快速构建深度学习图像数据集，微软Bing和Google哪个更好用？

$pip install requests

$ workon your_env_name
$ pip install requests

# import the necessary packages
from requests import exceptions
import argparse
import requests
import cv2
import os
# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-q", "--query", required=True,
    help="search query to search Bing Image API for")
ap.add_argument("-o", "--output", required=True,
    help="path to output directory of images")
args = vars(ap.parse_args())

# set your Microsoft Cognitive Services API key along with (1) the
# maximum number of results for a given search and (2) the group size
# for results (maximum of 50 per request)
API_KEY = "YOUR_API_KEY_GOES_HERE"
MAX_RESULTS = 250
GROUP_SIZE = 50
# set the endpoint API URL
URL = "https://api.cognitive.microsoft.com/bing/v7.0/images/search"

# when attempting to download images from the web both the Python
# programming language and the requests library have a number of
# exceptions that can be thrown so let's build a list of them now
# so we can filter on them
EXCEPTIONS = set([IOError, FileNotFoundError,
    exceptions.RequestException, exceptions.HTTPError,
    exceptions.ConnectionError, exceptions.Timeout])

# store the search term in a convenience variable then set the
# headers and search parameters
term = args["query"]
headers = {"Ocp-Apim-Subscription-Key" : API_KEY}
params = {"q": term, "offset": 0, "count": GROUP_SIZE}
# make the search
print("[INFO] searching Bing API for '{}'".format(term))
search = requests.get(URL, headers=headers, params=params)
search.raise_for_status()
# grab the results from the search, including the total number of
# estimated results returned by the Bing API
results = search.json()
estNumResults = min(results["totalEstimatedMatches"], MAX_RESULTS)
print("[INFO] {} total results for '{}'".format(estNumResults,
    term))
# initialize the total number of images downloaded thus far
total = 0

# loop over the estimated number of results in `GROUP_SIZE` groups
for offset in range(0, estNumResults, GROUP_SIZE):
    # update the search parameters using the current offset, then
    # make the request to fetch the results
    print("[INFO] making request for group {}-{} of {}...".format(
        offset, offset + GROUP_SIZE, estNumResults))
    params["offset"] = offset
    search = requests.get(URL, headers=headers, params=params)
    search.raise_for_status()
    results = search.json()
    print("[INFO] saving images for group {}-{} of {}...".format(
        offset, offset + GROUP_SIZE, estNumResults))

# loop over the results
    for v in results["value"]:
        # try to download the image
        try:
            # make a request to download the image
            print("[INFO] fetching: {}".format(v["contentUrl"]))
            r = requests.get(v["contentUrl"], timeout=30)
            # build the path to the output image
            ext = v["contentUrl"][v["contentUrl"].rfind("."):]
            p = os.path.sep.join([args["output"], "{}{}".format(
                str(total).zfill(8), ext)])
            # write the image to disk
            f = open(p, "wb")
            f.write(r.content)
            f.close()
        # catch any errors that would not unable us to download the
        # image
        except Exception as e:
            # check to see if our exception is in our list of
            # exceptions to check for
            if type(e) in EXCEPTIONS:
                print("[INFO] skipping: {}".format(v["contentUrl"]))
                continue

        # try to load the image from disk
        image = cv2.imread(p)
        # if the image is `None` then we could not properly load the
        # image from disk (so it should be ignored)
        if image is None:
            print("[INFO] deleting: {}".format(p))
            os.remove(p)
            continue
        # update the counter
        total += 1

$mkdirdataset

$ mkdir dataset/charmander
$ python search_bing_api.py --query "charmander" --output dataset/charmander
[INFO] searching Bing API for 'charmander'
[INFO] 250 total results for 'charmander'
[INFO] making request for group 0-50 of 250...
[INFO] saving images for group 0-50 of 250...
[INFO] fetching: http://fc06.deviantart.net/fs70/i/2012/355/8/2/0004_c___charmander_by_gaghiel1987-d5oqbts.png
[INFO] fetching: http://th03.deviantart.net/fs71/PRE/f/2010/067/5/d/Charmander_by_Woodsman819.jpg
[INFO] fetching: http://fc05.deviantart.net/fs70/f/2011/120/8/6/pokemon___charmander_by_lilnutta10-d2vr4ov.jpg
...
[INFO] making request for group 50-100 of 250...
[INFO] saving images for group 50-100 of 250...
...
[INFO] fetching: http://38.media.tumblr.com/f0fdd67a86bc3eee31a5fd16a44c07af/tumblr_nbhf2vTtSH1qc9mvbo1_500.gif
[INFO] deleting: dataset/charmander/00000174.gif
...

