+9/24

discord_analyse_v2.py

import json
import csv
from pathlib import Path
from datetime import datetime
 
# --- CONFIGURATION ---
BASE_PATH = 'C:/temp/discord/'
OUTPUT_FILENAME = 'output_timestamps_clean.csv'
 
def standardize_timestamp(ts_string):
    """Converts varying timestamp formats into a standard YYYY-MM-DD HH:MM:SS format."""
    if not ts_string:
        return None
 
    # Format 1: "02.06.2021 06:26"
    try:
        dt = datetime.strptime(ts_string, "%d.%m.%Y %H:%M")
        return dt.strftime("%Y-%m-%d %H:%M:%S")
    except ValueError:
        pass
 
    # Format 2: "2021-02-17T20:35:29.083Z" (ISO 8601)
    try:
        dt = datetime.strptime(ts_string.replace("\"","")[:19].replace('T', ' '), "%Y-%m-%d %H:%M:%S")
 
        #dt = datetime.fromisoformat(ts_string[:17].replace('T', ' '))
        return dt.strftime("%Y-%m-%d %H:%M:%S")
    except ValueError:
        pass
 
    # Fallback: return original string if it matches neither format
    return ts_string
 
def process_file(file_path, writer):
    """Attempts to read a file as standard JSON, falls back to JSON Lines if needed."""
    with open(file_path, 'r', encoding='utf-8') as f:
        try:
            # Attempt 1: Standard JSON
            data = json.load(f)
            records = data if isinstance(data, list) else [data]
 
            for entry in records:
                if isinstance(entry, dict):
                    # Check both capitalization variants just in case
                    raw_ts = entry.get('Timestamp') or entry.get('timestamp')
                    if raw_ts:
                        clean_ts = standardize_timestamp(raw_ts)
                        writer.writerow([clean_ts, file_path.name])
            return 
 
        except json.JSONDecodeError:
            pass 
 
        # Attempt 2: JSON Lines
        f.seek(0) 
 
        for line in f:
            line = line.strip()
            if not line:
                continue
 
            try:
                entry = json.loads(line)
                records = entry if isinstance(entry, list) else [entry]
 
                for rec in records:
                    if isinstance(rec, dict):
                        raw_ts = rec.get('Timestamp') or rec.get('timestamp')
                        if raw_ts:
                            clean_ts = standardize_timestamp(raw_ts)
                            writer.writerow([clean_ts, file_path.name])
 
            except json.JSONDecodeError:
                pass
 
def extract_and_format_timestamps():
    work_dir = Path(BASE_PATH)
    output_path = work_dir / OUTPUT_FILENAME
 
    with open(output_path, 'w', newline='', encoding='utf-8') as csv_out:
        writer = csv.writer(csv_out)
        writer.writerow(['Timestamp', 'Filename'])
 
        print(f"Scanning: {work_dir}")
        print(f"Output will be saved to: {output_path}")
 
        for file_path in work_dir.glob('**/*.json'):
            if file_path.name == OUTPUT_FILENAME:
                continue
 
            try:
                process_file(file_path, writer)
            except Exception as e:
                print(f"Error reading file {file_path.name}: {e}")
 
    print("Done!")
 
if __name__ == "__main__":
    extract_and_format_timestamps()

spotify_analyse.py

import json
import csv
from pathlib import Path
 
# --- CONFIGURATION ---
# Replace this with the path to your folder.
# The script will read JSONs from here AND save the CSV.
BASE_PATH = 'C:/temp/spotify/'  # <-- Change this to your actual folder path
OUTPUT_FILENAME = 'C:/temp/spotify_history.csv'
DELIM = ';'  # Delimiter for CSV, change if needed
 
 
def spotify_json_to_csv():
    # Create a Path object from the global variable
    work_dir = Path(BASE_PATH)
    output_path = OUTPUT_FILENAME
 
