| # List creation times for all files in a category | |
| from collections import Counter | |
| import pywikibot | |
| from tqdm import tqdm | |
| def get_creation_month(fp): | |
| creation_time = fp.oldest_revision.timestamp | |
| return creation_time.isoformat().rpartition('-')[0] |
| # https://commons.wikimedia.org/w/api.php?action=query&format=json&prop=linkshere&continue=gcmcontinue%7C%7C&generator=categorymembers&formatversion=2&lhprop=pageid%7Ctitle%7Credirect&lhnamespace=6&lhshow=!redirect&lhlimit=max&gcmtitle=Category%3A100%20000%20Bildminnen&gcmtype=file&gcmlimit=max | |
| import json | |
| import pywikibot | |
| from tqdm import tqdm | |
| def get_infiles(fp): | |
| links = fp.backlinks(filter_redirects=False, namespaces=['file']) | |
| return [link for link in links] |
| """Takes a commonsdiff output file and outputs some statistics.""" | |
| import json | |
| def check_changes(d, key, stats_data): | |
| key_data = d.get(key) | |
| if(key_data.get('added') or key_data.get('removed')): | |
| stats_data[key] += len(key_data.get('added')) - len(key_data.get('removed')) | |
| return True | |
| return False |
| """Get all media-views/mediarequests for files in a category for a time span. | |
| Returns only human views. | |
| Limitations: | |
| * Does a Rest-API call per file (and one to the Action API). | |
| * If the time span includes the current month the results will likely be partial. | |
| * Assumes a file has always been a member of the category if it is a member of it today. | |
| * The statistics only go back to 2015. | |
| """ |
| """Gets all images in a category and for each gets all global usages and associated captions. | |
| Limitations: | |
| * Not all Wikimedia wikis support returning captions. | |
| * Captions in <gallery>-tags are only returned if retrieve_gallery is set to True. | |
| * It does not filter by Namespace (but namespace is displayed in the results) | |
| This loops over all the images in the category and then over all pages which they appear on, | |
| so it isn't fast and doesn't make use of e.g. combined Action-API calls. | |
| """ |
| import csv | |
| from collections import defaultdict | |
| from tqdm import tqdm | |
| distribution_file = "wcvp_distribution.csv" | |
| names_file = "wcvp_names.csv" | |
| merge_file = "output_family/merge_{}.csv" | |
| fieldnames_distribution = None | |
| plant_id = defaultdict(list) | |
| demo = False # only output matches for plant_name_id = 1 or 2 |
| <?php | |
| /** | |
| * Created by User:Prolineserver | |
| * Released under GPL per the following statement | |
| * https://sv.wikipedia.org/w/index.php?title=Anv%C3%A4ndardiskussion:Prolineserver&oldid=53364425#Licens_f%C3%B6r_Slumpartikel | |
| * @license GPL-3.0-or-later | |
| */ | |
| if(isset($_REQUEST['source'])){ | |
| if(intval($_REQUEST['source']) == 1) { |
| # Allows for reconciliation against Wikidata using _only_ an external identifier. | |
| # This differs from the normal reconciliation which would use such a column together | |
| # with normal matching techniques such as label matching. | |
| # Add column by fetching URLs... | |
| return "https://query.wikidata.org/sparql?format=json&query=SELECT%20DISTINCT%20%3Fq%20%7B%20VALUES%20%3Fvalue%20%7B%20%22{val}%22%20%22{val}%22%20%22{val}%22%20%7D%20.%20%3Fq%20wdt%3AP{prop}%20%3Fvalue%20%7D".format(prop=1260, val=value) | |
| # more legible version of the above | |
| import urllib | |
| query = "SELECT DISTINCT ?q {{ VALUES ?value {{ '{val}' '{val}' '{val}' }} . ?q wdt:P{prop} ?value }}".format(prop=1260, val=value) |
| #!/usr/bin/python | |
| # -*- coding: utf-8 -*- | |
| # short script for scraping literaturbanken book images | |
| import requests | |
| from tqdm import tqdm | |
| def download_single(num, prefix, url): | |
| num_s = '{0:04}'.format(num) | |
| full_url = url.format(num_s) | |
| output_file = '{1}_{0}.jpg'.format(num_s, prefix) |
Phan needs php-ast to run, unfortunately this does not come included in the MediaWiki-Vagrant installation. To install it follow these instructions (largely influenced by Mainframe98). You can also try to run the associated shell script to automate this part.
From the vagrant home directory run vagrant up to spin up vagrant then run vagrant ssh to enter your vagrant shell.
Run the following and accept any prompts
wget http://pear.php.net/go-pear.phar
php go-pear.phar