脚本也是参考有关博客的,但是忘记录地址了,如有侵权立删。
下载百度图片:
import re
import requests
from urllib import error
from bs4 import BeautifulSoup
import os
num = 0
numPicture = 0
file = ''
List = []
def Find(url):
global List
print('正在检测图片总数,请稍等.....')
t = 0
i = 1
s = 0
while t < 10000:
Url = url + str(t)
try:
Result = requests.get(Url, timeout=7)
except BaseException:
t = t + 60
continue
else:
result = Result.text
pic_url = re.findall('"objURL":"(.*?)",', result, re.S) # 先利用正则表达式找到图片url
s += len(pic_url)
if len(pic_url) == 0:
break
else:
List.append(pic_url)
t = t + 60
return s
def recommend(url):
Re = []
try:
html = requests.get(url)
except error.HTTPError as e:
return
else:
html.encoding = 'utf-8'
bsObj = BeautifulSoup(html.text, 'html.parser')
div = bsObj.find('div', id='topRS')
if div is not None:
listA = div.findAll('a')
for i in listA:
if i is not None:
Re.append(i.get_text())
return Re
def dowmloadPicture(html, keyword):
global num
# t =0
pic_url = re.findall('"objURL":"(.*?)",', html, re.S) # 先利用正则表达式找到图片url
print('找到关键词:' + keyword + '的图片,即将开始下载图片...')
for each in pic_url:
print('正在下载第' + str(num + 1) + '张图片,图片地址:' + str(each))
try:
if each is not None:
pic = requests.get(each, timeout=7)
else:
continue
except BaseException:
print('错误,当前图片无法下载')
continue
else:
string = file + r'\\' + keyword + '_' + str(num) + '.jpg'
fp = open(string, 'wb')
fp.write(pic.content)
fp.close()
num += 1
if num >= numPicture:
return
if __name__ == '__main__': # 主函数入口
word = input("请输入搜索关键词(可以是人名,地名等): ")
#add = 'http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=%E5%BC%A0%E5%A4%A9%E7%88%B1&pn=120'
url = 'http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=' + word + '&pn='
tot = Find(url)
Recommend = recommend(url) # 记录相关推荐
print('经过检测%s类图片共有%d张' % (word, tot))
numPicture = int(input('请输入想要下载的图片数量 '))
file = input('请建立一个存储图片的文件夹,输入文件夹名称即可')
y = os.path.exists(file)
if y == 1:
print('该文件已存在,请重新输入')
file = input('请建立一个存储图片的文件夹,)输入文件夹名称即可')
os.mkdir(file)
else:
os.mkdir(file)
t = 0
tmp = url
while t < numPicture:
try:
url = tmp + str(t)
result = requests.get(url, timeout=10)
print(url)
except error.HTTPError as e:
print('网络错误,请调整网络后重试')
t = t+60
else:
dowmloadPicture(result.text, word)
t = t + 60
print('当前搜索结束,感谢使用')
print('猜你喜欢')
for re in Recommend:
print(re, end=' ')
下载必应图片:
#!/usr/bin/env python3
import os, urllib.request, re, threading, posixpath, urllib.parse, argparse, socket, time, hashlib, pickle, signal, imghdr
#config
output_dir = './bing' #default output dir
adult_filter = True #Do not disable adult filter by default
socket.setdefaulttimeout(2)
tried_urls = []
image_md5s = {}
in_progress = 0
urlopenheader={ 'User-Agent' : 'Mozilla/5.0 (X11; Fedora; Linux x86_64; rv:60.0) Gecko/20100101 Firefox/60.0'}
def download(pool_sema: threading.Semaphore, url: str, output_dir: str):
global in_progress
if url in tried_urls:
return
pool_sema.acquire()
in_progress += 1
path = urllib.parse.urlsplit(url).path
filename = posixpath.basename(path).split('?')[0] #Strip GET parameters from filename
name, ext = os.path.splitext(filename)
name = name[:36].strip()
filename = name + ext
try:
request=urllib.request.Request(url,None,urlopenheader)
image=urllib.request.urlopen(request).read()
if not imghdr.what(None, image):
print('Invalid image, not saving ' + filename)
return
md5_key = hashlib.md5(image).hexdigest()
if md5_key in image_md5s:
print('Image is a duplicate of ' + image_md5s[md5_key] + ', not saving ' + filename)
return
i = 0
while os.path.exists(os.path.join(output_dir, filename)):
if hashlib.md5(open(os.path.join(output_dir, filename), 'rb').read()).hexdigest() == md5_key:
print('Already downloaded ' + filename + ', not saving')
return
i += 1
filename = "%s-%d%s" % (name, i, ext)
image_md5s[md5_key] = filename
imagefile=open(os.path.join(output_dir, filename),'wb')
imagefile.write(image)
