How to download a higher resolution image from the wiki API with Python?

Question

I modified the code and added to it the ability to download photos from the wiki. I am downloading the url of the photo from the main wiki page. The problem is that it is low resolution and I would like it to be larger (the size after clicking on the image). EXAMPLE:

Wiki URL to the website - https://pl.wikipedia.org/wiki/Zamek_Kr%C3%B3lewski_na_Wawelu

URL downloaded using my script - https://upload.wikimedia.org/wikipedia/commons/thumb/e/ea/Royal_Castle%2C_Wawel_Hill%2C_4_Wawel%2C_Old_Town%2C_Krak%C3%B3w%2C_Poland.jpg/240px-Royal_Castle%2C_Wawel_Hill%2C_4_Wawel%2C_Old_Town%2C_Krak%C3%B3w%2C_Poland.jpg

URL address after clicking on the main photo - https://upload.wikimedia.org/wikipedia/commons/e/ea/Royal_Castle%2C_Wawel_Hill%2C_4_Wawel%2C_Old_Town%2C_Krak%C3%B3w%2C_Poland.jpg

As you can see the photos have a larger size after clicking and I would like to download such a link. I've been struggling with this code for two days and can't fix it. Anyone know what I'm doing wrong? Below is my script and call: Calling:

python fetch.py --directory output/england/Krakow --rating 4 --reviews 5000 --operator i --query "Zamek Królewski na Wawelu"

The code that is responsible for downloading url image

#url img for wikipedia
from bs4 import BeautifulSoup
if url:
    urladress = url
    soup = BeautifulSoup(requests.get(urladress).text,'html.parser')
    imglinks = soup.find_all('a', attrs = {'class':'image'})[0]
    for img in imglinks.find_all('img'):
        wiki_link = (img['src'].replace('//','https://'))
    if (wiki_link is not None):
        img_link = wiki_link
    else:
        img_link = -1   

Script:

#!/usr/bin/env python
import csv
import json
import pathlib
import operator
import requests
import argparse
import configparser
import re

import wikipedia

# Read the API key form the configuration.
config = configparser.ConfigParser()
config.read('secrets.ini')

API_KEY = '' #add API KEY Google
PLACES_TYPES = ['park', 'point_of_interest', 'establishment', 'museum', 'library', 'church', 'art_gallery', 'political']
# Search query operators.
OPERATORS = {
    'i': operator.and_,
    'lub': operator.or_
}

def fetch_place_detail(place_id):
    place_raw = requests.get(f'https://maps.googleapis.com/maps/api/place/details/json?placeid={place_id}&key={API_KEY}')
    try:
        return json.loads(place_raw.text)['result']
    except KeyError:
        raise KeyError('Index \'result\' does not exist')
        
# Add parameters for the search query.
parser = argparse.ArgumentParser()
parser.add_argument('--query', type=str, help='Search query for Google Maps API')
parser.add_argument('--directory', type=str, help='Output directory')
parser.add_argument('--rating', type=float, help='Minimum rating of the place(s)')
parser.add_argument('--reviews', type=int, help='Minimum review count of the place(s)')
parser.add_argument('--operator', default='and', choices=OPERATORS.keys(), type=str,
                                  help='Operation to perform between ratings and reviews count.')
parser.add_argument('--exclude', '-e', choices=PLACES_TYPES, nargs='+', type=str,
                                       help='Exclude the places from the query result')
parser.add_argument('--language', default='pl', choices=['pl', 'fr', 'de'], type=str,
                                  help='Language of the Wikipedia link')
parser.add_argument('--summary-length', type=int,
                                        help='Limit the number of sentences in place summary.')

args = parser.parse_args()
# Fetch the data.
places = requests.get(f'https://maps.googleapis.com/maps/api/place/textsearch/json?query={args.query}&language=pl&key={API_KEY}')
# Convert the response to a JSON object.
places = json.loads(places.text)['results']
if not places:
    raise Exception(f'No results found for query: {args.query}')

# Create the directory if it doesn't exist.
pathlib.Path(args.directory).mkdir(parents=True, exist_ok=True)
# Make the filename more readable, as this will appear as the layer title in Google My Maps.
query = args.query.split(' ')
filename = ' '.join([q.capitalize() for q in query])
# Set Wikipedia language.
wikipedia.set_lang(args.language)

columns = ['name', 'coordinates', 'types', 'rating', 'formatted_address', 'photo_reference', 'summary', 'url', 'reviews', 'img_link']
with open(args.directory + f'/{filename}.csv', 'w', encoding='utf-8') as out_file:
    writer = csv.writer(out_file, delimiter='|')
    writer.writerow(columns)
    for place in places:
        name = place['name']
        formatted_address = place['formatted_address']
        types = place['types']
        if 'photo_reference' in place:
            photo_reference = place['photo_reference']
        else:
            photo_reference = -1
        if 'user_ratings_total' in place:
            reviews = place['user_ratings_total']
        else:
            reviews = -1
        if 'rating' in place:
            rating = place['rating']
        else:
            rating = -1                 
        try:
            if args.summary_length:
                wiki_page = wikipedia.page(name, sentences=args.summary_length)
            else:
                wiki_page = wikipedia.page(name)
            url = wiki_page.url
            summary = wiki_page.summary.replace('\n', '')
        except KeyboardInterrupt:
            exit(-1)
        except:
            url, summary = '', ''
        #url img for wikipedia
        from bs4 import BeautifulSoup
        if url:
            urladress = url
            soup = BeautifulSoup(requests.get(urladress).text,'html.parser')
            imglinks = soup.find_all('a', attrs = {'class':'image'})[0]
            for img in imglinks.find_all('img'):
                wiki_link = (img['src'].replace('//','https://'))
            if (wiki_link is not None):
                img_link = wiki_link
            else:
                img_link = -1           
        #else:
        #   img_link = wiki_link        
        # If item type is from the exlude list, skip it.
        if args.exclude:
            if list(set(args.exclude) & set(types)):
                continue
        # If an item doesn't satify the rating and review count criteria, skip it.
        if args.rating and args.reviews:
            rating = place['rating']
            if not OPERATORS[args.operator](rating >= args.rating, reviews >= args.reviews):
                continue
        elif args.rating:
            if not rating >= args.rating:
                continue
        elif args.reviews:
            if not reviews >= args.reviews:
                continue
                            

        lat, lng = place['geometry']['location']['lat'], place['geometry']['location']['lng']
        data = [name, (lat, lng), ', '.join(types), rating, formatted_address, photo_reference, summary, url, reviews, img_link]
        print(f'{filename} -> {data}')
        writer.writerow(data)

Answer 1

You can use wiki_page.images[0] to extract the image url.