SearchBingImagesDownload.ps1
|
<#PSScriptInfo .VERSION 1.0.0 .GUID 06abc574-c34d-46a6-b30c-6eadc3931416 .AUTHOR mikko@lavento.com .COMPANYNAME .COPYRIGHT .TAGS Bing, imagesearch, download image, image, search .LICENSEURI .PROJECTURI .ICONURI .EXTERNALMODULEDEPENDENCIES .REQUIREDSCRIPTS .EXTERNALSCRIPTDEPENDENCIES .RELEASENOTES #> <# .DESCRIPTION Example how to download first image hit from Bing image search. This can be done without Azure APIs because it makes direct request mimicking browser request. #> Param() #19.7.2019 M.Lavento #Get first image from Bing based on Searchterm #Example search "LPS #7" --> https://www.bing.com/images/search?q=LPS%20%237 Add-Type -AssemblyName System.Web $SearchPlaintext = "LPS #1" #Convert searchstring to HTTP $SearchItem = [System.Web.HttpUtility]::UrlEncode($SearchPlaintext) #Foledr to store pics $TargetFolder = "C:\Skriptit\WebImageCrawler\Downloadedpics" if ( (Test-Path -Path $TargetFolder) -eq $false) { md $TargetFolder } Invoke-Item $TargetFolder #Bing is "simpler" $url = "https://www.bing.com/images/search?q=$SearchItem" $browserAgent = 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.146 Safari/537.36' $page = Invoke-WebRequest -Uri $url -UserAgent $browserAgent -UseBasicParsing #First picture resides in the link number 69 (Microsoft might change that over the time) $firsthit = $page.Links | select -Skip 68 -First 1 #pick rawurl. The link we are looking begins with mediaurl= $rawurl = $firsthit | ForEach-Object { ($_.href -split 'mediaurl=')[-1].Split('&')[0]} #convert to http, basically makes this: $fineurl = $rawurl -replace "%2f","/" -replace "%3a",":" $fineurl = [System.Web.HttpUtility]::UrlDecode($rawurl) #Check if there is too much on the end of URL (some of the results have tails) #For example http://vignette2.wikia.nocookie.net/littlestpetshoplps/images/b/b2/Littlest_Pet_Shop_-7.jpg/revision/latest?cb=20120124005013 $finalurl = ($fineurl -split '.jpg')[0]+".jpg" #Save file $file = Split-Path -Path $finalurl -Leaf $finalfile = $SearchPlaintext + "_" + $file #replace illegal chars if there is any [System.IO.Path]::GetInvalidFileNameChars() | foreach {$finalfile = $finalfile.replace($_,' ')} $path = Join-Path -Path $TargetFolder -ChildPath $finalfile #fetch the image Invoke-WebRequest -Uri $finalurl -OutFile $path |