Simple script to download images and videos from a Imgur category

ImgurDownloader.py

import os
import re
import hashlib
import urllib.request

class ImgurDownloader:
    destinationFolder = 'D:\\imgur-downloads\\'
    pattern = re.compile('<img alt="" src="//([^"]+)"')
    
    def __init__(self, category):
        self.category = category
        if not os.path.exists(self.destinationFolder):
            os.makedirs(self.destinationFolder)

    def getCategoryLink(self):
        return "https://imgur.com/r/%s/top/month" %self.category

    def getResources(self):
        resource = urllib.request.urlopen(self.getCategoryLink())
        source = resource.read().decode(resource.headers.get_content_charset())
        matches = self.pattern.findall(source)
        return list(map(lambda link: "https://" + link.replace("b.jpg", ".jpg"), matches))

    def getDestination(self, imgurLink):
        return self.destinationFolder + hashlib.sha224(imgurLink.encode()).hexdigest() + ".jpg"

    def download(self):
        images = self.getResources()
        print("Found %i images" %len(images))
        for image in images:
            destination = self.getDestination(image)
            print(image + " --> " + destination)
            urllib.request.urlretrieve(image, destination)

class AdvancedImgurDownloader(ImgurDownloader):
    pagePattern = re.compile('image-list-link" href="(/r[^"]+)"')
    imagePattern = re.compile('<meta property="og:image"\s+content="([^"\?]+)')
    videoPattern = re.compile('<meta name="twitter:player:stream"\s+content="([^"]+)"')
    
    def __init__(self, category):
        self.category = category
        if not os.path.exists(self.destinationFolder):
            os.makedirs(self.destinationFolder)

    def getResources(self):
        resources = {}
        for pageLink in self.getPageLinks():
            resources[pageLink] = self.getResourceLink(pageLink)
            print('Found ' + str(resources[pageLink]))
        return resources

    def getPageLinks(self):
        resource = urllib.request.urlopen(self.getCategoryLink())
        source = resource.read().decode(resource.headers.get_content_charset())
        pagesRelative = self.pagePattern.findall(source)
        return list(map(lambda link: "https://imgur.com/" + link, pagesRelative))

    def getResourceLink(self, pageLink):
        resource = urllib.request.urlopen(pageLink)
        source = resource.read().decode(resource.headers.get_content_charset())
        videoMatch = self.videoPattern.findall(source)
        if (videoMatch):
            return {'url': videoMatch[0], 'isVideo': True}

        imageMatch = self.imagePattern.findall(source)
        if (imageMatch):
            return {'url': imageMatch[0], 'isVideo': False}

    def getDestination(self, resource):
        extension = ".mp4" if resource["isVideo"] else ".jpg"
        return self.destinationFolder + hashlib.sha224(resource["url"].encode()).hexdigest() + extension
    
    def download(self):
        resources = self.getResources()
        print("Found %i resources" %len(resources))
        for key in resources:
            resource = resources[key]
            destination = self.getDestination(resource)
            print(resource["url"] + " --> " + destination)
            urllib.request.urlretrieve(resource["url"], destination)
        
        

advancedDownloader = AdvancedImgurDownloader("cats")
advancedDownloader.download()


#downloader = ImgurDownloader("cats")
#print("About to download from " + downloader.getCategoryLink())
#downloader.download()