I'm trying to download and save an image from the web using python's requests module.
Here is the (working) code I used:
img = urllib2.urlopen(settings.STATICMAP_URL.format(**data))
with open(path, 'w') as f:
f.write(img.read())
Here is the new (non-working) code using requests:
r = requests.get(settings.STATICMAP_URL.format(**data))
if r.status_code == 200:
img = r.raw.read()
with open(path, 'w') as f:
f.write(img)
Can you help me on what attribute from the response to use from requests?
You can either use the response.raw file object, or iterate over the response.
To use the response.raw file-like object will not, by default, decode compressed responses (with GZIP or deflate). You can force it to decompress for you anyway by setting the decode_content attribute to True (requests sets it to False to control decoding itself). You can then use shutil.copyfileobj() to have Python stream the data to a file object:
import requests
import shutil
r = requests.get(settings.STATICMAP_URL.format(**data), stream=True)
if r.status_code == 200:
with open(path, 'wb') as f:
r.raw.decode_content = True
shutil.copyfileobj(r.raw, f)
To iterate over the response use a loop; iterating like this ensures that data is decompressed by this stage:
r = requests.get(settings.STATICMAP_URL.format(**data), stream=True)
if r.status_code == 200:
with open(path, 'wb') as f:
for chunk in r:
f.write(chunk)
This'll read the data in 128 byte chunks; if you feel another chunk size works better, use the Response.iter_content() method with a custom chunk size:
r = requests.get(settings.STATICMAP_URL.format(**data), stream=True)
if r.status_code == 200:
with open(path, 'wb') as f:
for chunk in r.iter_content(1024):
f.write(chunk)
Note that you need to open the destination file in binary mode to ensure python doesn't try and translate newlines for you. We also set stream=True so that requests doesn't download the whole image into memory first.
Get a file-like object from the request and copy it to a file. This will also avoid reading the whole thing into memory at once.
import shutil
import requests
url = 'http://example.com/img.png'
response = requests.get(url, stream=True)
with open('img.png', 'wb') as out_file:
shutil.copyfileobj(response.raw, out_file)
del response
How about this, a quick solution.
import requests
url = "http://craphound.com/images/1006884_2adf8fc7.jpg"
response = requests.get(url)
if response.status_code == 200:
with open("/Users/apple/Desktop/sample.jpg", 'wb') as f:
f.write(response.content)
I have the same need for downloading images using requests. I first tried the answer of Martijn Pieters, and it works well. But when I did a profile on this simple function, I found that it uses so many function calls compared to urllib and urllib2.
I then tried the way recommended by the author of requests module:
import requests
from PIL import Image
# python2.x, use this instead
# from StringIO import StringIO
# for python3.x,
from io import StringIO
r = requests.get('https://example.com/image.jpg')
i = Image.open(StringIO(r.content))
This much more reduced the number of function calls, thus speeded up my application.
Here is the code of my profiler and the result.
#!/usr/bin/python
import requests
from StringIO import StringIO
from PIL import Image
import profile
def testRequest():
image_name = 'test1.jpg'
url = 'http://example.com/image.jpg'
r = requests.get(url, stream=True)
with open(image_name, 'wb') as f:
for chunk in r.iter_content():
f.write(chunk)
def testRequest2():
image_name = 'test2.jpg'
url = 'http://example.com/image.jpg'
r = requests.get(url)
i = Image.open(StringIO(r.content))
i.save(image_name)
if __name__ == '__main__':
profile.run('testUrllib()')
profile.run('testUrllib2()')
profile.run('testRequest()')
The result for testRequest:
343080 function calls (343068 primitive calls) in 2.580 seconds
And the result for testRequest2:
3129 function calls (3105 primitive calls) in 0.024 seconds
This might be easier than using requests. This is the only time I'll ever suggest not using requests to do HTTP stuff.
Two liner using urllib:
>>> import urllib
>>> urllib.request.urlretrieve("http://www.example.com/songs/mp3.mp3", "mp3.mp3")
There is also a nice Python module named wget that is pretty easy to use. Found here.
This demonstrates the simplicity of the design:
>>> import wget
>>> url = 'http://www.futurecrew.com/skaven/song_files/mp3/razorback.mp3'
>>> filename = wget.download(url)
100% [................................................] 3841532 / 3841532>
>> filename
'razorback.mp3'
Enjoy.
Edit: You can also add an out parameter to specify a path.
>>> out_filepath = <output_filepath>
>>> filename = wget.download(url, out=out_filepath)
Following code snippet downloads a file.
