From dd461cb457045c779d331459cad880a7f8490dc6 Mon Sep 17 00:00:00 2001
From: Edmond Yoo <hj3yoo@uwaterloo.ca>
Date: Sun, 16 Sep 2018 02:50:28 +0000
Subject: [PATCH] cleaning directory
---
fetch_data.py | 76 +++++++++++++++++++++++++++++++-------
1 files changed, 62 insertions(+), 14 deletions(-)
diff --git a/fetch_data.py b/fetch_data.py
index 5e3f23c..221e16c 100644
--- a/fetch_data.py
+++ b/fetch_data.py
@@ -1,16 +1,26 @@
from urllib import request
+import ast
import json
import pandas as pd
import re
+import os
+import transform_data
+import time
+
+all_set_list = ['cmd', 'bfz', 'all', 'ulg',
+ 'mrd', 'dst', '5dn', 'chk', 'bok', 'sok', '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']
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:
+ with open(res_file_dir, 'r') as res_file:
res_json = json.loads(res_file.read())
cards += res_json['data']
has_more = res_json['has_more']
@@ -18,23 +28,30 @@
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_json(csv_name)
+ df.to_csv(csv_name, sep=';') # Comma doesn't work, since some columns are saved as a dict
- return cards
+ 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=';')
+ 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 +63,45 @@
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']))
- pass
+def fetch_all_cards_image(df, out_dir='', size='png'):
+ if isinstance(df, pd.Series):
+ fetch_card_image(df, out_dir, size)
+ else:
+ for ind, row in df.iterrows():
+ 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'])
+ 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)
def main():
- fetch_all_cards_text(csv_name='data/all_cards.csv')
+ for set_name in all_set_list:
+ csv_name = '%s/csv/%s.csv' % (transform_data.data_dir, set_name)
+ print(csv_name)
+ if not os.path.isfile(csv_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)
+ time.sleep(1)
+ #fetch_all_cards_image(df, out_dir='../usb/data/png/%s' % set_name)
+ #df = fetch_all_cards_text(url='https://api.scryfall.com/cards/search?q=layout:normal+lang:en+frame:2003',
+ # csv_name='data/csv/all.csv')
+ pass
+
if __name__ == '__main__':
main()
+ pass
--
Gitblit v1.10.0