.0.0", + "strip-ansi": "^4.0.0" + } + }, "string_decoder": { "version": "1.2.0", "resolved": "https://registry.npmjs.org/string_decoder/-/string_decoder-1.2.0.tgz", @@ -664,6 +1292,36 @@ "safe-buffer": "~5.1.0" } }, + "strip-ansi": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-4.0.0.tgz", + "integrity": "sha1-qEeQIusaw2iocTibY1JixQXuNo8=", + "dev": true, + "requires": { + "ansi-regex": "^3.0.0" + } + }, + "strip-eof": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/strip-eof/-/strip-eof-1.0.0.tgz", + "integrity": "sha1-u0P/VZim6wXYm1n80SnJgzE2Br8=", + "dev": true + }, + "strip-json-comments": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/strip-json-comments/-/strip-json-comments-2.0.1.tgz", + "integrity": "sha1-PFMZQukIwml8DsNEhYwobHygpgo=", + "dev": true + }, + "supports-color": { + "version": "6.0.0", + "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-6.0.0.tgz", + "integrity": "sha512-on9Kwidc1IUQo+bQdhi8+Tijpo0e1SS6RoGo2guUwn5vdaxw8RXOF9Vb2ws+ihWOmh4JnCJOvaziZWP1VABaLg==", + "dev": true, + "requires": { + "has-flag": "^3.0.0" + } + }, "to-readable-stream": { "version": "1.0.0", "resolved": "https://registry.npmjs.org/to-readable-stream/-/to-readable-stream-1.0.0.tgz", @@ -672,7 +1330,8 @@ "type-detect": { "version": "4.0.8", "resolved": "https://registry.npmjs.org/type-detect/-/type-detect-4.0.8.tgz", - "integrity": "sha512-0fr/mIH1dlO+x7TlcMy+bIDqKPsw/70tVyeHW787goQjhmqaZe10uwLujubK9q9Lg6Fiho1KUKDYz0Z7k7g5/g==" + "integrity": "sha512-0fr/mIH1dlO+x7TlcMy+bIDqKPsw/70tVyeHW787goQjhmqaZe10uwLujubK9q9Lg6Fiho1KUKDYz0Z7k7g5/g==", + "dev": true }, "typedarray": { "version": "0.0.6", @@ -697,6 +1356,77 @@ "resolved": "https://registry.npmjs.org/util-deprecate/-/util-deprecate-1.0.2.tgz", "integrity": "sha1-RQ1Nyfpw3nMnYvvS1KKJgUGaDM8=" }, + "which": { + "version": "1.3.1", + "resolved": "https://registry.npmjs.org/which/-/which-1.3.1.tgz", + "integrity": "sha512-HxJdYWq1MTIQbJ3nw0cqssHoTNU267KlrDuGZ1WYlxDStUtKUhOaJmh112/TZmHxxUfuJqPXSOm7tDyas0OSIQ==", + "dev": true, + "requires": { + "isexe": "^2.0.0" + } + }, + "which-module": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/which-module/-/which-module-2.0.0.tgz", + "integrity": "sha1-2e8H3Od7mQK4o6j6SzHD4/fm6Ho=", + "dev": true + }, + "wide-align": { + "version": "1.1.3", + "resolved": "https://registry.npmjs.org/wide-align/-/wide-align-1.1.3.tgz", + "integrity": "sha512-QGkOQc8XL6Bt5PwnsExKBPuMKBxnGxWWW3fU55Xt4feHozMUhdUMaBCk290qpm/wG5u/RSKzwdAC4i51YigihA==", + "dev": true, + "requires": { + "string-width": "^1.0.2 || 2" + } + }, + "wrap-ansi": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-2.1.0.tgz", + "integrity": "sha1-2Pw9KE3QV5T+hJc8rs3Rz4JP3YU=", + "dev": true, + "requires": { + "string-width": "^1.0.1", + "strip-ansi": "^3.0.1" + }, + "dependencies": { + "ansi-regex": { + "version": "2.1.1", + "resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-2.1.1.tgz", + "integrity": "sha1-w7M6te42DYbg5ijwRorn7yfWVN8=", + "dev": true + }, + "is-fullwidth-code-point": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/is-fullwidth-code-point/-/is-fullwidth-code-point-1.0.0.tgz", + "integrity": "sha1-754xOG8DGn8NZDr4L95QxFfvAMs=", + "dev": true, + "requires": { + "number-is-nan": "^1.0.0" + } + }, + "string-width": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/string-width/-/string-width-1.0.2.tgz", + "integrity": "sha1-EYvfW4zcUaKn5w0hHgfisLmxB9M=", + "dev": true, + "requires": { + "code-point-at": "^1.0.0", + "is-fullwidth-code-point": "^1.0.0", + "strip-ansi": "^3.0.0" + } + }, + "strip-ansi": { + "version": "3.0.1", + "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-3.0.1.tgz", + "integrity": "sha1-ajhfuIU9lS1f8F0Oiq+UJ43GPc8=", + "dev": true, + "requires": { + "ansi-regex": "^2.0.0" + } + } + } + }, "wrappy": { "version": "1.0.2", "resolved": "https://registry.npmjs.org/wrappy/-/wrappy-1.0.2.tgz", @@ -710,6 +1440,124 @@ "async-limiter": "~1.0.0" } }, + "y18n": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/y18n/-/y18n-4.0.0.tgz", + "integrity": "sha512-r9S/ZyXu/Xu9q1tYlpsLIsa3EeLXXk0VwlxqTcFRfg9EhMW+17kbt9G0NrgCmhGb5vT2hyhJZLfDGx+7+5Uj/w==", + "dev": true + }, + "yargs": { + "version": "13.2.2", + "resolved": "https://registry.npmjs.org/yargs/-/yargs-13.2.2.tgz", + "integrity": "sha512-WyEoxgyTD3w5XRpAQNYUB9ycVH/PQrToaTXdYXRdOXvEy1l19br+VJsc0vcO8PTGg5ro/l/GY7F/JMEBmI0BxA==", + "dev": true, + "requires": { + "cliui": "^4.0.0", + "find-up": "^3.0.0", + "get-caller-file": "^2.0.1", + "os-locale": "^3.1.0", + "require-directory": "^2.1.1", + "require-main-filename": "^2.0.0", + "set-blocking": "^2.0.0", + "string-width": "^3.0.0", + "which-module": "^2.0.0", + "y18n": "^4.0.0", + "yargs-parser": "^13.0.0" + }, + "dependencies": { + "ansi-regex": { + "version": "4.1.0", + "resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-4.1.0.tgz", + "integrity": "sha512-1apePfXM1UOSqw0o9IiFAovVz9M5S1Dg+4TrDwfMewQ6p/rmMueb7tWZjQ1rx4Loy1ArBggoqGpfqqdI4rondg==", + "dev": true + }, + "string-width": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/string-width/-/string-width-3.1.0.tgz", + "integrity": "sha512-vafcv6KjVZKSgz06oM/H6GDBrAtz8vdhQakGjFIvNrHA6y3HCF1CInLy+QLq8dTJPQ1b+KDUqDFctkdRW44e1w==", + "dev": true, + "requires": { + "emoji-regex": "^7.0.1", + "is-fullwidth-code-point": "^2.0.0", + "strip-ansi": "^5.1.0" + } + }, + "strip-ansi": { + "version": "5.2.0", + "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-5.2.0.tgz", + "integrity": "sha512-DuRs1gKbBqsMKIZlrffwlug8MHkcnpjs5VPmL1PAh+mA30U0DTotfDZ0d2UUsXpPmPmMMJ6W773MaA3J+lbiWA==", + "dev": true, + "requires": { + "ansi-regex": "^4.1.0" + } + } + } + }, + "yargs-parser": { + "version": "13.0.0", + "resolved": "https://registry.npmjs.org/yargs-parser/-/yargs-parser-13.0.0.tgz", + "integrity": "sha512-w2LXjoL8oRdRQN+hOyppuXs+V/fVAYtpcrRxZuF7Kt/Oc+Jr2uAcVntaUTNT6w5ihoWfFDpNY8CPx1QskxZ/pw==", + "dev": true, + "requires": { + "camelcase": "^5.0.0", + "decamelize": "^1.2.0" + } + }, + "yargs-unparser": { + "version": "1.5.0", + "resolved": "https://registry.npmjs.org/yargs-unparser/-/yargs-unparser-1.5.0.tgz", + "integrity": "sha512-HK25qidFTCVuj/D1VfNiEndpLIeJN78aqgR23nL3y4N0U/91cOAzqfHlF8n2BvoNDcZmJKin3ddNSvOxSr8flw==", + "dev": true, + "requires": { + "flat": "^4.1.0", + "lodash": "^4.17.11", + "yargs": "^12.0.5" + }, + "dependencies": { + "get-caller-file": { + "version": "1.0.3", + "resolved": "https://registry.npmjs.org/get-caller-file/-/get-caller-file-1.0.3.tgz", + "integrity": "sha512-3t6rVToeoZfYSGd8YoLFR2DJkiQrIiUrGcjvFX2mDw3bn6k2OtwHN0TNCLbBO+w8qTvimhDkv+LSscbJY1vE6w==", + "dev": true + }, + "require-main-filename": { + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/require-main-filename/-/require-main-filename-1.0.1.tgz", + "integrity": "sha1-l/cXtp1IeE9fUmpsWqj/3aBVpNE=", + "dev": true + }, + "yargs": { + "version": "12.0.5", + "resolved": "https://registry.npmjs.org/yargs/-/yargs-12.0.5.tgz", + "integrity": "sha512-Lhz8TLaYnxq/2ObqHDql8dX8CJi97oHxrjUcYtzKbbykPtVW9WB+poxI+NM2UIzsMgNCZTIf0AQwsjK5yMAqZw==", + "dev": true, + "requires": { + "cliui": "^4.0.0", + "decamelize": "^1.2.0", + "find-up": "^3.0.0", + "get-caller-file": "^1.0.1", + "os-locale": "^3.0.0", + "require-directory": "^2.1.1", + "require-main-filename": "^1.0.1", + "set-blocking": "^2.0.0", + "string-width": "^2.0.0", + "which-module": "^2.0.0", + "y18n": "^3.2.1 || ^4.0.0", + "yargs-parser": "^11.1.1" + } + }, + "yargs-parser": { + "version": "11.1.1", + "resolved": "https://registry.npmjs.org/yargs-parser/-/yargs-parser-11.1.1.tgz", + "integrity": "sha512-C6kB/WJDiaxONLJQnF8ccx9SEeoTTLek8RVbaOIsrAUS8VrBEXfmeSnCZxygc+XC2sNMBIwOOnfcxiynjHsVSQ==", + "dev": true, + "requires": { + "camelcase": "^5.0.0", + "decamelize": "^1.2.0" + } + } + } + }, "yauzl": { "version": "2.4.1", "resolved": "https://registry.npmjs.org/yauzl/-/yauzl-2.4.1.tgz", diff --git a/package.json b/package.json index 2a6ab92..396ace1 100644 --- a/package.json +++ b/package.json @@ -21,12 +21,16 @@ }, "license": "ISC", "dependencies": { - "chai": "^4.2.0", "cheerio": "^1.0.0-rc.2", "debug": "^4.1.1", "got": "^9.6.0", "proxy-chain": "^0.2.7", "puppeteer": "^1.17.0", "puppeteer-cluster": "^0.13.0" + }, + "devDependencies": { + "chai": "^4.2.0", + "chai-string": "^1.5.0", + "mocha": "^6.1.4" } } diff --git a/src/modules/se_scraper.js b/src/modules/se_scraper.js index dc3cf82..940aeb6 100644 --- a/src/modules/se_scraper.js +++ b/src/modules/se_scraper.js @@ -70,15 +70,10 @@ module.exports = class Scraper { await this.scraping_loop(); - let response = this.results; - if (this.config.html_output) { - response = { - 'results': this.results, - 'html_output': this.html_output - }; - } - - return response; + return { + 'results': this.results, + 'html_output': this.html_output, + }; } /** @@ -199,7 +194,11 @@ module.exports = class Scraper { } let html = await this.page.content(); - this.html_output[keyword][page_num] = html; + + if (this.config.html_output) { + this.html_output[keyword][page_num] = html; + } + let parsed = this.parse(html); this.results[keyword][page_num] = parsed ? parsed : await this.parse_async(html); diff --git a/src/node_scraper.js b/src/node_scraper.js index d2156e9..02157b5 100644 --- a/src/node_scraper.js +++ b/src/node_scraper.js @@ -325,6 +325,7 @@ class ScrapeManager { Object.assign(this.config, scrape_config); var results = {}; + var html_output = {}; var num_requests = 0; var metadata = {}; @@ -389,11 +390,13 @@ class ScrapeManager { scraperInstances.push(obj); } - let resolved = await Promise.all(execPromises); + let promiseReturns = await Promise.all(execPromises); - for (var group of resolved) { - for (var key in group) { - results[key] = group[key]; + // Merge results per keyword + for (let promiseReturn of promiseReturns) { + for (let keyword of this.config.keywords) { + results[keyword] = promiseReturn.results[keyword]; + html_output[keyword] = promiseReturn.html_output[keyword]; } } @@ -446,6 +449,7 @@ class ScrapeManager { return { results: results, + html_output: (this.config.html_output) ? html_output : undefined, metadata: metadata || {}, }; } @@ -496,4 +500,4 @@ function parseEventData(config) { module.exports = { ScrapeManager: ScrapeManager, -}; \ No newline at end of file +}; diff --git a/test/test_google.js b/test/test_google.js index 6c6e371..5748b37 100644 --- a/test/test_google.js +++ b/test/test_google.js @@ -1,5 +1,7 @@ const se_scraper = require('./../index.js'); -var assert = require('chai').assert; +const chai = require('chai'); +chai.use(require('chai-string')); +const assert = chai.assert; /* * Use chai and mocha for tests. @@ -184,8 +186,46 @@ function test_case_effective_query(response) { } } -(async () => { - await normal_search_test(); - await no_results_test(); - await effective_query_test(); -})(); +async function html_output_query_test() { + let config = { + compress: false, + debug_level: 1, + keyword_file: '', + headless: true, + output_file: '', + block_assets: true, + 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', + random_user_agent: false, + }; + + let scrape_config = { + search_engine: 'google', + keywords: normal_search_keywords, + num_pages: 3, + html_output: true, + }; + + let output = await se_scraper.scrape(config, scrape_config); + normal_search_test_case( output ); + check_html_output_test_case( output ); +} + +function check_html_output_test_case( response ) { + for (let query in response.html_output) { + + assert.containsAllKeys(response.html_output, normal_search_keywords, 'not all keywords were scraped.'); + + for (let page_number in response.html_output[query]) { + assert.isNumber(parseInt(page_number), 'page_number must be numeric'); + assert.startsWith(response.html_output[query][page_number], '