The file is saved with its filename as in specified url.
import requests
url = "http://example.com/image.jpg"
filename = url.split("/")[-1]
r = requests.get(url, timeout=0.5)
if r.status_code == 200:
with open(filename, 'wb') as f:
f.write(r.content)
There are 2 main ways:
Using .content (simplest/official) (see Zhenyi Zhang's answer):
import io # Note: io.BytesIO is StringIO.StringIO on Python2.
import requests
r = requests.get('http://lorempixel.com/400/200')
r.raise_for_status()
with io.BytesIO(r.content) as f:
with Image.open(f) as img:
img.show()
Using .raw (see Martijn Pieters's answer):
import requests
r = requests.get('http://lorempixel.com/400/200', stream=True)
r.raise_for_status()
r.raw.decode_content = True # Required to decompress gzip/deflate compressed responses.
with PIL.Image.open(r.raw) as img:
img.show()
r.close() # Safety when stream=True ensure the connection is released.
Timing both shows no noticeable difference.
As easy as to import Image and requests
from PIL import Image
import requests
img = Image.open(requests.get(url, stream = True).raw)
img.save('img1.jpg')
This is how I did it
import requests
from PIL import Image
from io import BytesIO
url = 'your_url'
files = {'file': ("C:/Users/shadow/Downloads/black.jpeg", open('C:/Users/shadow/Downloads/black.jpeg', 'rb'),'image/jpg')}
response = requests.post(url, files=files)
img = Image.open(BytesIO(response.content))
img.show()
Here is a more user-friendly answer that still uses streaming.
Just define these functions and call getImage(). It will use the same file name as the url and write to the current directory by default, but both can be changed.
import requests
from StringIO import StringIO
from PIL import Image
def createFilename(url, name, folder):
dotSplit = url.split('.')
if name == None:
# use the same as the url
slashSplit = dotSplit[-2].split('/')
name = slashSplit[-1]
ext = dotSplit[-1]
file = '{}{}.{}'.format(folder, name, ext)
return file
def getImage(url, name=None, folder='./'):
file = createFilename(url, name, folder)
with open(file, 'wb') as f:
r = requests.get(url, stream=True)
for block in r.iter_content(1024):
if not block:
break
f.write(block)
def getImageFast(url, name=None, folder='./'):
file = createFilename(url, name, folder)
r = requests.get(url)
i = Image.open(StringIO(r.content))
i.save(file)
if __name__ == '__main__':
# Uses Less Memory
getImage('http://www.example.com/image.jpg')
# Faster
getImageFast('http://www.example.com/image.jpg')
The request guts of getImage() are based on the answer here and the guts of getImageFast() are based on the answer above.
I'm going to post an answer as I don't have enough rep to make a comment, but with wget as posted by Blairg23, you can also provide an out parameter for the path.
wget.download(url, out=path)
This is the first response that comes up for google searches on how to download a binary file with requests. In case you need to download an arbitrary file with requests, you can use:
import requests
url = 'https://s3.amazonaws.com/lab-data-collections/GoogleNews-vectors-negative300.bin.gz'
open('GoogleNews-vectors-negative300.bin.gz', 'wb').write(requests.get(url, allow_redirects=True).content)
my approach was to use response.content (blob) and save to the file in binary mode
img_blob = requests.get(url, timeout=5).content
with open(destination + '/' + title, 'wb') as img_file:
img_file.write(img_blob)
Check out my python project that downloads images from unsplash.com based on keywords.
You can do something like this:
import requests
import random
url = "https://images.pexels.com/photos/1308881/pexels-photo-1308881.jpeg? auto=compress&cs=tinysrgb&dpr=1&w=500"
name=random.randrange(1,1000)
filename=str(name)+".jpg"
response = requests.get(url)
if response.status_code.ok:
with open(filename,'w') as f:
f.write(response.content)
Agree with Blairg23 that using urllib.request.urlretrieve is one of the easiest solutions.
One note I want to point out here. Sometimes it won't download anything because the request was sent via script (bot), and if you want to parse images from Google images or other search engines, you need to pass user-agent to request headers first, and then download the image, otherwise, the request will be blocked and it will throw an error.
Pass user-agent and download image:
opener=urllib.request.build_opener()
opener.addheaders=[('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.19582')]
urllib.request.install_opener(opener)
urllib.request.urlretrieve(URL, 'image_name.jpg')
Code in the online IDE that scrapes and downloads images from Google images using requests, bs4, urllib.requests.
