我知道互联网上图片的网址。
e.g。 http://www.digimouth.com/news/media/2011/09/google-logo.jpg，其中包含Google徽标。
现在，如何使用Python下载此图像，而无需在浏览器中实际打开URL并手动保存文件。
答案 0 :(得分：250)
如果您只想将其保存为文件，这是一种更直接的方式：
import urllib
urllib.urlretrieve("http://www.digimouth.com/news/media/2011/09/google-logo.jpg", "local-filename.jpg")
第二个参数是应保存文件的本地路径。
正如SergO建议的，下面的代码应该适用于Python 3。
import urllib.request
urllib.request.urlretrieve("http://www.digimouth.com/news/media/2011/09/google-logo.jpg", "local-filename.jpg")
答案 1 :(得分：26)
import urllib
resource = urllib.urlopen("http://www.digimouth.com/news/media/2011/09/google-logo.jpg")
output = open("file01.jpg","wb")
output.write(resource.read())
output.close()
file01.jpg将包含您的图片。
答案 2 :(得分：15)
我写了a script that does just this，我可以在我的github上找到它供你使用。
我利用BeautifulSoup允许我解析任何网站的图像。如果您要进行大量网页抓取（或打算使用我的工具），我建议您sudo pip install BeautifulSoup。有关BeautifulSoup的信息可用here。
为方便起见，这是我的代码：
from bs4 import BeautifulSoup
from urllib2 import urlopen
import urllib
# use this image scraper from the location that
#you want to save scraped images to
def make_soup(url):
html = urlopen(url).read()
return BeautifulSoup(html)
def get_images(url):
soup = make_soup(url)
#this makes a list of bs4 element tags
images = [img for img in soup.findAll('img')]
print (str(len(images)) + "images found.")
print 'Downloading images to current working directory.'
#compile our unicode list of image links
image_links = [each.get('src') for each in images]
for each in image_links:
filename=each.split('/')[-1]
urllib.urlretrieve(each, filename)
return image_links
#a standard call looks like this
#get_images('http://www.wookmark.com')
答案 3 :(得分：6)
适用于Python 2和Python 3的解决方案：
try:
from urllib.request import urlretrieve # Python 3
except ImportError:
from urllib import urlretrieve # Python 2
url = "http://www.digimouth.com/news/media/2011/09/google-logo.jpg"
urlretrieve(url, "local-filename.jpg")
或者，如果requests的额外要求是可接受的，并且是http（s）网址：
def load_requests(source_url, sink_path):
"""
Load a file from an URL (e.g. http).
Parameters
----------
source_url : str
Where to load the file from.
sink_path : str
Where the loaded file is stored.
"""
import requests
r = requests.get(source_url, stream=True)
if r.status_code == 200:
with open(sink_path, 'wb') as f:
for chunk in r:
f.write(chunk)
答案 4 :(得分：5)
我制作了一个扩展Yup。脚本的脚本。我修了一些东西。它现在将绕过403：禁止的问题。当图像无法检索时，它不会崩溃。它试图避免损坏的预览。它获得了正确的绝对网址。它提供了更多信息。它可以使用命令行中的参数运行。
# getem.py
# python2 script to download all images in a given url
# use: python getem.py http://url.where.images.are
from bs4 import BeautifulSoup
import urllib2
import shutil
import requests
from urlparse import urljoin
import sys
import time
def make_soup(url):
req = urllib2.Request(url, headers={'User-Agent' : "Magic Browser"})
html = urllib2.urlopen(req)
return BeautifulSoup(html, 'html.parser')
def get_images(url):
soup = make_soup(url)
images = [img for img in soup.findAll('img')]
print (str(len(images)) + " images found.")
print 'Downloading images to current working directory.'
image_links = [each.get('src') for each in images]
for each in image_links:
try:
filename = each.strip().split('/')[-1].strip()
src = urljoin(url, each)
print 'Getting: ' + filename
response = requests.get(src, stream=True)
# delay to avoid corrupted previews
time.sleep(1)
with open(filename, 'wb') as out_file:
shutil.copyfileobj(response.raw, out_file)
except:
print ' An error occured. Continuing.'
print 'Done.'
