Merge branch 'help'

README.md

@@ -8,7 +8,7 @@ This **command line** script complements other command line tools like ack, grep
 
 ## Download and install
 
-### Install the last version
+### Install the lastest version
 
 Go to the [releases page](https://github.com/greenpeace/check-my-pages/releases) and download the last version for your operating system: Windows, Mac and Linux 64bit.
 
@@ -22,6 +22,20 @@ go get github.com/greenpeace/check-my-pages
 go install github.com/greenpeace/check-my-pages
 ```
 
+### Get help
+
+If you downloaded and installed the latest version from the [releases page](https://github.com/greenpeace/check-my-pages/releases) do:
+
+```
+ ./check-my-pages --help
+```
+
+If you installed from source do:
+
+```
+ check-my-pages --help
+```
+
 ## File with list of urls
 
 The urls file, by default `urls.csv` must have all the urls you want to check. You can use a text file with 1 url per line or a csv file with the urls on the first column and without headers.

check-my-pages.go

@@ -13,6 +13,7 @@ import (
 
 func main() {
 
+	isHelp := flag.Bool("help", false, "Help")
 	urlsFileName := flag.String("urls", "urls.csv", "Name of the csv file with the urs in the first column")
 	isHTTP := flag.Bool("http", false, "Http response codes")
 	isRedirects := flag.Bool("redirects", false, "Redirects response codes")
@@ -36,6 +37,11 @@ func main() {
 	c := colly.NewCollector()
 	// c.AllowedDomains = []string{"localhost", "greenpeace.es", "archivo.greenpeace.es"}
 
+	if *isHelp == true {
+		help()
+		os.Exit(0)
+	}
+
 	if *isHTTP == true {
 
 		httpResponses, httpErr := os.OpenFile("httpResponses.csv", os.O_CREATE|os.O_APPEND|os.O_WRONLY, 0600)

help.go

@@ -0,0 +1,70 @@
+package main
+
+import (
+	"fmt"
+)
+
+func help() {
+	fmt.Println(`
+
+-------------------
+CHECK-MY-PAGES HELP
+-------------------
+
+check-my-pages is a scrapping script. It checks each url in a list and creates report files about what was tested. Each file reports about a specific issue and includes the scanned url together with the result.
+
+
+EXAMPLES:
+
+./check-my-pages -urls=urls.csv -http -analytics -canonical -redirects -linkpattern -cssjspattern -mediapattern
+
+./check-my-pages -urls=urls.csv -fileinfo -miliseconds=100
+
+
+CHECKS:
+
+-http : Gets the http response code. If it's 200 it should be OK.
+
+-analytics : Gets the first Google Analytics account.
+
+-canonical : Gets the canonical URL for the url.
+
+-redirects : Gets info about redirects and final URLs.
+
+-linkpattern : Gets links that match the regular expression pattern.
+
+-cssjspattern : Gets CSS and JS URLs that match the regular expression pattern.
+
+-mediapattern : Gets urls from images, videos, audios, iframes and objects that match the regular expression pattern
+
+-fileinfo : Speciall check more suitable for non-html pages (for example images). It needs to be used alone as the example above, without other checks.
+
+
+OPTIONS:
+
+-urls=urls.csv : Sets the file with the urls to scan. Normally a text file with one URL per line or a csv without headers with the urls on the first column.
+
+-pattern='https?://(\w|-)+.greenpeace.org/espana/.+' : Changes the url search pattern to the regular expression. To be used with *pattern checks.
+
+-miliseconds=100 : Sets a delay of 100 miliseconds between requests.
+
+
+FILES WITH THE REPORTS:
+
+- httpResponses.csv : Stores the http response codes for the URL. 200 means everything is OK.
+
+- analytics.csv : Reports google analytics tracking ID.
+
+- canonicals.csv : Reports the canonical url for every url
+
+- redirects.csv : Reports the requested URL and the final URL. This will be useful to test the redirects in the main site.
+
+- linkpattern.csv : Reports on links that include a regular expression pattern. Useful to track links to specific dead sites. The default pattern can be set by the -pattern option.
+
+- cssjspattern.csv : Reports css and js urls that include a regular expression pattern. To detect dead css and js urls in large sites. The pattern can also be defined with the option -pattern (described bellow)
+
+- mediapattern.csv : Reports media links. Images, videos, audios, iframes and objects. Also use -pattern to define the urls pattern.
+
+	
+	`)
+}