Skip to content

Add regex for removing distracting brackets #17

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
harikrishnatp wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Add regex for removing distracting brackets #17

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1c5423e
added regex for removing distracting brackets
harikrishnatp Jan 21, 2026
3631d67
Fix: fixed some bugs I found while testing
harikrishnatp Feb 5, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 23 additions & 6 deletions wikiquote_wikidata_matches.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
# import pip
import os
import json
import re
# pip.main(['list'])
import pywikibot
import mysql.connector
Expand Down Expand Up @@ -155,14 +156,30 @@
mydb.commit()
# exit()
continue

skip = 0
# no need to create tile if link already exists
try:
sitelink = candidate_item_dict['sitelinks'][myresult[3]+'wikiquote']
siteLink = candidate_item_dict['siteLinks'][myresult[3]+'wikiquote']
except:
#{"type": "files","files": files, "q":myresult[1],'deferred_decision':'yes'}
tile = {"id": myresult[0], "sections": [ {"type": "item", "q":myresult[1]}, {"type": "text","title": myresult[2],"url": 'https://'+myresult[3]+'.wikiquote.org/wiki/'+myresult[2].replace(' ','_'),'text':target.text[0:500]}], "controls": [{"type":"buttons", "entries":[{"type": "green","decision": "yes","label": "Match", "api_action": {'action': "wbsetsitelink", "id": myresult[1],"linksite": myresult[3]+'wikiquote',"linktitle": myresult[2]}}, {"type": "white", "decision": "skip", "label": "Skip"}, {"type": "blue", "decision": "no", "label": "No"}]}]}#'q:'+myresult[3]
# tile = {"id": myresult[0], "sections": [ {"type": "item", "q":myresult[1]}, {"type": "wikipage","title": myresult[2],"wiki": 'enwikiquote'}], "controls": [{"type":"buttons", "entries":[{"type": "green","decision": "yes","label": "Match", "api_action": {'action': "wbsetsitelink", "id": myresult[1],"linksite": myresult[3]+'wikiquote',"linktitle": myresult[2]}}, {"type": "white", "decision": "skip", "label": "Skip"}, {"type": "blue", "decision": "no", "label": "No"}]}]}#'q:'+myresult[3]
cleaned_text = target.text[0:500]
# for template calls {{..}}
cleaned_text = re.sub(r'\{\{[^}]*\}\}', '', cleaned_text)
# for [category:..] or other similar cases
cleaned_text = re.sub(r'\[\[(?:Category|Kategorie|Categoria)[^\]]*\]\]', '', cleaned_text, flags=re.IGNORECASE)
# for [file] or other similar
cleaned_text = re.sub(r'\[\[(?:File|Image|Datei|Fichier|Archivo|Imagem)[^\]]*\]\]', '', cleaned_text, flags=re.IGNORECASE)
# for __NOTOC__ and similar
cleaned_text = re.sub(r'__[A-Z]+__', '', cleaned_text)
# [w:Page|Display] to Display (interwiki links)
cleaned_text = re.sub(r'\[\[[wW]:[^|]+\|([^\]]+)\]\]', r'\1', cleaned_text)
# [w:Page|Display] to Display (piped links)
cleaned_text = re.sub(r'\[\[[^\]|]+\|([^\]]+)\]\]', r'\1', cleaned_text)
# simple links without pipes
cleaned_text = re.sub(r'\[\[([^\]|]+)\]\]', r'\1', cleaned_text)
# section headers
cleaned_text = re.sub(r'={2,}[^=]+={2,}', '', cleaned_text)
# extra whitespace
cleaned_text = re.sub(r'\s+', ' ', cleaned_text).strip()
tile = {"id": myresult[0], "sections": [ {"type": "item", "q":myresult[1]}, {"type": "text","title": myresult[2],"url": 'https://'+myresult[3]+'.wikiquote.org/wiki/'+myresult[2].replace(' ','_'),'text':cleaned_text}], "controls": [{"type":"buttons", "entries":[{"type": "green","decision": "yes","label": "Match", "api_action": {'action': "wbsetsitelink", "id": myresult[1],"linksite": myresult[3]+'wikiquote',"linktitle": myresult[2]}}, {"type": "white", "decision": "skip", "label": "Skip"}, {"type": "blue", "decision": "no", "label": "No"}]}]}#'q:'+myresult[3]
tiles.append(tile)
i += 1
if i >= int(num):
Expand Down