From b88a7221000facda2fd81330417958adcc17dc3c Mon Sep 17 00:00:00 2001
From: Edmond Yoo <hj3yoo@uwaterloo.ca>
Date: Sun, 26 Aug 2018 02:22:57 +0000
Subject: [PATCH] Aggregating card images, importing texture images for background

---
 fetch_data.py |   36 ++++++++++++++++++++++++------------
 1 files changed, 24 insertions(+), 12 deletions(-)

diff --git a/fetch_data.py b/fetch_data.py
index 5e3f23c..6fc526a 100644
--- a/fetch_data.py
+++ b/fetch_data.py
@@ -2,12 +2,14 @@
 import json
 import pandas as pd
 import re
+import os
 
 
 def fetch_all_cards_text(url='https://api.scryfall.com/cards/search?q=layout:normal+format:modern+lang:en+frame:2003',
                          csv_name=''):
     has_more = True
     cards = []
+    # get cards dataset as a json from the query
     while has_more:
         res_file_dir, http_message = request.urlretrieve(url)
         with open(res_file_dir) as res_file:
@@ -18,23 +20,21 @@
                 url = res_json['next_page']
             print(len(cards))
 
+    # Convert them into a dataframe, and truncate unnecessary columns
     df = pd.DataFrame.from_dict(cards)
-    df['image'] = ''
-    for ind, row in df.iterrows():
-        df.set_value(ind, 'image', row['image_uris']['png'])
 
     if csv_name != '':
         df = df[['artist', 'border_color', 'collector_number', 'color_identity', 'colors', 'flavor_text', 'image_uris',
-                 'image', 'mana_cost', 'legalities', 'name', 'oracle_text', 'rarity', 'type_line', 'set', 'set_name',
-                 'power', 'toughness']]
-        df.to_csv(csv_name, sep=';')
+                 'mana_cost', 'legalities', 'name', 'oracle_text', 'rarity', 'type_line', 'set', 'set_name', 'power',
+                 'toughness']]
+        df.to_csv(csv_name, sep=';')  # Comma doesn't work, since some columns are saved as a dict
 
-    return cards
+    return df
 
 
+# Pulled from Django framework (https://github.com/django/django/blob/master/django/utils/text.py)
 def get_valid_filename(s):
     """
-    NOTE: Pulled from Django framework (https://github.com/django/django/blob/master/django/utils/text.py)
     Return the given string converted to a string that can be used for a clean
     filename. Remove leading and trailing spaces; convert other spaces to
     underscores; and remove anything that is not an alphanumeric, dash,
@@ -46,14 +46,26 @@
     return re.sub(r'(?u)[^-\w.]', '', s)
 
 
-def fetch_cards_image(cards_json, out_dir, size='large'):
-    for card in cards_json:
-        request.urlretrieve(card['image_uris'][size], '%s\%s' % (out_dir, card['name']))
+def fetch_cards_image(df, out_dir='', size='png'):
+    for ind, row in df.iterrows():
+        png_url = row['image_uris'][size]
+        if out_dir == '':
+            out_dir = 'data/png/%s' % row['set']
+        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']))
+        request.urlretrieve(png_url, filename=img_name)
+        print(img_name)
     pass
 
 
 def main():
-    fetch_all_cards_text(csv_name='data/all_cards.csv')
+    df = fetch_all_cards_text(url='https://api.scryfall.com/cards/search?q=layout:normal+set:rtr+lang:en',
+                              csv_name='data/all_cards.csv')
+    fetch_cards_image(df)
+    pass
+
 
 if __name__ == '__main__':
     main()
+    pass

--
Gitblit v1.10.0