def puppyScraper(): #Downloads the images of puppies
done = False
while not done:
amount = input("How many images?: ")
try:
downloader.download("puppies",
limit=int(amount),
adult_filter_off=True,
force_replace=True)
done = True
except:
print("That isn't a number! Try again...")
done = False
def main():
message =("Downloads a bunch of images from bing " +
"based on a search query.")
parser = get_default_ArgumentParser(message)
parser.add_argument("--query", type=str, default="dragon",
help="The query that is used to get the images.")
parser.add_argument("destination", type=str,
help="The directory where the files should be placed.")
parser.add_argument("--limit", type=int, default=1000,
help="The number of images to get.")
FLAGS = parser.parse_args()
process_common_arguments(FLAGS)
downloader.download(FLAGS.query,
output_dir=FLAGS.destination,
limit=FLAGS.limit)
async def img_sampler(event):
if event.fwd_from:
return
if event.is_group:
if not (await is_register_admin(event.input_chat, event.message.sender_id)):
await event.reply("Sorry But You Are Not Fully Worthy To Use My Death Note Power Use This In My Pm If You Need")
return
query = event.pattern_match.group(1)
jit = f'"{query}"'
downloader.download(jit, limit=5, output_dir='store', adult_filter_off=True, force_replace=False, timeout=60)
os.chdir(f'./store/"{query}"')
types = ('*.png', '*.jpeg', '*.jpg') # the tuple of file types
filesgrabbed = []
for files in types:
filesgrabbed.extend(glob.glob(files))
await event.client.send_file(event.chat_id, filesgrabbed, reply_to=event.id)
os.remove(filesgrabbed)
os.chdir('./')
def downloadImges(query,
storePath='dataset/bing/',
imgType='image',
quantity=1,
size=(1600, 900)):
search = query + ' ' + imgType
try:
downloader.download(search,
limit=quantity,
adult_filter_off=True,
force_replace=False)
resize(search, size, storePath)
except FileNotFoundError:
downloader.download(query,
limit=quantity,
adult_filter_off=True,
force_replace=False)
resize(query, size, storePath)
def scrape_bing(self):
download_things = downloader.download(
self.config.search,
limit=self.config.limit,
output_dir=self.config.output_dir,
adult_filter_off=True,
force_replace=False,
timeout=60)
return download_things
async def img_sampler(event):
if event.fwd_from:
return
if event.is_group:
if not (await is_register_admin(event.input_chat, event.message.sender_id)):
await event.reply("😜 Hai.. You are not admin..🤠You can't use this command.. But you can use in my pm🙈")
return
query = event.pattern_match.group(1)
jit = f'"{query}"'
downloader.download(jit, limit=5, output_dir='store', adult_filter_off=False, force_replace=False, timeout=60)
os.chdir(f'./store/"{query}"')
types = ('*.png', '*.jpeg', '*.jpg') # the tuple of file types
files_grabbed = []
for files in types:
files_grabbed.extend(glob.glob(files))
await event.client.send_file(event.chat_id, files_grabbed, reply_to=event.id)
os.remove(files_grabbed)
os.chdir('./')
def download_training_data(self, num_of_images_per_category,
list_of_categories):
"""
uses bing_image_downloader==1-0-2 to download images
"""
sys.path.append(bing_fork_location)
from bing_image_downloader import downloader
lim = str(num_of_images_per_category)
categories = list_of_categories
for category in categories:
downloader.download(category,
limit=lim,
adult_filter_off=True,
force_replace=False)
#summary of downloads
print('{} Images of {}'.format(lim, pet))
def main(list_path, output_dir, num_images):
with open(list_path) as list_file:
for search_term in [line.strip() for line in list_file.readlines()]:
# names list might have two columns: refkb_ID<TAB>person_name
search_term = search_term.split('\t', 1)[-1].strip()
if os.path.exists(os.path.join(output_dir, search_term)):
print(f'Skipping {search_term}, path exists')
continue
print('Search term:', search_term)
try:
bing.download(query=search_term,
limit=num_images,
adult_filter_off='off',
output_dir=output_dir,
timeout=30,
page_counter_limit=5)
except Exception:
sys.stderr.write(
"ERROR: Exception occurred while processing name: {0}\n".