    # Open the CSV file for writing
    with open(output_path, 'w', newline='', encoding='utf-8') as csv_out:
        writer = csv.writer(csv_out, delimiter=DELIM)
 
        # Write the header row with the new column
        writer.writerow(['Timestamp', 'Song Title', 'Artist', 'ms_played'])
 
        print(f"Scanning: {work_dir}")
        print(f"Output will be saved to: {output_path}")
 
        # Walk through all JSON files in the directory
        for file_path in work_dir.glob('**/*.json'):
            # Skip the output file itself if it already exists to avoid errors
            if file_path.name == OUTPUT_FILENAME:
                continue
 
            try:
                with open(file_path, 'r', encoding='utf-8') as f:
                    data = json.load(f)
                    print(
                        f"Processing: {file_path.name} with {len(data)} entries")
                    if isinstance(data, list):
                        for entry in data:
                            timestamp = entry.get('ts')
                            song = entry.get('master_metadata_track_name')
                            artist = entry.get(
                                'master_metadata_album_artist_name')
                            ms_played = entry.get('ms_played', 0)
 
                            # Write row only if we have a valid song title
                            if song:
                                writer.writerow(
                                    [timestamp, song, artist, ms_played])
 
            except json.JSONDecodeError:
                print(f"Warning: Could not decode {file_path.name}")
            except Exception as e:
                print(f"Error processing {file_path.name}: {e}")
 
    print("Done!")
 
 
if __name__ == "__main__":
    spotify_json_to_csv()

discord_analyse.py

import json
import csv
from pathlib import Path
 
# --- CONFIGURATION ---
# Replace this with the path to your folder.
# The script will read JSONs from here AND save the CSV here.
BASE_PATH = 'C:/temp/discord/'
OUTPUT_FILENAME = 'C:/temp/output_timestamps.csv'
DELIM = ';'  # Delimiter for CSV, change if needed
 
def json_to_csv():
    # Create a Path object from the global variable
    work_dir = Path(BASE_PATH)
    output_path = OUTPUT_FILENAME
 
    # Open the CSV file for writing
    with open(output_path, 'w', newline='', encoding='utf-8') as csv_out:
        writer = csv.writer(csv_out,delimiter=DELIM)
 
        # Write the header row
        writer.writerow(['Timestamp', 'Filename'])
 
        print(f"Scanning: {work_dir}")
        print(f"Output will be saved to: {output_path}")
 
        # Walk through all JSON files
        for file_path in work_dir.glob('**/*.json'):
            try:
                with open(file_path, 'r', encoding='utf-8') as f:
                    data = json.load(f)
 
                    # Ensure the structure is a list
                    if isinstance(data, list):
                        for entry in data:
                            timestamp = entry.get('Timestamp')
 
                            # Write row only if timestamp exists
                            if timestamp:
                                writer.writerow([timestamp, file_path.name])
 
            except json.JSONDecodeError:
                print(f"Warning: Could not decode {file_path.name}")
            except Exception as e:
                print(f"Error processing {file_path.name}: {e}")
 
    print("Done!")
 
if __name__ == "__main__":
    json_to_csv()

insta_analyse_deutsch.py

# -*- coding: utf-8 -*-
import re        # Regular Expressions
import datetime  # Datum/Zeit
import os        # Files suchen
 
# Erklärungen zu diesem Code sind bei der Lehrperson erhältlich. Es ist nicht nötig, diesen Code zu verstehen, um die Aufgabe zu lösen. Es könnte aber interessant sein, sich damit zu beschäftigen.
 
rootdir = 'C:/ordner/wo/alles/liegt/'
pathtocsv = 'C:/order/wo/das/resultat/sein/soll/dateiname.csv'
mnum = {
    "Januar": 1, "Februar": 2, "März": 3, "April": 4, "Mai": 5, "Juni": 6,
    "Juli": 7, "August": 8, "September": 9, "Oktober": 10, "November": 11, "Dezember": 12
}
 