Alternatively, if your goal is to scrape images from search engines like Google, Bing, Yahoo!, DuckDuckGo (and other search engines), then you can use SerpApi. It's a paid API with a free plan.
The biggest difference is that there's no need to figure out how to bypass blocks from search engines or how to extract certain parts from the HTML or JavaScript since it's already done for the end-user.
Example code to integrate:
import os, urllib.request
from serpapi import GoogleSearch
params = {
"api_key": os.getenv("API_KEY"),
"engine": "google",
"q": "pexels cat",
"tbm": "isch"
}
search = GoogleSearch(params)
results = search.get_dict()
print(json.dumps(results['images_results'], indent=2, ensure_ascii=False))
# download images
for index, image in enumerate(results['images_results']):
# print(f'Downloading {index} image...')
opener=urllib.request.build_opener()
opener.addheaders=[('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.19582')]
urllib.request.install_opener(opener)
# saves original res image to the SerpApi_Images folder and add index to the end of file name
urllib.request.urlretrieve(image['original'], f'SerpApi_Images/original_size_img_{index}.jpg')
-----------
'''
]
# other images
{
"position": 100, # 100 image
"thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQK62dIkDjNCvEgmGU6GGFZcpVWwX-p3FsYSg&usqp=CAU",
"source": "homewardboundnj.org",
"title": "pexels-helena-lopes-1931367 - Homeward Bound Pet Adoption Center",
"link": "https://homewardboundnj.org/upcoming-event/black-cat-appreciation-day/pexels-helena-lopes-1931367/",
"original": "https://homewardboundnj.org/wp-content/uploads/2020/07/pexels-helena-lopes-1931367.jpg",
"is_product": false
}
]
'''
Disclaimer, I work for SerpApi.
Here is a very simple code
import requests
response = requests.get("https://i.imgur.com/ExdKOOz.png") ## Making a variable to get image.
file = open("sample_image.png", "wb") ## Creates the file for image
file.write(response.content) ## Saves file content
file.close()
for download Image
import requests
Picture_request = requests.get(url)
Related
I am trying to fetch the data of a pdf file available online
I have tried
import requests
response = requests.get("http://imdagrimet.gov.in/sites/default/files/daas_bulletin/District%20Advisory%20patna_17.pdf")
print(response.content)
but it gives a byte object as a response, and I am not able to decode that
You should write the data inside a file in order to be able to get it.
Like this:
with open('/District_Advisory_patna_17.pdf', 'wb') as f:
f.write(response.content)
Try to write your data to file:
import requests
import shutil
url = 'your url'
r = requests.get(url, stream=True)
if r.status_code == 200:
with open(file_path, 'wb') as f:
r.raw.decode_content = True
shutil.copyfileobj(r.raw, f)
I have an existing url of an image,
I want to download the image straight to a variable (no need to actually download it, maybe get it from a response?
The end result will be "download an image into a BytesIO() variable".
What is the correct way to do so?
You can use requests:
import requests
from io import BytesIO
response = requests.get(url)
image_data = BytesIO(response.content)
Note this works in Python 3.X
You could also just duck-type the underlying urllib3 response object, which is for many practical purposes the same interface as a BytesIO anyway.
Example using the PNG of your identicon:
>>> url = "https://www.gravatar.com/avatar/33f6d36c91913f4b6776525a09d131d0?s=32&d=identicon&r=PG&f=1"
>>> resp = requests.get(url, stream=True)
>>> resp.raw
<urllib3.response.HTTPResponse at 0x7fffe88927b8>
>>> resp.raw.read()
b'\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00 \x00\x00\x00 \x08\x06\x00\x00\x00szz\xf4\x00\x00\x00\tpHYs\x00\x00\x0e\xc4\x00\x00\x0e\xc4\x01\x95+\x0e\x1b\x00\x00\x00\xf6IDATX\x85\xedW1\x12\xc20\x0c\x93\xb9\x0em\xc3\xeb\x98)3?b\x87\x9d\xcf\xd1\xa4[\xcd\x06\xd89bz\xe50C\xb4\xe5\xda\xaa\xba\xc8Qlbf\xc6\x0b\xd2.\xa1\x84\xfe\xda\x17\x9f\xa7!\x01\xf1\xfd\xf3\xee\xdc\x81\xb6\xf4Xo\x8al?#\x15\xd0h\xcf\xdbS\x0b\nO\x8f^\xfd\x02\x80\xe98\x81\xa3(\x1b\x81\xfe"k\x84G\xf9\xeet\x98\xa4\x00M#\x81\xb2\x9f\n\xc2\xc8\xc5"\xcb\xf8\n\\\xc0\x1fX\xe0. \xb7\xc0\xd82\xed\xf1b\x04\x08\x0b\xddw\xa0\n }\x17\xe8s\xbe\xd6\xf34\xc8\x9c\xd1|Y\x11.=\xe7&\x0c.w\x0b\xaa\x80*\xc0]\x00\xc5\xbd\xbc\xdcWg\xbd\x01\x9d3\xcdW\xcf\xfc\x07\xd09\xe3n\x81\xbb\x80<\x8aG.\xf6\x04V\xdfo\xcd\r\xfa[\xf7\x1d\xa8\x02h\xbe\xcd\xb2\x1fP};\x82\\Z9\x91\xcd\r\xcas=w4V\x13\xba4\'\xac~B\xcf\x1d\xee\x16\xb8\x0b\xb8\x03\x91\x99Z?\x1eYA8\x00\x00\x00\x00IEND\xaeB`\x82'
I am trying to download a PDF file from a website and save it to disk. My attempts either fail with encoding errors or result in blank PDFs.
