export_rated_songs_as_csv.py

import time

import requests


def get_rated_songs(user_id: int, extra_params):
    page = 1

    params = {
        "getTotalCount": "true",
        "maxResults": "50",
        "groupByRating": "false",
        "sort": "RatingDate",
    }

    for param in extra_params:
        params[param] = extra_params[param]

    rated_songs = []

    while True:
        r = requests.get(f"https://vocadb.net/api/users/{user_id}/ratedSongs", params)
        songs_in_total = r.json()["totalCount"]
        r.raise_for_status()
        pages_total = (songs_in_total // 50) + 1
        songs = r.json()["items"]
        if not songs:
            break
        rated_songs.extend(songs)

        print(f"Page {page}/{pages_total}")

        page += 1
        params["start"] = str(50 * (page - 1))
        time.sleep(1)

    return rated_songs


if __name__ == "__main__":
    USER_ID = 
    COLUMN_DELIMITER = "£"
    LIST_DELIMITER = ","

    params = {
        "fields": "Albums, Artists, PVs, ReleaseEvent, Tags, WebLinks, CultureCodes"
    }

    # Skipped: AdditionalNames,Bpm,Lyrics,MainPicture,Names,PVs,ThumbUrl

    rated_songs = get_rated_songs(USER_ID, params)

    save_file = f"rated songs (user {USER_ID}).csv"

    simple_columns = {
        "Song id": "id",
        "Name": "defaultName",
        "Total score": "ratingScore",
        "Times favorited": "favoritedTimes",
        "Entry created": "createDate",
        "Publish date": "publishDate",
        "PV services": "pvServices",
        "Song type": "songType",
        "Entry status": "status",
    }

    headers = list(simple_columns.keys())
    headers.extend(
        [
            "Rating date",
            "Own score",
            "Tag ids",
            "Album ids",
            "Producer ids",
            "Vocalist ids",
            "Other artist ids",
            "Number of external links",
            "Languages",
        ]
    )

    with open(save_file, "w", encoding="utf8") as f:
        print(headers)
        f.write(COLUMN_DELIMITER.join(headers) + "\n")

        def list_to_string_or_zero(data: list[str]) -> str:
            return LIST_DELIMITER.join(data) if data else "0"

        for song in rated_songs:
            output_data: list[str] = []
            entry = song["song"]
            for key, value in simple_columns.items():
                try:
                    output_data.append(str(entry[value]).replace(COLUMN_DELIMITER, " "))
                except KeyError:
                    print(f"{value} not found for {entry['id']}")
                    output_data.append("?")

            output_data.append(song["date"])  # rating date

            own_score = 3 if (song["rating"] == "Favorite") else 2
            output_data.append(str(own_score))

            tag_ids = []
            if "tags" in entry:
                tag_ids = [str(tag["tag"]["id"]) for tag in entry["tags"]]
            output_data.append(list_to_string_or_zero(tag_ids))

            album_ids = [str(album["id"]) for album in entry["albums"]]
            output_data.append(list_to_string_or_zero(album_ids))

            producer_ids = []
            vocalist_ids = []
            other_artist_ids = []

            if "artists" in entry:
                for artist in entry["artists"]:
                    if "categories" in artist:
                        if artist["categories"] == "Producer":
                            producer_ids.append(str(artist["id"]))
                        elif artist["categories"] == "Vocalist":
                            vocalist_ids.append(str(artist["id"]))
                        else:
                            other_artist_ids.append(str(artist["id"]))

            output_data.append(list_to_string_or_zero(producer_ids))
            output_data.append(list_to_string_or_zero(vocalist_ids))
            output_data.append(list_to_string_or_zero(other_artist_ids))

            if "webLinks" in entry:
                output_data.append(str(len(entry["webLinks"])))
            else:
                output_data.append("0")

            output_data.append(list_to_string_or_zero(entry["cultureCodes"]))
            assert len(output_data) == len(headers)
            f.write(COLUMN_DELIMITER.join(output_data) + "\n")

Default output columns = Song id, Name, Total score, Times favorited, Entry created, Publish date, PV services, Song type, Entry status, Rating date, Own score, Tag ids, Album ids, Producer ids, Vocalist ids, Other artist ids, Number of external links, Languages

For data visualization and exploration, one easy solution is using spreadsheet programs such as Libre calc.

Moved to https://github.com/Shiroizu/VocaDB-scripts/blob/master/export-rated-song-entries-as-csv.py