# Resultat, das am Schluss geschrieben werden soll
csv = ""   # Comma separated values
# Wie viele Kontrollausgaben?
debug = 10
 
# Alle HTML-Dateien im Verzeichnis anzeigen
for root, dirs, files in os.walk(rootdir):
    for file in files:
        if file.endswith(".html"):
            filepath = os.path.join(root, file)
            # Datei oeffnen
            f = open(filepath, "r", encoding="utf8")
            html = f.read()  # Alles einlesen
            f.close()        # Datei schliessen
 
            # Datum der Form Apr. 08, 2021 8:54 am einlesen
            # Alle nötigen Angaben werden in Klammern "ge-captured"
            daten = re.findall(
                "([A-Z][a-zä]+) (\d{1,2}), (\d{4}) (\d{1,2}):(\d{1,2}) ([ap]m)", html)
 
            if (debug > 0):
                print(file, ": ", len(daten))
                debug -= 1
 
            # Alle Einträge durchgehen, d enthält jeweils den nächsten Eintrag
            for d in daten:
                # Einträge in Zahlen umwandeln
                # Monat plus die anderen Einträge (ohne AM/PM) in Zahlen umgewandelt
                #   Die Zeichenkette "42" ist nicht das gleiche wie die Zahl 42.
                e = [mnum[d[0]]] + [int(x) for x in d[1:-1]]
                # Nachmittag? Plus 12 Stunden (Ausser Mitternacht = 0)
                if d[5] == "pm":
                    e[3] = (e[3]+12) % 24
                if debug > 0:
                    # Ausgabe zur Kontrolle, sollte folgendes Format Produzieren
                    print(e)  # [1, 6, 2021, 21, 23, 12]
                    debug -= 1  # Um 1 vermindern
 
                # Datum daraus generieren (macht die Datumsmanipulation einfacher).
                # Jahr, Monat, Tag, Stunde, Minute, Sekunde
                datum = datetime.datetime(e[2], e[0], e[1], e[3], e[4], 0)
 
                if debug > 0:
                    # Ausgabe zur Kontrolle, produziert folgendes Format
                    print(datum)   # 2021-01-06 21:23:12
                    debug -= 1  # Um 1 vermindern
 
                # Wochentag (Mo=0, Di=1, ..., So=6)
                # Sämtliche Methoden für datetime-Objekte sind hier beschrieben: https://docs.python.org/3/library/datetime.html#datetime-objects
                wday = datum.weekday()
 
                # Formatierte Ausgabe des Datums, siehe https://www.w3schools.com/python/python_datetime.asp
                # \n heisst neue Zeile.
                # Das Format soll so angepasst werden, damit die Tabellenkalkulation dann damit umgehen kann.
                csv += datum.strftime("%Y-%m-%d %H:%M:%S;" + os.path.splitext(file)[0]+"\n")
 
        # Ausgabe in Datei schreiben
        f = open(pathtocsv, "w")
        f.write(csv)
        f.close()

insta_analyse_english.py

import re        # Regular Expressions
import datetime  # Datum/Zeit
import os        # Files suchen
 
# Erklärungen zu diesem Code sind bei der Lehrperson erhältlich. Es ist nicht nötig, diesen Code zu verstehen, um die Aufgabe zu lösen. Es könnte aber interessant sein, sich damit zu beschäftigen.
 
rootdir = 'C:/ordner/wo/alles/liegt/'
pathtocsv = 'C:/order/wo/das/resultat/sein/soll/dateiname.csv'
mnum = {"Jan": 1, "Feb": 2, "Mar": 3, "Apr": 4, "May": 5, "Jun": 6,
        "Jul": 7, "Aug": 8, "Sep": 9, "Oct": 10, "Nov": 11, "Dec": 12}
 
# Resultat, das am Schluss geschrieben werden soll
csv = ""   # Comma separated values
# Wie viele Kontrollausgaben?
debug = 10
 
