From b95bf33cb5b296efb70a0c4b1c82c0f62286f52a Mon Sep 17 00:00:00 2001
From: Constantin Wenger <constantin.wenger@googlemail.com>
Date: Thu, 03 Feb 2022 20:18:17 +0000
Subject: [PATCH] added options to flip/rotate and specify different input resolutions also fixed displayed image to max 800x800 everything above will be scaled while keeping aspect ratio
---
fetch_data.py | 135 ++++++++++++++++++++++++++++++++------------
1 files changed, 97 insertions(+), 38 deletions(-)
diff --git a/fetch_data.py b/fetch_data.py
index 2d66e02..a43cb68 100644
--- a/fetch_data.py
+++ b/fetch_data.py
@@ -1,17 +1,26 @@
-from urllib import request
import ast
import json
+import os
import pandas as pd
import re
-import os
+from urllib import request, error
-all_set_list = ['8ed', 'mrd', 'dst', '5dn', 'chk', 'bok', 'sok', '9ed', 'rav', 'gpt', 'dis', 'csp', 'tsp', 'plc', 'fut',
- '10e', 'lrw', 'mor', 'shm', 'eve', 'ala', 'con', 'arb', 'm10', 'zen', 'wwk', 'roe', 'm11', 'som', 'mbs',
- 'nph', 'm12', 'isd', 'dka', 'avr', 'm13', 'rtr', 'gtc', 'dgm', 'm14', 'ths', 'bng', 'jou']
+from config import Config
+
+"""
+Note: All codes in this file realies on Scryfall API to aggregate card database and their images.
+Scryfall API doc is available at: https://scryfall.com/docs/api
+"""
def fetch_all_cards_text(url='https://api.scryfall.com/cards/search?q=layout:normal+format:modern+lang:en+frame:2003',
- csv_name=''):
+ csv_name=None):
+ """
+ Given the query URL using Scryfall API, aggregate all card information and convert them from json to table
+ :param url: query URL
+ :param csv_name: path of the csv file to save the result
+ :return: pandas dataframe of the fetch cards
+ """
has_more = True
cards = []
# get cards dataset as a json from the query
@@ -28,25 +37,19 @@
# Convert them into a dataframe, and truncate unnecessary columns
df = pd.DataFrame.from_dict(cards)
- if csv_name != '':
- df = df[['artist', 'border_color', 'collector_number', 'color_identity', 'colors', 'flavor_text', 'image_uris',
- 'mana_cost', 'legalities', 'name', 'oracle_text', 'rarity', 'type_line', 'set', 'set_name', 'power',
- 'toughness']]
- #df.to_json(csv_name)
- df.to_csv(csv_name, sep=';') # Comma doesn't work, since some columns are saved as a dict
-
+ if csv_name is not None:
+ #df = df[['artist', 'border_color', 'collector_number', 'color_identity', 'colors', 'flavor_text', 'image_uris',
+ # 'mana_cost', 'legalities', 'name', 'oracle_text', 'rarity', 'type_line', 'set', 'set_name', 'power',
+ # 'toughness']]
+ df.to_csv(csv_name, sep=';') # Comma seperator doesn't work, since some columns are saved as a dict
return df
def load_all_cards_text(csv_name):
- #with open(csv_name, 'r') as json_file:
- # cards = json.loads(json_file.read())
- #df = pd.DataFrame.from_dict(cards)
- df = pd.read_csv(csv_name, sep=';')
+ df = pd.read_csv(csv_name, sep=';') # Comma seperator doesn't work, since some columns are saved as a dict
return df
-# Pulled from Django framework (https://github.com/django/django/blob/master/django/utils/text.py)
def get_valid_filename(s):
"""
Return the given string converted to a string that can be used for a clean
@@ -55,47 +58,103 @@
underscore, or dot.