In [1]: import requests
In [2]: url = 'http://www.hrecos.org//images/Data/forweb/HRTVBSH.Metadata.pdf'
In [3]: response = requests.get(url)
In [4]: with open('/tmp/metadata.pdf', 'wb') as f:
...: f.write(response.text)
---------------------------------------------------------------------------
UnicodeEncodeError Traceback (most recent call last)
<ipython-input-4-4be915a4f032> in <module>()
1 with open('/tmp/metadata.pdf', 'wb') as f:
----> 2 f.write(response.text)
3
UnicodeEncodeError: 'ascii' codec can't encode characters in position 11-14: ordinal not in range(128)
In [5]: import codecs
In [6]: with codecs.open('/tmp/metadata.pdf', 'wb', encoding='utf8') as f:
...: f.write(response.text)
...:
I know it is a codec problem of some kind but I can't seem to get it to work.
You should use response.content in this case:
with open('/tmp/metadata.pdf', 'wb') as f:
f.write(response.content)
From the document:
You can also access the response body as bytes, for non-text requests:
>>> r.content
b'[{"repository":{"open_issues":0,"url":"https://github.com/...
So that means: response.text return the output as a string object, use it when you're downloading a text file. Such as HTML file, etc.
And response.content return the output as bytes object, use it when you're downloading a binary file. Such as PDF file, audio file, image, etc.
You can also use response.raw instead. However, use it when the file which you're about to download is large. Below is a basic example which you can also find in the document:
import requests
url = 'http://www.hrecos.org//images/Data/forweb/HRTVBSH.Metadata.pdf'
r = requests.get(url, stream=True)
with open('/tmp/metadata.pdf', 'wb') as fd:
for chunk in r.iter_content(chunk_size):
fd.write(chunk)
chunk_size is the chunk size which you want to use. If you set it as 2000, then requests will download that file the first 2000 bytes, write them into the file, and do this again, again and again, unless it finished.
So this can save your RAM. But I'd prefer use response.content instead in this case since your file is small. As you can see use response.raw is complex.
Relates:
How to download large file in python with requests.py?
How to download image using requests
In Python 3, I find pathlib is the easiest way to do this. Request's response.content marries up nicely with pathlib's write_bytes.
from pathlib import Path
import requests
filename = Path('metadata.pdf')
url = 'http://www.hrecos.org//images/Data/forweb/HRTVBSH.Metadata.pdf'
response = requests.get(url)
filename.write_bytes(response.content)
You can use urllib:
import urllib.request
urllib.request.urlretrieve(url, "filename.pdf")
Please note I'm a beginner. If My solution is wrong, please feel free to correct and/or let me know. I may learn something new too.
My solution:
Change the downloadPath accordingly to where you want your file to be saved. Feel free to use the absolute path too for your usage.
Save the below as downloadFile.py.
Usage: python downloadFile.py url-of-the-file-to-download new-file-name.extension
Remember to add an extension!
Example usage: python downloadFile.py http://www.google.co.uk google.html
import requests
import sys
import os
def downloadFile(url, fileName):
with open(fileName, "wb") as file:
response = requests.get(url)
file.write(response.content)
scriptPath = sys.path[0]
downloadPath = os.path.join(scriptPath, '../Downloads/')
url = sys.argv[1]
fileName = sys.argv[2]
print('path of the script: ' + scriptPath)
print('downloading file to: ' + downloadPath)
downloadFile(url, downloadPath + fileName)
print('file downloaded...')
print('exiting program...')
