Merge branch 'release/v0.4.0-alpha'

.github/workflows/go.yml

@@ -0,0 +1,26 @@
+name: Go
+
+on: [push]
+
+jobs:
+
+  build:
+    name: Build
+    runs-on: ubuntu-latest
+    steps:
+
+    - name: Set up Go 1.x
+      uses: actions/setup-go@v2
+      with:
+        go-version: ^1
+
+    - name: Check out code into the Go module directory
+      uses: actions/checkout@v2
+
+    - name: Build
+      run: |
+        go mod tidy
+        go build -v .
+
+    - name: Test
+      run: go test -v .

.gitignore

@@ -1 +1,3 @@
+.DS_Store
 /.idea
+/vendor

CHANGELOG.md

@@ -4,10 +4,19 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/)
 and this project adheres to [Semantic Versioning](http://semver.org/).
 
-## [Unreleased]
+## [v0.4.0-alpha] - 2020-11-05
+
+Logging
 
 ### Added
 - Add "Save downloaded data to disk" to the roadmap (feature request #1)
+- Log results to a log file
+- Add Github actions
+
+### Changed
+- Add support for non-sitemap URLs
+- Capture the parent URL
+- Switch from go 1.14 to 1.15
 
 ## [v0.2.0-alpha] - 2017-02-07
 

README.md

@@ -33,6 +33,30 @@ You can specify a customized user agent using the `--user-agent` argument:
 gargantua crawl --url https://www.sitemaps.org/sitemap.xml --workers 5 --user-agent "gargantua bot / iPhone"
 ```
 
+### Log all requests
+
+You can specify a log file with the `--log` argument:
+
+```bash
+gargantua crawl --url https://www.sitemaps.org/sitemap.xml --workers 5 --log "gargantua.log"
+```
+
+```
+Date and time       #worker   Status Code     Bytes   Response Time   URL                                                          Parent URL
+2020/11/05 09:23:14 #001:     200             4403    148.759000ms    https://www.sitemaps.org                                     https://www.sitemaps.org/ko/faq.html
+2020/11/05 09:23:14 #002:     200             4403    290.536000ms    http://www.sitemaps.org/                                     https://www.sitemaps.org/ko/faq.html
+2020/11/05 09:23:14 #003:     200            45077    283.243000ms    https://www.sitemaps.org/protocol.html                       https://www.sitemaps.org/ko/faq.html
+2020/11/05 09:23:14 #004:     404             1245    155.376000ms    https://www.sitemaps.org/protocol.htm                        https://www.sitemaps.org/ko/faq.html
+2020/11/05 09:23:14 #005:     200             4403    155.577000ms    https://www.sitemaps.org/index.html                          https://www.sitemaps.org/ko/faq.html
+2020/11/05 09:23:14 #001:     200             2591    286.451000ms    http://www.sitemaps.org/schemas/sitemap/0.9/siteindex.xsd    https://www.sitemaps.org/ko/faq.html
+2020/11/05 09:23:14 #003:     200            10839    143.738000ms    https://www.sitemaps.org/terms.html                          https://www.sitemaps.org/ko/faq.html
+2020/11/05 09:23:14 #005:     200            15681    141.580000ms    https://www.sitemaps.org/faq.html                            https://www.sitemaps.org/ko/protocol.html
+2020/11/05 09:23:14 #002:     404             1245    286.175000ms    http://www.sitemaps.org/protocol.htm                         https://www.sitemaps.org/ko/faq.html
+```
+
+[gargantua.log](files/gargantua.log)
+
+
 ## Download
 
 You can download binaries for Linux, macOS and Windows from [github.com »andreaskoch » gargantua » releases](https://github.com/andreaskoch/gargantua/releases):

crawler.go

@@ -1,14 +1,18 @@
 package main
 
 import (
+	"github.com/pkg/errors"
+	"log"
 	"net/url"
+	"os"
 	"time"
 )
 
 type CrawlOptions struct {
 	NumberOfConcurrentRequests int
 	Timeout                    time.Duration
 	UserAgent                  string
+	LogFile                    string
 }
 
 func crawl(xmlSitemapURL url.URL, options CrawlOptions, stop chan bool) error {
@@ -20,7 +24,7 @@ func crawl(xmlSitemapURL url.URL, options CrawlOptions, stop chan bool) error {
 	}
 
 	// the URL queue
-	urls := make(chan url.URL, len(urlsFromXMLSitemap))
+	urls := make(chan crawlerUrl, len(urlsFromXMLSitemap))
 
 	// fill the URL queue with the URLs from the XML sitemap
 	for _, xmlSitemapURLEntry := range urlsFromXMLSitemap {
@@ -37,7 +41,7 @@ func crawl(xmlSitemapURL url.URL, options CrawlOptions, stop chan bool) error {
 
 	allURLsHaveBeenVisited := make(chan bool)
 	go func() {
-		var visitedURLs = make(map[string]url.URL)
+		var visitedURLs = make(map[string]crawlerUrl)
 		for {
 			select {
 			case <-stop:
@@ -76,6 +80,17 @@ func crawl(xmlSitemapURL url.URL, options CrawlOptions, stop chan bool) error {
 		}
 	}()
 
+	var logger *log.Logger
+	if options.LogFile != "" {
+		file, err := os.OpenFile(options.LogFile, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0666)
+		if err != nil {
+			return errors.Wrapf(err, "failed to open log file %q for writing", options.LogFile)
+		}
+
+		defer file.Close()
+		logger = log.New(file, "", log.Ldate|log.Ltime)
+	}
+
 	// update the statistics with the results
 	allStatisticsHaveBeenUpdated := make(chan bool)
 	go func() {
@@ -89,6 +104,10 @@ func crawl(xmlSitemapURL url.URL, options CrawlOptions, stop chan bool) error {
 				receivedUrl := result.URL()
 				debugf("Received results for URL %q", receivedUrl.String())
 				updateStatistics(result)
+
+				if logger != nil {
+					logResult(logger, result)
+				}
 			}
 		}
 	}()