>>> get_valid_filename("john's portrait in 2004.jpg")
'johns_portrait_in_2004.jpg'
+ From: https://github.com/django/django/blob/master/django/utils/text.py
+ :param s: input string
+ :return: string of valid filename
"""
s = str(s).strip().replace(' ', '_')
return re.sub(r'(?u)[^-\w.]', '', s)
-def fetch_all_cards_image(df, out_dir='', size='png'):
+def fetch_all_cards_image(df, out_dir=None, size='png'):
+ """
+ Download card images from Scryfall database
+ :param df: pandas dataframe (or series) of cards
+ :param out_dir: path of output directory
+ :param size: Image format given by Scryfall API - 'png', 'large', 'normal', 'small', 'art_crop', 'border_crop'
+ :return:
+ """
+ if size != 'png':
+ print('Note: this repo has been implemented using only \'png\' size. '
+ 'Using %s may result in an unexpected behaviour in other parts of this repo.' % size)
if isinstance(df, pd.Series):
+ # df is a single row of card
fetch_card_image(df, out_dir, size)
else:
+ from concurrent.futures import ThreadPoolExecutor, wait as fwait
+ executor = ThreadPoolExecutor(5)
+ # df is a dataframe containing list of cards
+ arglist = []
for ind, row in df.iterrows():
- fetch_card_image(row, out_dir, size)
+ arglist.append(executor.submit(fetch_card_image, row, out_dir, size))
+ fwait(arglist)
+ # fetch_card_image(row, out_dir, size)
-def fetch_card_image(row, out_dir='', size='png'):
- if isinstance(row['image_uris'], str): # For some reason, dict isn't being parsed in the previous step
- png_url = ast.literal_eval(row['image_uris'])[size]
- else:
- png_url = row['image_uris'][size]
- if out_dir == '':
- out_dir = 'data/%s/%s' % (size, row['set'])
+def fetch_card_image(row, out_dir=None, size='png'):
+ """
+ Download a card's image from Scryfall database
+ :param row: pandas series including the card's information
+ :param out_dir: path of the output directory
+ :param size: Image format given by Scryfall API - 'png', 'large', 'normal', 'small', 'art_crop', 'border_crop'
+ :return:
+ """
+ if out_dir is None:
+ s = row['set']
+ if s == 'con':
+ s = 'con__'
+ out_dir = '%s/card_img/%s/%s' % (Config.data_dir, size, s)
if not os.path.exists(out_dir):
os.makedirs(out_dir)
- img_name = '%s/%s_%s.png' % (out_dir, row['collector_number'], get_valid_filename(row['name']))
- if not os.path.isfile(img_name):
- request.urlretrieve(png_url, filename=img_name)
- print(img_name)
+
+ # Extract card's name and URL for image accordingly
+ # Double-faced cards have a different format, and results in two separate card images
+ png_urls = []
+ card_names = []
+ if row['layout'] in ['transform', 'double_faced_token']:
+ if isinstance(row['card_faces'], str): # For some reason, dict isn't being parsed in the previous step
+ card_faces = ast.literal_eval(row['card_faces'])
+ else:
+ card_faces = row['card_faces']
+ for i in range(len(card_faces)):
+ png_urls.append(card_faces[i]['image_uris'][size])
+ card_names.append(get_valid_filename(card_faces[i]['name']))
+ else: #if row['layout'] == 'normal':
+ if isinstance(row['image_uris'], str): # For some reason, dict isn't being parsed in the previous step
+ png_urls.append(ast.literal_eval(row['image_uris'])[size])
+ else:
+ png_urls.append(row['image_uris'][size])
+ card_names.append(get_valid_filename(row['name']))
+
+ for i in range(len(png_urls)):
+ img_name = '%s/%s_%s.png' % (out_dir, row['collector_number'], card_names[i])
+ if not os.path.isfile(img_name):
+ request.urlretrieve(png_urls[i], filename=img_name)
+ print(img_name)
def main():
- for set_name in all_set_list:
- csv_name = 'data/csv/%s.csv' % set_name
+ # Query card data by each set, then merge them together
+ if not os.path.exists(os.path.join(Config.data_dir, 'csv')):
+ os.mkdir(os.path.join(Config.data_dir, 'csv'))
+ for set_name in Config.all_set_list:
+ set_name_m = set_name
+ if set_name_m == 'con':
+ set_name_m = 'con__'
+ csv_name = '%s/csv/%s.csv' % (Config.data_dir, set_name_m)
+ print(csv_name)
if not os.path.isfile(csv_name):
- df = fetch_all_cards_text(url='https://api.scryfall.com/cards/search?q=layout:normal+set:%s+lang:en' % set_name,
+ df = fetch_all_cards_text(url='https://api.scryfall.com/cards/search?q=set:%s+lang:en' % set_name,
csv_name=csv_name)
else:
df = load_all_cards_text(csv_name)
- print(csv_name)
- fetch_all_cards_image(df, out_dir='../usb/data/png/%s' % set_name)
- pass
+ df.sort_values('collector_number')
+ fetch_all_cards_image(df, out_dir='%s/card_img/png/%s' % (Config.data_dir, set_name))
+
+ #df = fetch_all_cards_text(url='https://api.scryfall.com/cards/search?q=layout:normal+lang:en+frame:2003',
+ # csv_name='%s/csv/all.csv' % Config.data_dir)
+ return
if __name__ == '__main__':
main()
- pass
--
Gitblit v1.10.0