Generally, this should work in Python3:
import urllib.request
..
urllib.request.get(url)
Remember that urllib and urllib2 don't work properly after Python2.
If in some mysterious cases requests don't work (happened with me), you can also try using
wget.download(url)
Related:
Here's a decent explanation/solution to find and download all pdf files on a webpage:
https://medium.com/#dementorwriter/notesdownloader-use-web-scraping-to-download-all-pdfs-with-python-511ea9f55e48
regarding Kevin answer to write in a folder tmp, it should be like this:
with open('./tmp/metadata.pdf', 'wb') as f:
f.write(response.content)
he forgot . before the address and of-course your folder tmp should have been created already
So I'm trying to make a Python script that downloads webcomics and puts them in a folder on my desktop. I've found a few similar programs on here that do something similar, but nothing quite like what I need. The one that I found most similar is right here (http://bytes.com/topic/python/answers/850927-problem-using-urllib-download-images). I tried using this code:
>>> import urllib
>>> image = urllib.URLopener()
>>> image.retrieve("http://www.gunnerkrigg.com//comics/00000001.jpg","00000001.jpg")
('00000001.jpg', <httplib.HTTPMessage instance at 0x1457a80>)
I then searched my computer for a file "00000001.jpg", but all I found was the cached picture of it. I'm not even sure it saved the file to my computer. Once I understand how to get the file downloaded, I think I know how to handle the rest. Essentially just use a for loop and split the string at the '00000000'.'jpg' and increment the '00000000' up to the largest number, which I would have to somehow determine. Any reccomendations on the best way to do this or how to download the file correctly?
Thanks!
EDIT 6/15/10
Here is the completed script, it saves the files to any directory you choose. For some odd reason, the files weren't downloading and they just did. Any suggestions on how to clean it up would be much appreciated. I'm currently working out how to find out many comics exist on the site so I can get just the latest one, rather than having the program quit after a certain number of exceptions are raised.
import urllib
import os
comicCounter=len(os.listdir('/file'))+1 # reads the number of files in the folder to start downloading at the next comic
errorCount=0
def download_comic(url,comicName):
"""
download a comic in the form of
url = http://www.example.com
comicName = '00000000.jpg'
"""
image=urllib.URLopener()
image.retrieve(url,comicName) # download comicName at URL
while comicCounter <= 1000: # not the most elegant solution
os.chdir('/file') # set where files download to
try:
if comicCounter < 10: # needed to break into 10^n segments because comic names are a set of zeros followed by a number
comicNumber=str('0000000'+str(comicCounter)) # string containing the eight digit comic number
comicName=str(comicNumber+".jpg") # string containing the file name
url=str("http://www.gunnerkrigg.com//comics/"+comicName) # creates the URL for the comic
comicCounter+=1 # increments the comic counter to go to the next comic, must be before the download in case the download raises an exception
download_comic(url,comicName) # uses the function defined above to download the comic
print url
if 10 <= comicCounter < 100:
comicNumber=str('000000'+str(comicCounter))
comicName=str(comicNumber+".jpg")
url=str("http://www.gunnerkrigg.com//comics/"+comicName)
comicCounter+=1
download_comic(url,comicName)
print url
if 100 <= comicCounter < 1000:
comicNumber=str('00000'+str(comicCounter))
comicName=str(comicNumber+".jpg")
url=str("http://www.gunnerkrigg.com//comics/"+comicName)
comicCounter+=1
download_comic(url,comicName)
print url
else: # quit the program if any number outside this range shows up
quit
except IOError: # urllib raises an IOError for a 404 error, when the comic doesn't exist
errorCount+=1 # add one to the error count
if errorCount>3: # if more than three errors occur during downloading, quit the program
break
else:
print str("comic"+ ' ' + str(comicCounter) + ' ' + "does not exist") # otherwise say that the certain comic number doesn't exist
print "all comics are up to date" # prints if all comics are downloaded
Python 2
Using urllib.urlretrieve
import urllib
urllib.urlretrieve("http://www.gunnerkrigg.com//comics/00000001.jpg", "00000001.jpg")
Python 3
Using urllib.request.urlretrieve (part of Python 3's legacy interface, works exactly the same)
import urllib.request
urllib.request.urlretrieve("http://www.gunnerkrigg.com//comics/00000001.jpg", "00000001.jpg")
Python 2:
import urllib
f = open('00000001.jpg','wb')
f.write(urllib.urlopen('http://www.gunnerkrigg.com//comics/00000001.jpg').read())
f.close()
Python 3:
import urllib.request
f = open('00000001.jpg','wb')
f.write(urllib.request.urlopen('http://www.gunnerkrigg.com//comics/00000001.jpg').read())
f.close()
Just for the record, using requests library.
import requests
f = open('00000001.jpg','wb')
f.write(requests.get('http://www.gunnerkrigg.com//comics/00000001.jpg').content)
f.close()
Though it should check for requests.get() error.
