prototyping-times/mediawiki-api-download-images.ipynb

Mediawiki API Download Images¶

In [ ]:

In [ ]:

# Let's first test it with one image.
# For example: File:Debo 009 05 01.jpg

filename = 'Debo 009 05 01.jpg'
filename = filename.replace(' ', '_') # let's replace spaces again with _
filename = filename.replace('.jpg', '') # and let's remove the file extension

In [ ]:

In [ ]:

# We cannot ask the API for the URL of a specific image (:///), but we can still find it using the "aifrom=" parameter.
# Note: ai=allimages
url = f'https://pzwiki.wdka.nl/mw-mediadesign/api.php?action=query&list=allimages&aifrom={ filename }&format=json'
response = urllib.request.urlopen(url).read()
data = json.loads(response)
JSON(data)

In [ ]:

In [ ]:

# Select the first result [0], let's assume that that is always the right image that we need :)
image = data['query']['allimages'][0]

In [ ]:

In [ ]:

print(image)

In [ ]:

print(image['url'])

In [ ]:

Now we can use this URL to download the images!

In [ ]:

image_url = image['url']
image_filename = image['name']
image_response = urllib.request.urlopen(image_url).read() # We use urllib for this again, this is basically our tool to download things from the web !

In [ ]:

In [ ]:

print(image_response)

In [ ]:

out = open(image_filename, 'wb') # 'wb' stands for 'write bytes', we basically ask this file to accept data in byte format
out.write(image_response)
out.close()

In [ ]:

Download all the images of our page¶

In [ ]:

# We have our variable "images"
print(images)

In [ ]:

# Let's loop through this list and download each image!
for filename in images:
    print('Downloading:', filename)
    
    filename = filename.replace(' ', '_') # let's replace spaces again with _
    filename = filename.replace('.jpg', '').replace('.gif', '').replace('.png','').replace('.jpeg','').replace('.JPG','').replace('.JPEG','') # and let's remove the file extension
    
    # first we search for the full URL of the image
    url = f'https://pzwiki.wdka.nl/mw-mediadesign/api.php?action=query&list=allimages&aifrom={ filename }&format=json'
    response = urllib.request.urlopen(url).read()
    data = json.loads(response)
    image = data['query']['allimages'][0]
    
    # then we download the image
    image_url = image['url']
    image_filename = image['name']
    image_response = urllib.request.urlopen(image_url).read()
    
    # and we save it as a file
    out = open(image_filename, 'wb') 
    out.write(image_response)
    out.close()

In [ ]:

In [ ]:

In [ ]:

In [ ]: