Refactor NPM module

run

@@ -11,8 +11,6 @@ fi
 cmd="docker run --rm -v "$(pwd):/opt/wappalyzer" -it wappalyzer/dev"
 
 $cmd sh -c "\
-	yarn install; \
-	cd src/drivers/webextension; \
 	yarn install; \
 	cd ../npm; \
 	yarn install"

src/drivers/npm/cli.js

@@ -84,10 +84,6 @@ Options:
 
     const site = await wappalyzer.open(url)
 
-    site.on('error', (error) => {
-      process.stderr.write(`page error: ${error}\n`)
-    })
-
     const results = await site.analyze()
 
     process.stdout.write(
@@ -98,7 +94,8 @@ Options:
 
     process.exit(0)
   } catch (error) {
-    process.stderr.write(error.toString())
+    // eslint-disable-next-line no-console
+    console.error(error)
 
     await wappalyzer.destroy()
 

src/drivers/npm/driver.js

@@ -2,7 +2,13 @@ const { URL } = require('url')
 const fs = require('fs')
 const path = require('path')
 const LanguageDetect = require('languagedetect')
-const Wappalyzer = require('./wappalyzer')
+const {
+  setTechnologies,
+  setCategories,
+  analyze,
+  analyzeManyToMany,
+  resolve
+} = require('./wappalyzer')
 
 const { AWS_LAMBDA_FUNCTION_NAME, CHROMIUM_BIN } = process.env
 
@@ -30,8 +36,6 @@ const languageDetect = new LanguageDetect()
 
 languageDetect.setLanguageType('iso2')
 
-const json = JSON.parse(fs.readFileSync(path.resolve(`${__dirname}/apps.json`)))
-
 const extensions = /^([^.]+$|\.(asp|aspx|cgi|htm|html|jsp|php)$)/
 
 const errorTypes = {
@@ -40,6 +44,13 @@ const errorTypes = {
   NO_HTML_DOCUMENT: 'No HTML document'
 }
 
+const { apps: technologies, categories } = JSON.parse(
+  fs.readFileSync(path.resolve(`${__dirname}/apps.json`))
+)
+
+setTechnologies(technologies)
+setCategories(categories)
+
 function sleep(ms) {
   return new Promise((resolve) => setTimeout(resolve, ms))
 }
@@ -188,7 +199,7 @@ class Driver {
 
         await this.browser.close()
 
-        this.log('Done')
+        this.log('Browser closed')
       } catch (error) {
         throw new Error(error.toString())
       }
@@ -199,10 +210,10 @@ class Driver {
     return new Site(url, this)
   }
 
-  log(message, source = 'driver', type = 'debug') {
+  log(message, source = 'driver') {
     if (this.options.debug) {
       // eslint-disable-next-line no-console
-      console.log(`${type.toUpperCase()} | ${source} | ${message}`)
+      console.log(`wappalyzer | log | ${source} |`, message)
     }
   }
 }
@@ -219,21 +230,9 @@ class Site {
       throw new Error(error.message || error.toString())
     }
 
-    this.wappalyzer = new Wappalyzer()
-
-    this.wappalyzer.apps = json.apps
-    this.wappalyzer.categories = json.categories
-
-    this.wappalyzer.parseJsPatterns()
-
-    this.wappalyzer.driver.log = (message, source, type) =>
-      this.log(message, source, type)
-    this.wappalyzer.driver.displayApps = (detected, meta, context) =>
-      this.displayApps(detected, meta, context)
-
     this.analyzedUrls = {}
-    this.technologies = []
+    this.detections = []
-    this.meta = {}
+    this.language = ''
 
     this.listeners = {}
 
@@ -242,7 +241,18 @@ class Site {
     this.pages = []
   }
 
-  async init() {}
+  log(message, source = 'driver', type = 'log') {
+    if (this.options.debug) {
+      // eslint-disable-next-line no-console
+      console[type](`wappalyzer | ${type} | ${source} |`, message)
+    }
+
+    this.emit(type, { message, source })
+  }
+
+  error(error, source = 'driver') {
+    this.log(error, source, 'error')
+  }
 
   on(event, callback) {
     if (!this.listeners[event]) {
@@ -258,14 +268,6 @@ class Site {
     }
   }
 
-  log(...args) {
-    this.emit('log', ...args)
-
-    this.driver.log(...args)
-  }
-
-  async fetch(url, index, depth) {}
-
   async goto(url) {
     // Return when the URL is a duplicate or maxUrls has been reached
     if (
@@ -293,7 +295,7 @@ class Site {
 
     await page.setRequestInterception(true)
 
-    page.on('error', (error) => this.emit('error', error))
+    page.on('error', (error) => this.error(error))
 
     let responseReceived = false
 
@@ -309,7 +311,7 @@ class Site {
           request.continue()
         }
       } catch (error) {
-        this.emit('error', error)
+        this.error(error)
       }
     })
 
@@ -340,7 +342,7 @@ class Site {
           }
         }
       } catch (error) {
-        this.emit('error', error)
+        this.error(error)
       }
     })
 
@@ -356,7 +358,7 @@ class Site {
         )
       ])
     } catch (error) {
-      this.emit('error', error)
+      this.error(error)
     }
 
     await sleep(1000)
@@ -387,7 +389,8 @@ class Site {
       ).jsonValue()
     ).filter((script) => script)
 