# Alle HTML-Dateien im Verzeichnis anzeigen
for root, dirs, files in os.walk(rootdir):
    for file in files:
        if file.endswith(".html"):
            filepath = os.path.join(root, file)
            # Datei oeffnen
            f = open(filepath, "r", encoding="utf8")
            html = f.read()  # Alles einlesen
            f.close()        # Datei schliessen
 
            # Datum der Form Apr. 08, 2021 8:54 am einlesen
            # Alle nötigen Angaben werden in Klammern "ge-captured"
            daten = re.findall(
                "([A-Z][a-z][a-z])\.? (\d{1,2}), (\d{4}) (\d{1,2}):(\d{1,2}) ([ap]m)", html)
 
            if (debug > 0):
                print(file, ": ", len(daten))
                debug -= 1
 
            # Alle Einträge durchgehen, d enthält jeweils den nächsten Eintrag
            for d in daten:
                # Einträge in Zahlen umwandeln
                # Monat plus die anderen Einträge (ohne AM/PM) in Zahlen umgewandelt
                #   Die Zeichenkette "42" ist nicht das gleiche wie die Zahl 42.
                e = [mnum[d[0]]] + [int(x) for x in d[1:-1]]
                # Nachmittag? Plus 12 Stunden (Ausser Mitternacht = 0)
                if d[5] == "pm":
                    e[3] = (e[3]+12) % 24
                if debug > 0:
                    # Ausgabe zur Kontrolle, sollte folgendes Format Produzieren
                    print(e)  # [1, 6, 2021, 21, 23, 12]
                    debug -= 1  # Um 1 vermindern
 
                # Datum daraus generieren (macht die Datumsmanipulation einfacher).
                # Jahr, Monat, Tag, Stunde, Minute, Sekunde
                datum = datetime.datetime(e[2], e[0], e[1], e[3], e[4], 0)
 
                if debug > 0:
                    # Ausgabe zur Kontrolle, produziert folgendes Format
                    print(datum)   # 2021-01-06 21:23:12
                    debug -= 1  # Um 1 vermindern
 
                # Wochentag (Mo=0, Di=1, ..., So=6)
                # Sämtliche Methoden für datetime-Objekte sind hier beschrieben: https://docs.python.org/3/library/datetime.html#datetime-objects
                wday = datum.weekday()
 
                # Formatierte Ausgabe des Datums, siehe https://www.w3schools.com/python/python_datetime.asp
                # \n heisst neue Zeile.
                # Das Format soll so angepasst werden, damit die Tabellenkalkulation dann damit umgehen kann.
                csv += datum.strftime("%Y-%m-%d %H:%M:%S;" + os.path.splitext(file)[0]+"\n")
 
        # Ausgabe in Datei schreiben
        f = open(pathtocsv, "w")
        f.write(csv)
        f.close()

insta_analyse.py

import os
 
# --- Programm um alle Dateien zu durchlaufen---
# Pfad anpassen
folder_to_check = 'C:/ordner/wo/alles/liegt/' #Achtung: Forward slashes oder ein r vor dem String
 
def get_directory_size(start_path):
    total_size = 0
 
    # os.walk() generates the file names in a directory tree
    # It yields a 3-tuple (dirpath, dirnames, filenames)
    for dirpath, dirnames, filenames in os.walk(start_path):
        for f in filenames:
            # Join the directory path and file name to get the full path
            fp = os.path.join(dirpath, f)
            print(fp)
            # Skip if it is a symbolic link (optional, but good practice)
            if not os.path.islink(fp):
                total_size += os.path.getsize(fp)
 
    return total_size
 
 
 
print(f"Berechne Grösse für: {os.path.abspath(folder_to_check)}")
 
size_in_bytes = get_directory_size(folder_to_check)
 
# Convert to Megabytes for easier reading
size_in_mb = size_in_bytes / (1024 * 1024)
 
print(f"Gesamtgrösse: {size_in_bytes} bytes")
print(f"Gesamtgrösse: {size_in_mb:.2f} MB")