imagefile.close()
print("OK: " + filename)
tried_urls.append(url)
except Exception as e:
print("FAIL: " + filename)
finally:
pool_sema.release()
in_progress -= 1
def fetch_images_from_keyword(pool_sema: threading.Semaphore, keyword: str, output_dir: str, filters: str, limit: int):
current = 0
last = ''
while True:
time.sleep(0.1)
if in_progress > 10:
continue
request_url='https://www.bing.com/images/async?q=' + urllib.parse.quote_plus(keyword) + '&first=' + str(current) + '&count=35&adlt=' + adlt + '&qft=' + ('' if filters is None else filters)
request=urllib.request.Request(request_url,None,headers=urlopenheader)
response=urllib.request.urlopen(request)
html = response.read().decode('utf8')
links = re.findall('murl":"(.*?)"',html)
try:
if links[-1] == last:
return
for index, link in enumerate(links):
if limit is not None and current + index >= limit:
return
t = threading.Thread(target = download,args = (pool_sema, link, output_dir))
t.start()
current += 1
last = links[-1]
except IndexError:
print('No search results for "{0}"'.format(keyword))
return
def backup_history(*args):
download_history = open(os.path.join(output_dir, 'download_history.pickle'), 'wb')
pickle.dump(tried_urls,download_history)
copied_image_md5s = dict(image_md5s) #We are working with the copy, because length of input variable for pickle must not be changed during dumping
pickle.dump(copied_image_md5s, download_history)
download_history.close()
print('history_dumped')
if args:
exit(0)
if __name__ == "__main__":
parser = argparse.ArgumentParser(description = 'Bing image bulk downloader')
parser.add_argument('-s', '--search-string', help = 'Keyword to search', required = False)
parser.add_argument('-f', '--search-file', help = 'Path to a file containing search strings line by line', required = False)
parser.add_argument('-o', '--output', help = 'Output directory', required = False)
parser.add_argument('--adult-filter-on', help ='Enable adult filter', action = 'store_true', required = False)
parser.add_argument('--adult-filter-off', help = 'Disable adult filter', action = 'store_true', required = False)
parser.add_argument('--filters', help = 'Any query based filters you want to append when searching for images, e.g. +filterui:license-L1', required = False)
parser.add_argument('--limit', help = 'Make sure not to search for more than specified amount of images.', required = False, type = int)
parser.add_argument('--threads', help = 'Number of threads', type = int, default = 20)
args = parser.parse_args()
if (not args.search_string) and (not args.search_file):
parser.error('Provide Either search string or path to file containing search strings')
if args.output:
output_dir = args.output
if not os.path.exists(output_dir):
os.makedirs(output_dir)
output_dir_origin = output_dir
signal.signal(signal.SIGINT, backup_history)
try:
download_history = open(os.path.join(output_dir, 'download_history.pickle'), 'rb')
tried_urls=pickle.load(download_history)
image_md5s=pickle.load(download_history)
download_history.close()
except (OSError, IOError):
tried_urls=[]
if adult_filter:
adlt = ''
else:
adlt = 'off'
if args.adult_filter_off:
adlt = 'off'
elif args.adult_filter_on:
adlt = ''
pool_sema = threading.BoundedSemaphore(args.threads)
if args.search_string:
fetch_images_from_keyword(pool_sema, args.search_string,output_dir, args.filters, args.limit)
elif args.search_file:
try:
inputFile=open(args.search_file)
except (OSError, IOError):
print("Couldn't open file {}".format(args.search_file))
exit(1)
for keyword in inputFile.readlines():
output_sub_dir = os.path.join(output_dir_origin, keyword.strip().replace(' ', '_'))
if not os.path.exists(output_sub_dir):
os.makedirs(output_sub_dir)
fetch_images_from_keyword(pool_sema, keyword,output_sub_dir, args.filters, args.limit)
backup_history()
time.sleep(10)
inputFile.close()