-    const js = processJs(await page.evaluate(getJs), this.wappalyzer.jsPatterns)
+    // const js = processJs(await page.evaluate(getJs), this.wappalyzer.jsPatterns)
+    // TODO
 
     const cookies = (await page.cookies()).map(
       ({ name, value, domain, path }) => ({
@@ -413,29 +416,40 @@ class Site {
       throw new Error('NO_RESPONSE')
     }
 
-    let language = null
+    if (!this.language) {
+      this.language = await (
+        await page.evaluateHandle(
+          () =>
+            document.documentElement.getAttribute('lang') ||
+            document.documentElement.getAttribute('xml:lang')
+        )
+      ).jsonValue()
+    }
 
-    try {
+    if (!this.language) {
-      const [attrs] = languageDetect.detect(
+      try {
-        html.replace(/<\/?[^>]+(>|$)/g, ' '),
+        const [attrs] = languageDetect.detect(
-        1
+          html.replace(/<\/?[^>]+(>|$)/gs, ' '),
-      )
+          1
+        )
 
-      if (attrs) {
+        if (attrs) {
-        ;[language] = attrs
+          ;[this.language] = attrs
+        }
+      } catch (error) {
+        this.error(error)
       }
-    } catch (error) {
-      this.log(`${error} (${url.href})`, 'driver', 'error')
     }
 
-    await this.wappalyzer.analyze(url, {
+    await this.onDetect(
-      cookies,
+      url,
-      headers: this.headers,
+      await analyze(url, {
-      html,
+        cookies,
-      js,
+        headers: this.headers,
-      scripts,
+        html,
-      language
+        scripts
-    })
+      })
+    )
 
     const reducedLinks = Array.prototype.reduce.call(
       links,
@@ -496,13 +510,30 @@ class Site {
         }
       }
 
-      this.log(`${message} (${url.href})`, 'driver', 'error')
+      this.error(error)
     }
 
     return {
       urls: this.analyzedUrls,
-      applications: this.technologies,
+      applications: resolve(this.detections).map(
-      meta: this.meta
+        ({ name, confidence, version, icon, website, categories }) => ({
+          name,
+          confidence,
+          version,
+          icon,
+          website,
+          categories: categories.reduce(
+            (categories, { id, name }) => ({
+              ...categories,
+              [id]: name
+            }),
+            {}
+          )
+        })
+      ),
+      meta: {
+        language: this.language
+      }
     }
   }
 
@@ -520,34 +551,16 @@ class Site {
     await this.batch(links, depth, batch + 1)
   }
 
-  displayApps(technologies, meta) {
+  onDetect(url, detections = [], language) {
-    this.meta = meta
+    this.detections = this.detections.concat(detections)
-
-    Object.keys(technologies).forEach((name) => {
-      const {
-        confidenceTotal: confidence,
-        version,
-        props: { cats, icon, website, cpe }
-      } = technologies[name]
-
-      const categories = cats.reduce((categories, id) => {
-        categories[id] = json.categories[id].name
 
-        return categories
+    this.detections.filter(
-      }, {})
+      ({ technology: { name }, pattern: { regex } }, index) =>
-
+        this.detections.findIndex(
-      if (!this.technologies.some(({ name: _name }) => name === _name)) {
+          ({ technology: { name: _name }, pattern: { regex: _regex } }) =>
-        this.technologies.push({
+            name === _name && (!regex || regex.toString() === _regex.toString())
-          name,
+        ) === index
-          confidence,
+    )
-          version: version || null,
-          icon: icon || 'default.svg',
-          website,
-          cpe: cpe || null,
-          categories
-        })
-      }
-    })
   }
 
   async destroy() {
@@ -570,6 +583,3 @@ class Site {
 }
 
 module.exports = Driver
-
-module.exports.processJs = processJs
-module.exports.processHtml = processHtml

src/drivers/webextension/.gitignore

@@ -1,6 +1,5 @@
 /apps.json
 /images/icons/converted/*
 /js/wappalyzer.js
-/node_modules
 
 !.gitkeep

src/drivers/webextension/js/driver.js

@@ -80,10 +80,6 @@ const Driver = {
     console[type](`wappalyzer | ${source} |`, message)
   },
 
-  warn(message, source = 'driver') {
-    Driver.log(message, source, 'warn')
-  },
-
   error(error, source = 'driver') {
     Driver.log(error, source, 'error')
   },
@@ -230,7 +226,7 @@ const Driver = {
     })
 
     // Remove duplicates
-    cache.detections = cache.detections = cache.detections.concat(detections)
+    cache.detections = cache.detections.concat(detections)
 
     cache.detections.filter(
       ({ technology: { name }, pattern: { regex } }, index) =>

src/drivers/webextension/package.json

@@ -1,5 +0,0 @@
-{
-  "dependencies": {
-    "webextension-polyfill": "^0.4.0"
-  }
-}

src/drivers/webextension/yarn.lock

@@ -1,8 +0,0 @@
-# THIS IS AN AUTOGENERATED FILE. DO NOT EDIT THIS FILE DIRECTLY.
-# yarn lockfile v1
-
-
-webextension-polyfill@^0.4.0:
-  version "0.4.0"
-  resolved "https://registry.yarnpkg.com/webextension-polyfill/-/webextension-polyfill-0.4.0.tgz#9cc5a60f0f2bf907a6b349fdd7e61701f54956f9"
-  integrity sha512-oreMp+EoAo1pzRMigx4jB5jInIpx6NTCySPSjGyLLee/dCIPiRqowCEfbFP8o20wz9SOtNwSsfkaJ9D/tRgpag==