format(search_term))
traceback.print_exc()
async def img_sampler(event):
if event.fwd_from:
return
query = event.pattern_match.group(1)
jit = f'"{query}"'
downloader.download(
jit,
limit=5,
output_dir="store",
adult_filter_off=False,
force_replace=False,
timeout=60,
)
os.chdir(f'./store/"{query}"')
types = ("*.png", "*.jpeg", "*.jpg") # the tuple of file types
files_grabbed = []
for files in types:
files_grabbed.extend(glob.glob(files))
await tbot.send_file(event.chat_id, files_grabbed, reply_to=event.id)
os.chdir("/app")
os.system("rm -rf store")
async def img(
ctx,
nr: int,
*,
name: str,
):
if nr > 10:
await ctx.send(
"Da mi ssd u tau daca esti asa smecher 1000 de poze nu vrei?")
else:
downloader.download(name,
nr,
output_dir='dataset',
adult_filter_off=True,
force_replace=False,
timeout=60)
for file in os.listdir(f'dataset/{name}/'):
filename_str = f'dataset/{name}/{os.fsdecode(file)}'
file = discord.File(filename_str, filename=filename_str)
await ctx.send(file=file)
os.remove(filename_str)
from email.mime.text import MIMEText
from bing_image_downloader import downloader
# function that calls quotes api to get a random quote
from Day2_API_excel import get_random_quote
# save random quote to a map
data = {
'quote': get_random_quote()['text'],
'author': get_random_quote()['author']
}
# download an image, search by the contents of a quote
downloader.download(query=data['quote'],
limit=1,
output_dir='attachment//',
adult_filter_off=True,
force_replace=False,
timeout=60)
# save downloaded image, by default bing downloader creates a folder with query as a name
img_file_name = r"current_project's_path\attachment\\" + data[
'quote'] + "\Image_1.jpg"
# prepare message
img_data = open(img_file_name, 'rb').read()
msg = MIMEMultipart()
msg['Subject'] = 'A quote from ' + data['author']
msg['From'] = '*****@*****.**'
msg['To'] = '*****@*****.**'
from bing_image_downloader import downloader
query_string = input('what do you want images of?\n')
downloader.download(query_string, limit=100, adult_filter_off=True, force_replace=False)
def main():
parser = argparse.ArgumentParser(description='download some images')
parser.add_argument('search_term', help='the query string')
parser.add_argument('limit',
type=int,
help='the number of images to download')
parser.add_argument('--only_yandex', type=str, default='False')
args = parser.parse_args()
search_phrase = args.search_term
only_yandex = args.only_yandex
only_yandex = False if only_yandex == 'False' else True
limit = args.limit
if 'FLICKR_API_KEY' in os.environ:
api_key = os.environ['FLICKR_API_KEY']
else:
print("Set the FLICKR_API_KEY environment variable.")
sys.exit()
if 'FLICKR_API_SECRET' in os.environ:
api_secret = os.environ['FLICKR_API_SECRET']
else:
print("Set the FLICKR_API_SECRET_KEY")
sys.exit()
if 'WEBLY_DOWNLOAD_DIR' in os.environ:
webly_download_dir = Path(os.environ['WEBLY_DOWNLOAD_DIR'])
else:
print("Set the WEBLY_DOWNLOAD_DIR")
sys.exit()
# Create download folder.
search_dir = Path(webly_download_dir / search_phrase.replace(' ', '_'))
if not search_dir.exists():
search_dir.mkdir()
if not only_yandex:
print('Downloading bing images!')
downloader.download(search_phrase,
limit=limit,
adult_filter_off=True,
force_replace=False,
timeout=60)
# Move bing files.
bing_download_dir = Path(f'./dataset/{search_phrase}')
for b in bing_download_dir.iterdir():
shutil.move(b, Path(search_dir / b.name))
if bing_download_dir.exists():
bing_download_dir.rmdir()
if Path('./dataset').exists():
Path('./dataset').rmdir()
print('Downloading flickr images!')
download_flickr_images(api_key,
api_secret,
webly_download_dir,
search_phrase,
max_dl=limit)
print('Launching yandex script.')
