Download Flickr Public Photos/Videso

flickrdownload.py

#!/usr/bin/python3
import flickr_api
import os
import sys
import urllib
import threading
from six import text_type, iteritems, with_metaclass

flickr_api.set_keys(api_key = 'coolapikey', api_secret = 'secretsthebest')

def fetch_flickr_user(username):
    try:
        user = flickr_api.Person.findByUserName(username)
        print(f"Fetched user {user.username} {user.realname} {user.id} {user.photosurl}")
        return user
    except:
        print("User not found")
        return None
    return user



def getLargestSizeVideo(photo):
        """
            returns the largest size for the current photo.
        """
        sizes = {k:v for k,v in photo.getSizes().items() if v["media"] == photo.media}
        max_size = None
        max_area = None
        for sl, s in iteritems(sizes):
            if(s["height"] == None or s["width"] == None or sl == "Video Player"):
                continue
            area = int(s["height"]) * int(s["width"])
            if max_area is None or area > max_area:
                max_size = sl
                max_area = area
        
        if (max_size == None):
            if(700 in sizes.keys()):
                return 700
            else:
                return list(sizes.keys())[-1]
        return max_size

def download_photo(photo,path,thisCount):
    
    try:
        if(photo.media == "video"):
            size_label = getLargestSizeVideo(photo)
        else:
            size_label = photo._getLargestSizeLabel() #largest size
        photo_file = photo.getPhotoFile(size_label)
        file_ext = '.' + photo_file.split('.')[-1]
        if(photo.media == "video"):
            filename = os.path.join(path,str(thisCount) + "_" + photo.title+"_")
            file_ext = 'flv'
        else:
            filename = os.path.join(path,str(thisCount) + "_" + photo.title.replace(" ","_")+"-"+size_label.replace(" ","_")+file_ext)
        if(os.path.isfile(filename)):
            print(f"\t [!] File {filename} already exists, Skipping Download")
            return
        #print(f"\t[-] Downloading image {filename}")
        r = urllib.request.urlopen(photo_file)
        with open(filename, 'wb') as f:
            f.write(r.read())
            f.close()
        metaInfo = filename + ".txt"
        #print(f"\t[-] Saving metadata (descrip,exif,details) to {metaInfo}")
        with open(metaInfo, "w") as text_file:
            text_file.write(f"\nINFO {photo.title}\n")
            text_file.write("*"*50)
            
            exif = "".join([f"{e['tag']}: {e['raw']}\n" for e in photo.getExif()])
            text_file.write(f"\nEXIF\n")
            text_file.write("*"*50 + "\n")
            text_file.write(str(exif))
            details = photo.getInfo()
            text_file.write(f"\nDETAILS\n")
            text_file.write("*"*50 + "\n")
            text_file.write(str(details))
        print(f"[+] Downloaded Photo {photo.title} count: {thisCount}\n\t[-] Image: {filename}\n\t[-] Metadata: {metaInfo}")
        return True
    except Exception as e:
        print(f"Error Trying to get {photo}:  {e}")
        #sys.exit(1)
        

def fetch_all_public_photos(user,page=1,totalcount=0,path="."):
    
    photos = user.getPublicPhotos(per_page=50,page=page)
    if(page == 1):
        print(f"Found {photos.info.total} photos over {photos.info.pages} pages of {photos.info.perpage} per page.. starting threads for each download")
        print("-"*50)
    else:
        print("-"*50)
        print(f"Starting Page {page} of {photos.info.pages} ({totalcount} photos downloaded of {photos.info.total} ({round(totalcount / photos.info.total,2) * 100}%))")
        print("-"*50)
    threads=[]
    for photo in photos:
        totalcount += 1
        t = threading.Thread(target=download_photo, args=(photo,path,totalcount))
        t.start()
        threads.append(t)

    for t in threads:
        t.join()
        
    if (photos.info.pages > page):
        fetch_all_public_photos(user,page+1,totalcount,path)
    
    return photos

if __name__ == '__main__':
    if(len(sys.argv) < 2):
        print("Usage: flickrdownload.py <username> <path>")
        sys.exit(1)
    username = sys.argv[1]
    path = "."
    if(len(sys.argv) > 2):
        path = sys.argv[2]
    print(f"Fetching Username {username} and saving to {path}...")
    user = fetch_flickr_user(username)
    if(user):
        print(f"Fetching All Public Photos for {username}")
        fetch_all_public_photos(user,path=path, page=1)