BoardGameGeek データの Python フェッチャーを更新しました

# Import libraries
from bs4 import BeautifulSoup
from csv import DictWriter
import pandas as pd
import requests
import time

# CSV file saving function
def save_to_csv(games):
    csv_header = [
        'name', 'game_id', 'type', 'rating', 'weight', 'year_published', 'min_players', 'max_players',
        'min_play_time', 'max_play_time', 'min_age', 'owned_by', 'categories',
        'mechanics', 'designers', 'artists', 'publishers'
    ]
    with open('bgg.csv', 'a', encoding='UTF8') as f:
        dictwriter_object = DictWriter(f, fieldnames=csv_header)
        if f.tell() == 0:
            dictwriter_object.writeheader()
        dictwriter_object.writerows(games)

# Define request url headers
headers = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.16; rv:85.0) Gecko/20100101 Firefox/85.0",
    "Accept-Language": "en-GB, en-US, q=0.9, en"
}

# Define sleep timer value between requests
SLEEP_BETWEEN_REQUEST = 0

# Define max id range
start_id_range = 0
max_id_range = 403000
batch_size = 800
base_url = "https://boardgamegeek.com/xmlapi2/thing?id="

# Main loop that will iterate between the starting and maximum range in intervals of the batch size
for batch_start in range(start_id_range, max_id_range, batch_size):
    # Make sure that the batch size will not exceed the maximum ids range
    batch_end = min(batch_start + batch_size - 1, max_id_range)
    # Join and append to the url the IDs within batch size
    ids = ",".join(map(str, range(batch_start, batch_end + 1)))
    url = f"{base_url}?id={ids}&stats=1"

    # If by any chance there is an error, this will throw the exception and continue on the next batch
    try:
        response = requests.get(url, headers=headers)
    except Exception as err:
        print(err)
        continue


    if response.status_code == 200:
        soup = BeautifulSoup(response.text, features="html.parser")
        items = soup.find_all("item")
        games = []
        for item in items:
            if item:
                try:
                    # Find values in the XML
                    name = item.find("name")['value'] if item.find("name") is not None else 0
                    year_published = item.find("yearpublished")['value'] if item.find("yearpublished") is not None else 0
                    min_players = item.find("minplayers")['value'] if item.find("minplayers") is not None else 0
                    max_players = item.find("maxplayers")['value'] if item.find("maxplayers") is not None else 0
                    min_play_time = item.find("minplaytime")['value'] if item.find("minplaytime") is not None else 0
                    max_play_time = item.find("maxplaytime")['value'] if item.find("maxplaytime") is not None else 0
                    min_age = item.find("minage")['value'] if item.find("minage") is not None else 0
                    rating = item.find("average")['value'] if item.find("average") is not None else 0
                    weight = item.find("averageweight")['value'] if item.find("averageweight") is not None else 0
                    owned = item.find("owned")['value'] if item.find("owned") is not None else 0


                    link_type = {'categories': [], 'mechanics': [], 'designers': [], 'artists': [], 'publishers': []}

                    links = item.find_all("link")

                    # Append value(s) for each link type
                    for link in links:                            
                        if link['type'] == "boardgamecategory":
                            link_type['categories'].append(link['value'])
                        if link['type'] == "boardgamemechanic":
                            link_type['mechanics'].append(link['value'])
                        if link['type'] == "boardgamedesigner":
                            link_type['designers'].append(link['value'])
                        if link['type'] == "boardgameartist":
                            link_type['artists'].append(link['value'])
                        if link['type'] == "boardgamepublisher":
                            link_type['publishers'].append(link['value'])

                    # Append 0 if there is no value for any link type
                    for key, ltype in link_type.items():
                        if not ltype:
                            ltype.append("0")

                    game = {
                        "name": name,
                        "game_id": item['id'],
                        "type": item['type'],
                        "rating": rating,
                        "weight": weight,
                        "year_published": year_published,
                        "min_players": min_players,
                        "max_players": max_players,
                        "min_play_time": min_play_time,
                        "max_play_time": max_play_time,
                        "min_age": min_age,
                        "owned_by": owned,
                        "categories": ', '.join(link_type['categories']),
                        "mechanics": ', '.join(link_type['mechanics']),
                        "designers": ', '.join(link_type['designers']),
                        "artists": ', '.join(link_type['artists']),
                        "publishers": ', '.join(link_type['publishers']),
                    }

                    # Append current item to games list
                    games.append(game)
                except TypeError:
                    print(">>> NoneType error. Continued on the next item.")
                    continue
        save_to_csv(games)

        print(f">>> Request successful for batch {batch_start}-{batch_end}")
    else:
        print(f">>> FAILED batch {batch_start}-{batch_end}")

    # Pause between requests
    time.sleep(SLEEP_BETWEEN_REQUEST)

# Preview the CSV as pandas DataFrame
df = pd.read_csv('./bgg.csv')
print(df.head(5))