subprocess.call([
'yandex-images-download', 'Chrome', '--keywords', f'"{search_phrase}"',
'--limit', f'{limit}', '-o', f'{str(webly_download_dir.resolve())}'
])
yandex_dir = Path(webly_download_dir / f'"{search_phrase}"')
for p in yandex_dir.iterdir():
shutil.move(p, Path(search_dir / p.name))
if yandex_dir.exists():
yandex_dir.rmdir()
from bing_image_downloader import downloader
downloader.download('mascara covid', limit=100, output_dir='dataset',
adult_filter_off=False, force_replace=False, timeout=60)
def fetchIMG(name):
downloader.download(name, limit=1)
return 'dataset/',name,'/',os.listdir("dataset/"+str(name))[0]
from bing_image_downloader import downloader
downloader.download("apple fruit", limit=20, output_dir='images')
from bing_image_downloader import downloader
import os
from PIL import Image
query_string = 'frog on mountain'
thisDir = os.getcwd()
downloader.download(query_string,
limit=1,
adult_filter_off=False,
force_replace=False,
timeout=60,
output_dir="")
fileName = thisDir + "/" + query_string + "/Image_1.jpg"
im = Image.open(fileName)
im.show()
from bing_image_downloader import downloader
downloader.download('apple fruit', limit=3, output_dir='dataset/train')
# downloader.download('fresh guava', limit=350, output_dir='dataset/test')
'Jackie Chan': 'Male',
'Stephen Chow': 'Male',
'Fan BingBing': 'Female',
'Yang Mi': 'Female'
}
print("[INFO] Downloading images ... ")
names = list(search_queries.keys())
for query in names:
if (os.path.exists(DATA_DIR + "/" + query)):
print("[INFO] Data dir '" + query +
"' has already exist, Skipping ... ")
continue
downloader.download(query,
limit=35,
adult_filter_off=False,
force_replace=True)
### After the download we need to check for validity ###
### Criteria : only 1 face per image, true gender ###
print("[INFO] Checking data validity ... ")
ALL_SATISFIED = False
while (not ALL_SATISFIED):
invalid_count = 0
for (dir, dirs, files) in os.walk(DATA_DIR):
if (dir != DATA_DIR):
for file in files:
abs_path = dir + "/" + file
print("[INFO] Check image file " + abs_path)
# 01_load_images.py
# ref https://pypi.org/project/bing-image-downloader/
from utility import create_folders
from bing_image_downloader import downloader
DIR_IMG = 'data/images'
search_string ='superman'
search_limit=15
if __name__ == "__main__":
#create some folders to store
create_folders([DIR_IMG])
#get a csv
downloader.download(search_string, limit=search_limit, \
output_dir=DIR_IMG, adult_filter_off=True, force_replace=False, timeout=60)
from bing_image_downloader import downloader as bing
print("Query String:")
query = input()
print("How many images:")
number = int(input())
bing.download(query, limit=number, output_dir='data', adult_filter_off=False, force_replace=False, timeout=60)
print("Complete")
from google_images_download import google_images_download
#instantiate the class
response = google_images_download.googleimagesdownload()
arguments = {
"keywords": "aeroplane, school bus, dog in front of house",
"limit": 10,
"print_urls": False
}
paths = response.download(arguments)
#print complete paths to the downloaded images
print(paths)
#####################################
#Bing
from bing_image_downloader import downloader
downloader.download("monkey",
limit=200,
output_dir='dataset',
adult_filter_off=True,
force_replace=False,
timeout=60)
downloader.download("tiger",
limit=200,
output_dir='dataset',
adult_filter_off=True,
force_replace=False,
timeout=60)
from bing_image_downloader import downloader
with open('download-dataset-query-strings.txt') as f:
for query_string in f:
query_string = query_string.strip()
print('Downloading images for:', query_string)
print()
downloader.download(query_string,
limit=500,
output_dir='indian-food-dataset-divyanshu',
adult_filter_off=True,
force_replace=False,
timeout=60)
print()
print()
from bing_image_downloader import downloader
file = open('Dishes.txt', 'r')
queries = file.read().splitlines()
for query in queries:
downloader.download(query.lower()+' images', limit=1000,
adult_filter_off=True, force_replace=False)
from bing_image_downloader import downloader
downloader.download('shopping trolley', limit=200, output_dir='dataset', adult_filter_off=True, force_replace=False, timeout=60)
#path to place you want training data to be dumped if not same dir as this py file
#path_to_training_data = '.'
gendirs = ['Gen1', 'Gen2', 'Gen3', 'Gen4', 'Gen5', 'Gen6', 'Gen7', 'Gen8']
gens = [gen1, gen2, gen3, gen4, gen5, gen6, gen7, gen8]
for gen in gens:
gendir = gendirs[gens.index(gen)]
directory = path_to_training_data + '/' + gendir + '/'
if not os.path.exists(directory):
os.makedirs(directory)
for pokemon in gen:
downloader.download(pokemon + ' pokemon',
limit=lim,
adult_filter_off=True,
force_replace=False)
#moves data to new location as we dont like dataset/bing/...
# bing-image-downloader 1.0.2 fork
os.system('mv dataset/bing/{} {}'.format(
pokemon + '\ pokemon',
path_to_training_data + '/' + gendir + '/' + pokemon))
#removes dataset/bing/ folder
os.system('rm -rf dataset/')
#######################################################
#summary of downloads
names_done = os.listdir('./images')
with open('strong_man.txt', encoding='utf-8') as file:
strong_mans = file.read().split(',')
strong_mans = [(strong + " strongman") if "strongman" not in strong else strong
for strong in strong_mans]
for index, query_string in enumerate(strong_mans):
if query_string in names_done:
continue
try:
now = time.time()
timeToFinish = ((now - start) / (index + 1)) * (len(strong_mans) -
(index + 1))
print(
f' {query_string}, {index + 1}/{len(strong_mans)} {(index + 1)/len(strong_mans) * 100}% timeToF: {timeToFinish}s '
.center(100, '#'))
downloader.download(query_string,
limit=7,
output_dir='./images',
adult_filter_off=True,
force_replace=False)
except:
logging.error(f'{query_string} not downloded')
print(f'done'.center(100, '#'))
input()
plt.imshow(andhra_cm_image_np)
plt.show()
"""# sometimes google wont allow the images to be downloaded, then we have an alternative which is microsoft bing. so lets see how we can extract the images from bing.
# download images from bing image search
"""
!pip install bing-image-downloader
"""# make a directory in current folder"""
!mkdir images
from bing_image_downloader import downloader
downloader.download("elephant in africa", limit = 5, output_dir ="images", adult_filter_off = True, force_replace = False)
downloader.download("tigers in india", limit = 10, output_dir="images", force_replace = False)
!ls images/ - alrt
!ls "images"/"tigers in india"
!ls "images"/"elephant in africa"
from IPython.display import Image
Image('images/elephant in africa/Image_1.jpg')
Image('images/tigers in india/Image_1.jpg')
# convert into numpy so that i can feed it into any model
from bing_image_downloader import downloader
import os
import shutil
query = ["rural", "gray backgrounds"] #put words to search
output_dir = "bing_images"
if not os.path.exists(output_dir): #if dir not present, make it
os.mkdir(output_dir)
for i in range(len(query)):
downloader.download(query[i],
limit=100,
output_dir=output_dir,
adult_filter_off=True,
force_replace=False,
timeout=60)
### merge image folders with search queary name into one image dir:"images" ###
target_dir = "images"
if not os.path.exists(target_dir): #if dir not present, make it
os.mkdir(target_dir)
count = 0
for dirname in os.listdir(output_dir):
file_names = os.listdir(os.path.join(output_dir, dirname))
for file_name in file_names:
count += 1
shutil.move(os.path.join(os.path.join(output_dir, dirname), file_name),
target_dir)
# Importation des librairies
import os
# git clone https://github.com/gurugaurav/bing_image_downloader
# sudo python3 setup.py install
# Lien vers doc API : pypi.org/project/bing-image-downloader
from bing_image_downloader import downloader
# Nombre d'images à télécharger
NB_IMG = 15
# Creation du dossier 'bing_search' s'il n'existe pas
if not os.path.exists("bing_search"):
os.makedirs("bing_search")
# Demande des mots clefs à l'utilisateur
mots_clefs = input("Quels mots clefs souhaitez-vous pour votre recherche ? ")
# Récupération des images du résultat de la recherche
downloader.download(mots_clefs,
limit=NB_IMG,
output_dir="bing_search",
force_replace=True)