For Python 3 you will need to import import urllib.request:
import urllib.request
urllib.request.urlretrieve(url, filename)
for more info check out the link
Python 3 version of #DiGMi's answer:
from urllib import request
f = open('00000001.jpg', 'wb')
f.write(request.urlopen("http://www.gunnerkrigg.com/comics/00000001.jpg").read())
f.close()
I have found this answer and I edit that in more reliable way
def download_photo(self, img_url, filename):
try:
image_on_web = urllib.urlopen(img_url)
if image_on_web.headers.maintype == 'image':
buf = image_on_web.read()
path = os.getcwd() + DOWNLOADED_IMAGE_PATH
file_path = "%s%s" % (path, filename)
downloaded_image = file(file_path, "wb")
downloaded_image.write(buf)
downloaded_image.close()
image_on_web.close()
else:
return False
except:
return False
return True
From this you never get any other resources or exceptions while downloading.
It's easiest to just use .read() to read the partial or entire response, then write it into a file you've opened in a known good location.
If you know that the files are located in the same directory dir of the website site and have the following format: filename_01.jpg, ..., filename_10.jpg then download all of them:
import requests
for x in range(1, 10):
str1 = 'filename_%2.2d.jpg' % (x)
str2 = 'http://site/dir/filename_%2.2d.jpg' % (x)
f = open(str1, 'wb')
f.write(requests.get(str2).content)
f.close()
Maybe you need 'User-Agent':
import urllib2
opener = urllib2.build_opener()
opener.addheaders = [('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.137 Safari/537.36')]
response = opener.open('http://google.com')
htmlData = response.read()
f = open('file.txt','w')
f.write(htmlData )
f.close()
Using urllib, you can get this done instantly.
import urllib.request
opener=urllib.request.build_opener()
opener.addheaders=[('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1941.0 Safari/537.36')]
urllib.request.install_opener(opener)
urllib.request.urlretrieve(URL, "images/0.jpg")
Aside from suggesting you read the docs for retrieve() carefully (http://docs.python.org/library/urllib.html#urllib.URLopener.retrieve), I would suggest actually calling read() on the content of the response, and then saving it into a file of your choosing rather than leaving it in the temporary file that retrieve creates.
All the above codes, do not allow to preserve the original image name, which sometimes is required.
This will help in saving the images to your local drive, preserving the original image name
IMAGE = URL.rsplit('/',1)[1]
urllib.urlretrieve(URL, IMAGE)
Try this for more details.
This worked for me using python 3.
It gets a list of URLs from the csv file and starts downloading them into a folder. In case the content or image does not exist it takes that exception and continues making its magic.
import urllib.request
import csv
import os
errorCount=0
file_list = "/Users/$USER/Desktop/YOUR-FILE-TO-DOWNLOAD-IMAGES/image_{0}.jpg"
# CSV file must separate by commas
# urls.csv is set to your current working directory make sure your cd into or add the corresponding path
with open ('urls.csv') as images:
images = csv.reader(images)
img_count = 1
print("Please Wait.. it will take some time")
for image in images:
try:
urllib.request.urlretrieve(image[0],
file_list.format(img_count))
img_count += 1
except IOError:
errorCount+=1
# Stop in case you reach 100 errors downloading images
if errorCount>100:
break
else:
print ("File does not exist")
print ("Done!")
A simpler solution may be(python 3):
import urllib.request
import os
os.chdir("D:\\comic") #your path
i=1;
s="00000000"
while i<1000:
try:
urllib.request.urlretrieve("http://www.gunnerkrigg.com//comics/"+ s[:8-len(str(i))]+ str(i)+".jpg",str(i)+".jpg")
except:
print("not possible" + str(i))
i+=1;
According to urllib.request.urlretrieve — Python 3.9.2 documentation, The function is ported from the Python 2 module urllib (as opposed to urllib2). It might become deprecated at some point in the future.
