|
|
@ -3,6 +3,7 @@ import json
|
|
|
|
import requests
|
|
|
|
import requests
|
|
|
|
import mwclient
|
|
|
|
import mwclient
|
|
|
|
import os
|
|
|
|
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()
|
|
|
|
data=request.urlopen('https://pzwiki.wdka.nl/mw-mediadesign/api.php?action=parse&page=User:FLEM/Notebook&format=json').read()
|
|
|
|
print(data)
|
|
|
|
print(data)
|
|
|
@ -24,8 +25,8 @@ print(text)
|
|
|
|
|
|
|
|
|
|
|
|
for image in images:
|
|
|
|
for image in images:
|
|
|
|
|
|
|
|
|
|
|
|
here we download images
|
|
|
|
#here we download images
|
|
|
|
S = requests.Session()
|
|
|
|
S = requests.Session()
|
|
|
|
|
|
|
|
|
|
|
|
URL = "https://pzwiki.wdka.nl/mw-mediadesign/api.php"
|
|
|
|
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
|
|
|
|
#this is wrong, it gives me the images of all the media design instead of just one page
|
|
|
@ -46,7 +47,7 @@ for image in images:
|
|
|
|
|
|
|
|
|
|
|
|
for image in IMAGES:
|
|
|
|
for image in IMAGES:
|
|
|
|
imageurl = image["url"]
|
|
|
|
imageurl = image["url"]
|
|
|
|
filename = image["title"].replace('File:', '')
|
|
|
|
filename = image["title"].replace('File:', '').replace(' ', '_')
|
|
|
|
print(imageurl)
|
|
|
|
print(imageurl)
|
|
|
|
print(filename)
|
|
|
|
print(filename)
|
|
|
|
|
|
|
|
|
|
|
@ -61,6 +62,7 @@ html=text.split("\n")
|
|
|
|
new_html=""
|
|
|
|
new_html=""
|
|
|
|
for line in html:
|
|
|
|
for line in html:
|
|
|
|
for image in images:
|
|
|
|
for image in images:
|
|
|
|
|
|
|
|
image=urllib.parse.quote_plus(image)
|
|
|
|
#replace html img element
|
|
|
|
#replace html img element
|
|
|
|
if image in line:
|
|
|
|
if image in line:
|
|
|
|
new=f"""<div class="image"><img src="{image}"></div>"""
|
|
|
|
new=f"""<div class="image"><img src="{image}"></div>"""
|
|
|
|