From 05ecccf0da08e843a11b325738be0eaab27bf752 Mon Sep 17 00:00:00 2001 From: Sunpy Date: Mon, 11 Mar 2019 16:21:31 +0100 Subject: [PATCH] Del old files --- scrape.py | 67 ------------------------------------------------------- zipper.py | 50 ----------------------------------------- 2 files changed, 117 deletions(-) delete mode 100644 scrape.py delete mode 100644 zipper.py diff --git a/scrape.py b/scrape.py deleted file mode 100644 index 4d34ffb..0000000 --- a/scrape.py +++ /dev/null @@ -1,67 +0,0 @@ -#Used for scraping osu files from osu.ppy.sh and storing them into self database - -import urllib.request, json -import MySQLdb -import MySQLdb.cursors -import time, calendar -import atexit - -finished = False - -with open("config.json", "r") as f: - config = json.load(f) - -with open("memory.json", "r") as f: - memory = json.load(f) - -sql = MySQLdb.connect(**config["sql"], cursorclass = MySQLdb.cursors.DictCursor) - -cur = sql.cursor() - -def on_close(): - with open("memory.json", "w") as f: - json.dump(memory, f) - print("Closing...") - -atexit.register(on_close) - -failed_streak = 0 - -while not finished: - target = memory["scrape"]["last"] + 1 - attempts = 0 - completed = False - extra_sleep = 0 - while attempts < config["scrape"]["max_attempts"] and not completed: - try: - with urllib.request.urlopen("https://osu.ppy.sh/web/check-updates.php?action=path&stream=stable&target={}".format(target)) as url: - data = json.loads(url.read().decode())[0] - if "url_patch" not in data.keys(): - data["url_patch"] = None - cur.execute("INSERT INTO updates (file_version,filename,file_hash,filesize,timestamp,patch_id,url_full,url_patch) VALUES (%s,%s,%s,%s,%s,%s,%s,%s)", - [ - data["file_version"], - data["filename"], - data["file_hash"], - data["filesize"], - calendar.timegm(time.strptime(data["timestamp"], "%Y-%m-%d %H:%M:%S")), - data["patch_id"], - data["url_full"], - data["url_patch"] - ]) - sql.commit() - completed = True - failed_streak = 0 - print("target: {}, status: OK".format(target)) - except: - if target not in memory["scrape"]["failed"]: - memory["scrape"]["failed"].append(target) - attempts += 1 - failed_streak += 1 - if config["scrape"]["increase_delay_on_fail"]: - extra_sleep = attempts - print("target: {}, status: FAILED, attempt: {}".format(target, attempts)) - time.sleep(config["scrape"]["delay"] + extra_sleep) - if failed_streak > 100: - exit() - memory["scrape"]["last"] = target \ No newline at end of file diff --git a/zipper.py b/zipper.py deleted file mode 100644 index b91341b..0000000 --- a/zipper.py +++ /dev/null @@ -1,50 +0,0 @@ -#Used to zip all the files into new local folders after downloader is done - -import urllib.request, json -import MySQLdb -import MySQLdb.cursors -import os -import atexit - -with open("config.json", "r") as f: - config = json.load(f) - -with open("memory.json", "r") as f: - memory = json.load(f) - -sql = MySQLdb.connect(**config["sql"], cursorclass = MySQLdb.cursors.DictCursor) - -cur = sql.cursor() - -def on_close(): - with open("memory.json", "w") as f: - json.dump(memory, f) - print("Closing...") - -atexit.register(on_close) - -cur.execute("SELECT file_version,filename,file_hash,url_full FROM updates") -data = cur.fetchall() - -# Remove already downloaded files (checked from memory.json) -data = data[memory["zipper"]["last"]:] - -# Unfinished - replace with zipper code -""" -for row in data: - try: - print("Downloading {} with id {}".format(row["filename"], row["file_version"])) - urllib.request.urlretrieve( - row["url_full"], - os.path.join( - config["downloader"]["download_folder"], - row["filename"], - "f_" + row["file_hash"] - ) - ) - print("Done.") - except Exception as e: - memory["downloader"]["failed"].append(row["file_version"]) - print("Error downloading file {}: {}".format(row["file_version"], e)) - memory["downloader"]["last"] += 1 -""" \ No newline at end of file