from urllib import request
import json
import requests
import mwclient
import os
import urllib.parse
data=request.urlopen('https://pzwiki.wdka.nl/mw-mediadesign/api.php?action=parse&page=User:FLEM/Notebook&format=json').read()
print(data)
json_data=json.loads(data)
print(json_data)
title=json_data['parse']['title']
print(title)
images=json_data['parse']['images']
print(images)
#['Inside_overview_(1).gif', 'Inside_overview_(2).gif', 'Inside_pocket.gif', 'Opened.jpeg', 'Outside_cover.jpeg', 'Paper_selection.jpeg', 'Side_view.jpeg', 'Inuse.jpg', 'Multicolumnednotebook_.jpg', 'Multicolumnednotebook_(1).jpg', 'Multicolumnednotebook_(2).jpg', 'Archive_01.jpg', 'Concertina2.jpg', 'Concertina1.jpg', 'Metalring5.jpg', 'Metalring6.jpg', 'Penholder.jpg', 'Paperfoldedupdate.jpg', 'Notesfrompellebyme3.jpg', 'M&Ms_results.jpg', 'Notebookworkflow_(8).jpg', 'Longletternotebook.jpg', 'Longletternotebooktext.jpg', 'Prototype.gif', 'First_notebook_kit.jpg', 'Annotation_scans_(1).jpg']
text=json_data['parse']['text']['*']
print(text)
for image in images:
#here we download images
S = requests.Session()
URL = "https://pzwiki.wdka.nl/mw-mediadesign/api.php"
#this is wrong, it gives me the images of all the media design instead of just one page
PARAMS = {
"action": "query",
"format": "json",
"list": "allimages",
"aifrom": image, #using variable from the list above
"ailimit": "1" #here i can say how many i want from the list
}
R = S.get(url=URL, params=PARAMS)
DATA = R.json()
IMAGES = DATA["query"]["allimages"]
for image in IMAGES:
imageurl = image["url"]
filename = image["title"].replace('File:', '').replace(' ', '_')
print(imageurl)
print(filename)
response = requests.get(imageurl)
#if response.status_code == 200: #what does this mean?
with open(filename, 'wb') as f: #what is f? why in the other one we used fd?
f.write(response.content)
html=text.split("\n")
new_html=""
for line in html:
for image in images:
image=urllib.parse.quote_plus(image)
#replace html img element
if image in line:
new=f"""