Because of this, it might be better to use requests.get(url, params=None, **kwargs). Here is a MWE.
import requests
url = 'http://example.com/example.jpg'
response = requests.get(url)
with open(filename, "wb") as f:
f.write(response.content)
Refer to Downlolad Google’s WebP Images via Take Screenshots with Selenium WebDriver.
What about this:
import urllib, os
def from_url( url, filename = None ):
'''Store the url content to filename'''
if not filename:
filename = os.path.basename( os.path.realpath(url) )
req = urllib.request.Request( url )
try:
response = urllib.request.urlopen( req )
except urllib.error.URLError as e:
if hasattr( e, 'reason' ):
print( 'Fail in reaching the server -> ', e.reason )
return False
elif hasattr( e, 'code' ):
print( 'The server couldn\'t fulfill the request -> ', e.code )
return False
else:
with open( filename, 'wb' ) as fo:
fo.write( response.read() )
print( 'Url saved as %s' % filename )
return True
##
def main():
test_url = 'http://cdn.sstatic.net/stackoverflow/img/favicon.ico'
from_url( test_url )
if __name__ == '__main__':
main()
If you need proxy support you can do this:
if needProxy == False:
returnCode, urlReturnResponse = urllib.urlretrieve( myUrl, fullJpegPathAndName )
else:
proxy_support = urllib2.ProxyHandler({"https":myHttpProxyAddress})
opener = urllib2.build_opener(proxy_support)
urllib2.install_opener(opener)
urlReader = urllib2.urlopen( myUrl ).read()
with open( fullJpegPathAndName, "w" ) as f:
f.write( urlReader )
Another way to do this is via the fastai library. This worked like a charm for me. I was facing a SSL: CERTIFICATE_VERIFY_FAILED Error using urlretrieve so I tried that.
url = 'https://www.linkdoesntexist.com/lennon.jpg'
fastai.core.download_url(url,'image1.jpg', show_progress=False)
Using requests
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)
if __name__ == '__main__':
ImageDl(url)
And if you want to download images similar to the website directory structure, you can do this:
result_path = './result/'
soup = BeautifulSoup(self.file, 'css.parser')
for image in soup.findAll("img"):
image["name"] = image["src"].split("/")[-1]
image['path'] = image["src"].replace(image["name"], '')
os.makedirs(result_path + image['path'], exist_ok=True)
if image["src"].lower().startswith("http"):
urlretrieve(image["src"], result_path + image["src"][1:])
else:
urlretrieve(url + image["src"], result_path + image["src"][1:])
I know the URL of an image on Internet.
e.g. http://www.digimouth.com/news/media/2011/09/google-logo.jpg, which contains the logo of Google.
Now, how can I download this image using Python without actually opening the URL in a browser and saving the file manually.
Python 2
Here is a more straightforward way if all you want to do is save it as a file:
import urllib
urllib.urlretrieve("http://www.digimouth.com/news/media/2011/09/google-logo.jpg", "local-filename.jpg")
The second argument is the local path where the file should be saved.
Python 3
As SergO suggested the code below should work with Python 3.
import urllib.request
urllib.request.urlretrieve("http://www.digimouth.com/news/media/2011/09/google-logo.jpg", "local-filename.jpg")
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 will contain your image.
I wrote a script that does just this, and it is available on my github for your use.
I utilized BeautifulSoup to allow me to parse any website for images. If you will be doing much web scraping (or intend to use my tool) I suggest you sudo pip install BeautifulSoup. Information on BeautifulSoup is available here.
For convenience here is my code:
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')
This can be done with requests. Load the page and dump the binary content to a file.
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)
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
I made a script expanding on Yup.'s script. I fixed some things. It will now bypass 403:Forbidden problems. It wont crash when an image fails to be retrieved. It tries to avoid corrupted previews. It gets the right absolute urls. It gives out more information. It can be run with an argument from the command line.
# 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)
A solution which works with Python 2 and Python 3:
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")
or, if the additional requirement of requests is acceptable and if it is a http(s) URL:
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)
Using requests library
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)
Use a simple python wget module to download the link. Usage below:
import wget
wget.download('http://www.digimouth.com/news/media/2011/09/google-logo.jpg')
This is very short answer.
import urllib
urllib.urlretrieve("http://photogallery.sandesh.com/Picture.aspx?AlubumId=422040", "Abc.jpg")
Version for Python 3
I adjusted the code of #madprops for Python 3
# 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')
Late answer, but for python>=3.6 you can use dload, i.e.:
import dload
dload.save("http://www.digimouth.com/news/media/2011/09/google-logo.jpg")
if you need the image as bytes, use:
img_bytes = dload.bytes("http://www.digimouth.com/news/media/2011/09/google-logo.jpg")
install using pip3 install dload
Something fresh for Python 3 using Requests:
Comments in the code. Ready to use function.
