SearchYahooImagesDownload.ps1
|
<#PSScriptInfo .VERSION 1.0.0 .GUID cf1173f4-5876-4ca8-a348-20d2df75b55a .AUTHOR mikko@lavento.com .COMPANYNAME .COPYRIGHT .TAGS Yahoo, imagesearch, download image, image, search .LICENSEURI .PROJECTURI .ICONURI .EXTERNALMODULEDEPENDENCIES .REQUIREDSCRIPTS .EXTERNALSCRIPTDEPENDENCIES .RELEASENOTES #> <# .DESCRIPTION Example how to download first x number image hits from Yahoo image search. This can be done without Yahoo APIs because it makes direct request mimicking browser request. #> Param() #19.7.2019 M.Lavento #Get first x number of images from Yahoo image search based on Searchterm Add-Type -AssemblyName System.Web $SearchPlaintext = "LPS #7" #Convert searchstring to HTTP $SearchItem = [System.Web.HttpUtility]::UrlEncode($SearchPlaintext) $HowManyHits = "4" #Folder to store pics $TargetFolder = "C:\Skriptit\WebImageCrawler\Downloadedpics" if ( (Test-Path -Path $TargetFolder) -eq $false) { md $TargetFolder } Invoke-Item $TargetFolder $url = "https://images.search.yahoo.com/search/images;?p=$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 #Yahoo, have to read hits from rawcontent $jpgsplit = $page.RawContent -split "," | where {$_ -like "*.jpg*"} $jpgonlysplit = $jpgsplit | where {$_ -like "*iurl*"} #clean up the answer some more and get 10 first results $iurlsplit = $jpgonlysplit -split '":"' -replace '"', "" -replace "[\\]", ""| where {$_ -like "*.jpg*"} | select -First $HowManyHits #Loop and get the images foreach ($urlhit in $iurlsplit) { #Save file $file = Split-Path -Path $urlhit -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 $urlhit -OutFile $path -ErrorAction Continue } |