Tool for cite generation

Today I developed a simple tool to generate citations. It is available here.

Steps

1. Click the above link

2. Paste your URL

3. Generate and copy. 

PAWS in Wikisource

Add page number 

import pywikibot

# Set the site to Malayalam Wikisource

site = pywikibot.Site('ml', 'wikisource')

# Loop through pages 16 to 30

for i in range(16, 31):

    # Set the correct page title

    page_title = f'താൾ:സുവിശേഷം-ഭാഷാഗാനം.pdf/{i}'

    page = pywikibot.Page(site, page_title)

    # Set the content as the incrementing page number (starting from 12)

    page_number = i - 4  # This will give 12 for page 16

    content = f'<div style="text-align: center;">{page_number}</div>'

    # Check if the page exists

    if page.exists():

        # If the page exists, add content at the top

        new_content = content + "\n" + page.text

        page.text = new_content

        page.save(f"Added page number {page_number} at the top center")

    else:

        # If the page does not exist, create it with the content

        page.text = content

        page.save(f"Created page and added page number {page_number} at the top center")

        print(f"Page '{page_title}' was created.")

PAWS Fetch the pages from search box

 import requests

from bs4 import BeautifulSoup

search_url = "https://ml.wikipedia.org/w/index.php?title=പ്രത്യേകം:അന്വേഷണം&limit=500&offset=0&ns0=1&search=ഇസ്ലാം+ഇസ്ലാം&advancedSearch-current="

# Send a GET request to the search URL

response = requests.get(search_url)

# Check if the request was successful (status code 200)

if response.status_code == 200:

    # Parse the HTML content of the page

    soup = BeautifulSoup(response.text, 'html.parser')

    # Find the elements that contain article titles

    title_elements = soup.find_all('div', class_='mw-search-result-heading')

    # Extract and print the article titles

    for title_element in title_elements:

        article_title = title_element.text.strip()

        print(article_title)

else:

    print(f"Failed to retrieve search results. Status code: {response.status_code}")

Paws : Fixing spelling mistake (replace)

import pywikibot

site = pywikibot.Site('ml', 'wikipedia')  # Malayalam Wikipedia

site.login()

# Read page titles from replace.txt

with open('replace.txt', 'r', encoding='utf-8') as file:

    page_titles = file.read().splitlines()

# Search and replace for each page title

search_term = 'അള്ളാഹു'

replace_term = 'അല്ലാഹു'

for title in page_titles:

    page = pywikibot.Page(site, title)

    page_text = page.text

    # Check if the page text already contains the replacement term

    if replace_term not in page_text:

        updated_text = page_text.replace(search_term, replace_term)

        # Edit the page with the updated text

        page.text = updated_text

        page.save(summary='Fixing misspelling')

    else:

        print(f'Skipping page {title} as it already contains the replacement term.')

Python Query for Description

 import requests

import csv

def get_missing_labels(limit=10000):

    # Define the Wikidata endpoint and SPARQL query

    endpoint = "https://query.wikidata.org/sparql"

    query = f"""

    SELECT ?item ?itemLabel

    WHERE {{

      ?item wdt:P31 wd:Q202444;  # Instance of "male given name"

            schema:description ?description.

      FILTER(LANG(?description) = "en")  # English description

      FILTER NOT EXISTS {{

        ?item rdfs:label ?malayalamLabel.

        FILTER(LANG(?malayalamLabel) = "ml")  # Malayalam label does not exist

      }}

    }}

    LIMIT {limit}

    """

    # Set headers for the request

    headers = {

        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',

        'Accept': 'application/json',

        'Content-Type': 'application/json',

    }

    # Set parameters for the request

    params = {

        'query': query,

        'format': 'json'

    }

    # Make the request to the Wikidata API

    response = requests.get(endpoint, headers=headers, params=params)

    # Check if the request was successful (status code 200)

    if response.status_code == 200:

        data = response.json().get('results', {}).get('bindings', [])

        # Create a list to store the results

        results = []

        for item in data:

            entity_id = item.get('item', {}).get('value', '').split('/')[-1]

            english_label = item.get('itemLabel', {}).get('value', '')

            results.append({'entity_id': entity_id, 'english_label': english_label})

        return results

    else:

        print(f"Failed to retrieve data. Status code: {response.status_code}")

        return None

def write_to_csv(data, filename='missing_labels_male_given_name.csv'):

    # Write the results to a CSV file

    with open(filename, 'w', newline='', encoding='utf-8') as csv_file:

        fieldnames = ['entity_id', 'english_label']

        writer = csv.DictWriter(csv_file, fieldnames=fieldnames)

        writer.writeheader()

        writer.writerows(data)

if __name__ == "__main__":

    # Run the function to get items with missing labels

    results = get_missing_labels(limit=10000)

    # Check if there are results

    if results:

        # Print the results

        print("Items with English description 'male given name' lacking Malayalam label (limited to 10000 results):")

        for result in results:

            print(f"{result['entity_id']}: {result['english_label']}")

        # Write the results to a CSV file

        write_to_csv(results, filename='missing_labels_male_given_name.csv')

        print("\nResults have been saved to missing_labels_male_given_name.csv.")

    else:

        print("No results obtained.")

Notepad file