if __name__ == '__main__':
url = sys.argv[1]
get_images(url)
答案 5 :(得分：5)
Python 3
urllib.request — Extensible library for opening URLs
from urllib.error import HTTPError
from urllib.request import urlretrieve
try:
urlretrieve(image_url, image_local_path)
except FileNotFoundError as err:
print(err) # something wrong with local path
except HTTPError as err:
print(err) # something wrong with url
答案 6 :(得分：3)
这可以通过请求来完成。加载页面并将二进制内容转储到文件中。
import os
import requests
url = 'https://apod.nasa.gov/apod/image/1701/potw1636aN159_HST_2048.jpg'
page = requests.get(url)
f_ext = os.path.splitext(url)[-1]
f_name = 'img{}'.format(f_ext)
with open(f_name, 'wb') as f:
f.write(page.content)
答案 7 :(得分：3)
使用请求库
import requests
import shutil,os
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'
}
currentDir = os.getcwd()
path = os.path.join(currentDir,'Images')#saving images to Images folder
def ImageDl(url):
attempts = 0
while attempts < 5:#retry 5 times
try:
filename = url.split('/')[-1]
r = requests.get(url,headers=headers,stream=True,timeout=5)
if r.status_code == 200:
with open(os.path.join(path,filename),'wb') as f:
r.raw.decode_content = True
shutil.copyfileobj(r.raw,f)
print(filename)
break
except Exception as e:
attempts+=1
print(e)
ImageDl(url)
答案 8 :(得分：1)
这是一个非常简短的答案。
import urllib
urllib.urlretrieve("http://photogallery.sandesh.com/Picture.aspx?AlubumId=422040", "Abc.jpg")
答案 9 :(得分：1)
我为Python 3调整了@madprops的代码
# getem.py
# python2 script to download all images in a given url
# use: python getem.py http://url.where.images.are
from bs4 import BeautifulSoup
import urllib.request
import shutil
import requests
from urllib.parse import urljoin
import sys
import time
def make_soup(url):
req = urllib.request.Request(url, headers={'User-Agent' : "Magic Browser"})
html = urllib.request.urlopen(req)
return BeautifulSoup(html, 'html.parser')
def get_images(url):
soup = make_soup(url)
images = [img for img in soup.findAll('img')]
print (str(len(images)) + " images found.")
print('Downloading images to current working directory.')
image_links = [each.get('src') for each in images]
for each in image_links:
try:
filename = each.strip().split('/')[-1].strip()
src = urljoin(url, each)
print('Getting: ' + filename)
response = requests.get(src, stream=True)
# delay to avoid corrupted previews
time.sleep(1)
with open(filename, 'wb') as out_file:
shutil.copyfileobj(response.raw, out_file)
except:
print(' An error occured. Continuing.')
print('Done.')
if __name__ == '__main__':
get_images('http://www.wookmark.com')
答案 10 :(得分：1)
使用Requests对于Python 3来说是新鲜的东西
代码中的注释。随时可用的功能。
import requests
from os import path
def get_image(image_url):
"""
Get image based on url.
:return: Image name if everything OK, False otherwise
"""
image_name = path.split(image_url)[1]
try:
image = requests.get(image_url)
except OSError: # Little too wide, but work OK, no additional imports needed. Catch all conection problems
return False
if image.status_code == 200: # we could have retrieved error page
base_dir = path.join(path.dirname(path.realpath(__file__)), "images") # Use your own path or "" to use current working directory. Folder must exist.
with open(path.join(base_dir, image_name), "wb") as f:
f.write(image.content)
return image_name
get_image("https://apod.nasddfda.gov/apod/image/2003/S106_Mishra_1947.jpg")
答案 11 :(得分：1)
如果您还没有图片的网址，则可以使用gazpacho进行抓取：
from gazpacho import Soup
base_url = "http://books.toscrape.com"
soup = Soup.get(base_url)
links = [img.attrs["src"] for img in soup.find("img")]
然后按照所述用urllib下载资产：
from pathlib import Path
from urllib.request import urlretrieve as download
directory = "images"
Path(directory).mkdir(exist_ok=True)
link = links[0]
name = link.split("/")[-1]
download(f"{base_url}/{link}", f"{directory}/{name}")
答案 12 :(得分：0)
最新答案，但是对于python>=3.6，您可以使用dload，即：
import dload
dload.save("http://www.digimouth.com/news/media/2011/09/google-logo.jpg")
如果您需要将图像作为bytes，请使用：
img_bytes = dload.bytes("http://www.digimouth.com/news/media/2011/09/google-logo.jpg")
使用pip3 install dload
答案 13 :(得分：0)
使用简单的python wget模块下载链接。用法如下：
import wget
wget.download('http://www.digimouth.com/news/media/2011/09/google-logo.jpg')
答案 14 :(得分：-1)
img_data=requests.get('https://apod.nasa.gov/apod/image/1701/potw1636aN159_HST_2048.jpg')
with open(str('file_name.jpg', 'wb') as handler:
handler.write(img_data)
答案 15 :(得分：-1)
下载图片文件，避免所有可能的错误：
import requests
import validators
from urllib.request import Request, urlopen
from urllib.error import URLError, HTTPError
def is_downloadable(url):
valid=validators. url(url)
if valid==False:
return False
req = Request(url)
try:
response = urlopen(req)
except HTTPError as e:
return False
except URLError as e:
return False
else:
return True
for i in range(len(File_data)): #File data Contain list of address for image
#file
url = File_data[i][1]
try:
if (is_downloadable(url)):
try:
r = requests.get(url, allow_redirects=True)
if url.find('/'):
fname = url.rsplit('/', 1)[1]
fname = pth+File_data[i][0]+"$"+fname #Destination to save
#image file
open(fname, 'wb').write(r.content)
except Exception as e:
print(e)
except Exception as e:
print(e)