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")
this is the easiest method to download images.
import requests
from slugify import slugify
img_url = 'https://apod.nasa.gov/apod/image/1701/potw1636aN159_HST_2048.jpg'
img = requests.get(img_url).content
img_file = open(slugify(img_url) + '.' + str(img_url).split('.')[-1], 'wb')
img_file.write(img)
img_file.close()
If you don't already have the url for the image, you could scrape it with gazpacho:
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")]
And then download the asset with urllib as mentioned:
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}")
# import the required libraries from Python
import pathlib,urllib.request
# Using pathlib, specify where the image is to be saved
downloads_path = str(pathlib.Path.home() / "Downloads")
# Form a full image path by joining the path to the
# images' new name
picture_path = os.path.join(downloads_path, "new-image.png")
# "/home/User/Downloads/new-image.png"
# Using "urlretrieve()" from urllib.request save the image
urllib.request.urlretrieve("//example.com/image.png", picture_path)
# urlretrieve() takes in 2 arguments
# 1. The URL of the image to be downloaded
# 2. The image new name after download. By default, the image is saved
# inside your current working directory
Ok, so, this is my rudimentary attempt, and probably total overkill.
Update if needed, as this doesn't handle any timeouts, but, I got this working for fun.
Code listed here: https://github.com/JayRizzo/JayRizzoTools/blob/master/pyImageDownloader.py
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# =============================================================================
# Created Syst: MAC OSX High Sierra 21.5.0 (17G65)
# Created Plat: Python 3.9.5 ('v3.9.5:0a7dcbdb13', 'May 3 2021 13:17:02')
# Created By : Jeromie Kirchoff
# Created Date: Thu Jun 15 23:31:01 2022 CDT
# Last ModDate: Thu Jun 16 01:41:01 2022 CDT
# =============================================================================
# NOTE: Doesn't work on SVG images at this time.
# I will look into this further: https://stackoverflow.com/a/6599172/1896134
# =============================================================================
import requests # to get image from the web
import shutil # to save it locally
import os # needed
from os.path import exists as filepathexist # check if file paths exist
from os.path import join # joins path for different os
from os.path import expanduser # expands current home
from pyuser_agent import UA # generates random UserAgent
class ImageDownloader(object):
"""URL ImageDownloader.
Input : Full Image URL
Output: Image saved to your ~/Pictures/JayRizzoDL folder.
"""
def __init__(self, URL: str):
self.url = URL
self.headers = {"User-Agent" : UA().random}
self.currentHome = expanduser('~')
self.desktop = join(self.currentHome + "/Desktop/")
self.download = join(self.currentHome + "/Downloads/")
self.pictures = join(self.currentHome + "/Pictures/JayRizzoDL/")
self.outfile = ""
self.filename = ""
self.response = ""
self.rawstream = ""
self.createdfilepath = ""
self.imgFileName = ""
# Check if the JayRizzoDL exists in the pictures folder.
# if it doesn't exist create it.
if not filepathexist(self.pictures):
os.mkdir(self.pictures)
self.main()
def getFileNameFromURL(self, URL: str):
"""Parse the URL for the name after the last forward slash."""
NewFileName = self.url.strip().split('/')[-1].strip()
return NewFileName
def getResponse(self, URL: str):
"""Try streaming the URL for the raw data."""
self.response = requests.get(self.url, headers=self.headers, stream=True)
return self.response
def gocreateFile(self, name: str, response):
"""Try creating the file with the raw data in a custom folder."""
self.outfile = join(self.pictures, name)
with open(self.outfile, 'wb') as outFilePath:
shutil.copyfileobj(response.raw, outFilePath)
return self.outfile
def main(self):
"""Combine Everything and use in for loops."""
self.filename = self.getFileNameFromURL(self.url)
self.rawstream = self.getResponse(self.url)
self.createdfilepath = self.gocreateFile(self.filename, self.rawstream)
print(f"File was created: {self.createdfilepath}")
return
if __name__ == '__main__':
# Example when calling the file directly.
ImageDownloader("https://stackoverflow.design/assets/img/logos/so/logo-stackoverflow.png")
Download Image file, with avoiding all possible error:
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)