$ mkdir dataset/pikachu
$ python search_bing_api.py --query "pikachu" --output dataset/pikachu
[INFO] searching Bing API for 'pikachu'
[INFO] 250 total results for 'pikachu'
[INFO] making request for group 0-50 of 250...
[INFO] saving images for group 0-50 of 250...
[INFO] fetching: http://www.mcmbuzz.com/wp-content/uploads/2014/07/025Pikachu_OS_anime_4.png
[INFO] fetching: http://images4.fanpop.com/image/photos/23300000/Pikachu-pikachu-23385603-814-982.jpg
[INFO] fetching: http://images6.fanpop.com/image/photos/33000000/pikachu-pikachu-33005706-895-1000.png
...

$ mkdir dataset/squirtle
$ python search_bing_api.py --query "squirtle" --output dataset/squirtle
[INFO] searching Bing API for 'squirtle'
[INFO] 250 total results for 'squirtle'
[INFO] making request for group 0-50 of 250...
[INFO] saving images for group 0-50 of 250...
[INFO] fetching: http://fc03.deviantart.net/fs71/i/2013/082/1/3/007_squirtle_by_pklucario-d5z1gj5.png
[INFO] fetching: http://fc03.deviantart.net/fs70/i/2012/035/b/2/squirtle_by_maii1234-d4oo1aq.jpg
[INFO] fetching: http://3.bp.blogspot.com/-yeK-y_dHCCQ/TWBkDZKi6vI/AAAAAAAAABU/_TVDXBrxrkg/s1600/Leo%2527s+Squirtle.jpg
...

$ mkdir dataset/bulbasaur
$ python search_bing_api.py --query "bulbasaur" --output dataset/bulbasaur
[INFO] searching Bing API for 'bulbasaur'
[INFO] 250 total results for 'bulbasaur'
[INFO] making request for group 0-50 of 250...
[INFO] saving images for group 0-50 of 250...
[INFO] fetching: http://fc06.deviantart.net/fs51/f/2009/261/3/e/Bulbasaur_by_elfaceitoso.png
[INFO] skipping: http://fc06.deviantart.net/fs51/f/2009/261/3/e/Bulbasaur_by_elfaceitoso.png
[INFO] fetching: http://4.bp.blogspot.com/-b-dLFLsHtm4/Tq9265UAmjI/AAAAAAAAHls/CrkUUFrj6_c/s1600/001Bulbasaur+pokemon+firered+leafgreen.png
[INFO] skipping: http://4.bp.blogspot.com/-b-dLFLsHtm4/Tq9265UAmjI/AAAAAAAAHls/CrkUUFrj6_c/s1600/001Bulbasaur+pokemon+firered+leafgreen.png
[INFO] fetching: http://fc09.deviantart.net/fs71/i/2012/088/9/6/bulbasaur_by_songokukai-d4gecpp.png
...

$ mkdir dataset/mewtwo
$ python search_bing_api.py --query "mewtwo" --output dataset/mewtwo
[INFO] searching Bing API for 'mewtwo'
[INFO] 250 total results for 'mewtwo'
[INFO] making request for group 0-50 of 250...
[INFO] saving images for group 0-50 of 250...
[INFO] fetching: http://sickr.files.wordpress.com/2011/09/mewtwo.jpg
[INFO] fetching: http://4.bp.blogspot.com/-_7XMdCIyKDs/T3f-0h2X4zI/AAAAAAAABmQ/S2904beJlOw/s1600/Mewtwo+Pokemon+Wallpapers+3.jpg
[INFO] fetching: http://2.bp.blogspot.com/-3jDdQdPl1yQ/T3f-61gJXEI/AAAAAAAABmg/AUmKm65ckv8/s1600/Mewtwo+Pokemon+Wallpapers.jpg
...

$ find . -type d -print0 | while read -d '' -r dir; do
> files=("$dir"/*)
> printf "%5d files in directory %sn" "${#files[@]}" "$dir"
> done
    2 files in directory .
    5 files in directory ./dataset
  235 files in directory ./dataset/bulbasaur
  245 files in directory ./dataset/charmander
  245 files in directory ./dataset/mewtwo
  238 files in directory ./dataset/pikachu
  230 files in directory ./dataset/squirtle

$ find . -type d -print0 | while read -d '' -r dir; do
> files=("$dir"/*);
> printf "%5d files in directory %sn" "${#files[@]}" "$dir";
> done
     3 files in directory .
     5 files in directory ./dataset
   234 files in directory ./dataset/bulbasaur
   238 files in directory ./dataset/charmander
   239 files in directory ./dataset/mewtwo
   234 files in directory ./dataset/pikachu
   223 files in directory ./dataset/squirtle