1. 梗概：我是个化验师，我们可是也要我们做PPT，医学知识往往繁多复杂，要是有比较好的照片配合文字，可以大大增加PPT的效果。必应这个网站可以搜索到比较有价值的医学图片，要是你输入一个医学名词，同样的搜索引擎，必应检索到的医学图片比较精准。所以，今天，我们就来做这个批量下载必应图片的项目。

1. 软件条件：安装anaconda的电脑。

1. 需要写两个py：bing.py和downloader.py。

bing.py

from pathlib import Path
import urllib.request
import urllib
import imghdr
import posixpath
import reclass Bing:def __init__(self, query, limit, output_dir, adult, timeout,  filter='', verbose=True):self.download_count = 0self.query = queryself.output_dir = output_dirself.adult = adultself.filter = filterself.verbose = verboseself.seen = set()assert type(limit) == int, "limit must be integer"self.limit = limitassert type(timeout) == int, "timeout must be integer"self.timeout = timeout# self.headers = {'User-Agent': 'Mozilla/5.0 (X11; Fedora; Linux x86_64; rv:60.0) Gecko/20100101 Firefox/60.0'}self.page_counter = 0self.headers = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) ' 'AppleWebKit/537.11 (KHTML, like Gecko) ''Chrome/23.0.1271.64 Safari/537.11','Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8','Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3','Accept-Encoding': 'none','Accept-Language': 'en-US,en;q=0.8','Connection': 'keep-alive'}def get_filter(self, shorthand):if shorthand == "line" or shorthand == "linedrawing":return "+filterui:photo-linedrawing"elif shorthand == "photo":return "+filterui:photo-photo"elif shorthand == "clipart":return "+filterui:photo-clipart"elif shorthand == "gif" or shorthand == "animatedgif":return "+filterui:photo-animatedgif"elif shorthand == "transparent":return "+filterui:photo-transparent"else:return ""def save_image(self, link, file_path):request = urllib.request.Request(link, None, self.headers)image = urllib.request.urlopen(request, timeout=self.timeout).read()if not imghdr.what(None, image):print('[Error]Invalid image, not saving {}\n'.format(link))raise ValueError('Invalid image, not saving {}\n'.format(link))with open(str(file_path), 'wb') as f:f.write(image)def download_image(self, link):self.download_count += 1# Get the image linktry:path = urllib.parse.urlsplit(link).pathfilename = posixpath.basename(path).split('?')[0]file_type = filename.split(".")[-1]if file_type.lower() not in ["jpe", "jpeg", "jfif", "exif", "tiff", "gif", "bmp", "png", "webp", "jpg"]:file_type = "jpg"if self.verbose:# Download the imageprint("[%] Downloading Image #{} from {}".format(self.download_count, link))self.save_image(link, self.output_dir.joinpath("Image_{}.{}".format(str(self.download_count), file_type)))if self.verbose:print("[%] File Downloaded !\n")except Exception as e:self.download_count -= 1print("[!] Issue getting: {}\n[!] Error:: {}".format(link, e))def run(self):while self.download_count < self.limit:if self.verbose:print('\n\n[!!]Indexing page: {}\n'.format(self.page_counter + 1))# Parse the page source and download picsrequest_url = 'https://www.bing.com/images/async?q=' + urllib.parse.quote_plus(self.query) \+ '&first=' + str(self.page_counter) + '&count=' + str(self.limit) \+ '&adlt=' + self.adult + '&qft=' + ('' if self.filter is None else self.get_filter(self.filter))request = urllib.request.Request(request_url, None, headers=self.headers)response = urllib.request.urlopen(request)html = response.read().decode('utf8')if html ==  "":print("[%] No more images are available")breaklinks = re.findall('murl&quot;:&quot;(.*?)&quot;', html)if self.verbose:print("[%] Indexed {} Images on Page {}.".format(len(links), self.page_counter + 1))print("\n===============================================\n")for link in links:if self.download_count < self.limit and link not in self.seen:self.seen.add(link)self.download_image(link)self.page_counter += 1print("\n\n[%] Done. Downloaded {} images.".format(self.download_count))

downloader.py

在最后一行代码download('urine crystal', output_dir="..\\Users\\cat", limit=100, timeout=1)的第一个参数修改你自己想要检索的英文关键字就可以了。

import os, sys
import shutil
from pathlib import Pathtry:from bing import Bing
except ImportError:  # Python 3from .bing import Bingdef download(query, limit=100, output_dir='dataset', adult_filter_off=True,
force_replace=False, timeout=60, filter="", verbose=True):# engine = 'bing'if adult_filter_off:adult = 'off'else:adult = 'on'image_dir = Path(output_dir).joinpath(query).absolute()if force_replace:if Path.is_dir(image_dir):shutil.rmtree(image_dir)# check directory and create if necessarytry:if not Path.is_dir(image_dir):Path.mkdir(image_dir, parents=True)except Exception as e:print('[Error]Failed to create directory.', e)sys.exit(1)print("[%] Downloading Images to {}".format(str(image_dir.absolute())))bing = Bing(query, limit, image_dir, adult, timeout, filter, verbose)bing.run()if __name__ == '__main__':download('urine crystal', output_dir="..\\Users\\cat", limit=100, timeout=1)#输入你想要搜索的英文关键字

效果：

尽管我们这个脚本可以下载到图片，但是，有时候图片下载不到，不过，下载不到的图片链接不会影响我们其他图片的下载，因为，我们有用try...except...

总结：总体这个脚本还可以用，不过，改进。