Sandra 5 years ago
commit 61b4fe977e

1
.gitignore vendored

@ -18,3 +18,4 @@ __pycache__/
*.jpg *.jpg
*.jpeg *.jpeg
secrets.py secrets.py
archive/*

@ -0,0 +1,26 @@
import os, argparse, sys, re, json
from mwclient import (Site,
errors)
# API CALL
# https://hub.xpub.nl/sandbox/itchwiki/api.php?action=smwbrowse&browse=pvalue&params={ "limit": 1500, "offset": 0, "property" : "Title", "search": "" }&format=json
# generated orgs.json
# login
site = Site(host='hub.xpub.nl/sandbox', path='/itchwiki/')
wd =os.path.dirname(os.path.abspath(__file__)) # parent working directory
with open(os.path.join(wd, 'login.txt'), 'r') as login: # read login user & pwd
loginlines = login.read()
user, pwd = loginlines.split('\n')
site.login(username=user, password=pwd) # login to wiki
with open('titles.json', 'r') as f:
titles = json.load(f)
for pagename in titles['query']:
page = site.pages[pagename]
if not page.text(): # if page has no text
print(pagename)
page.save('{{Publication}}\n[[Category:Title]]')

@ -0,0 +1,33 @@
import os, argparse, sys, re, json
from mwclient import (Site,
errors)
# API CALL
# https://hub.xpub.nl/sandbox/itchwiki/api.php?action=smwbrowse&browse=pvalue&params={ "limit": 1500, "offset": 0, "property" : "Title", "search": "" }&format=json
# generated orgs.json
# >>> result = site.api('query', prop='coordinates', titles='Oslo|Copenhagen')
# login
site = Site(host='hub.xpub.nl/sandbox', path='/itchwiki/')
wd =os.path.dirname(os.path.abspath(__file__)) # parent working directory
with open(os.path.join(wd, 'login.txt'), 'r') as login: # read login user & pwd
loginlines = login.read()
user, pwd = loginlines.split('\n')
site.login(username=user, password=pwd) # login to wiki
# To query a large number of ite:
for i in range(0, 1500, 100):
# variable i will increase 100 at each iteration
# between 0 and 1400
# and will make the offset parameter change
print('\n', f'Querying from {i} to {i+100}', '\n')
ask_query = f'[[Category:Title]]|format=json|limit=100|offset={i}'
response = site.api(action='ask', query=ask_query)
for pagetitle in response['query']['results']:
print(pagetitle)
page = site.pages[pagetitle]
# # text = page.text()
page.save('{{Publication}}\n[[Category:Title]]')

File diff suppressed because one or more lines are too long
Loading…
Cancel
Save