パケ画像を自動で全部落とすやつ （https://psxdatacenter.com/ntsc-j_list.html）

PS1-scraping.py

from bs4 import BeautifulSoup
import requests
import urllib
import re
import os
import unicodedata


def _path_executable_kai(moji: str) -> str:
    moji = moji.replace("/", "／")
    moji = moji.replace("\\", "＼")
    moji = moji.replace("?", "？")
    moji = moji.replace("\n", "_")
    moji = moji.replace(":", "：")
    moji = moji.replace("\"", "”")
    moji = moji.replace("<", "＜")
    moji = moji.replace(">", "＞")
    moji = moji.replace("|", "｜")
    moji = moji.replace("*", "＊")
    moji = moji.replace("\r", "")
    moji = moji.replace("\t", "")
    moji = moji.replace("\xa0", "")
    return moji

def main():
    #! ※注意 requestsが<frame>に対応していないっぽいのでjlist.htmlを直で叩くようにした
    #? root_page = requests.get(r"https://psxdatacenter.com/ntsc-j_list.html")
    root_page = requests.get(r"https://psxdatacenter.com/jlist.html")
    root_image = r"https://psxdatacenter.com/images/covers/"
    soup = BeautifulSoup(root_page.text, "html.parser")
    # print(soup.prettify())
    os.makedirs("PS1_covers", exist_ok=True)
    os.chdir("PS1_covers")
    for table in soup.select("table[class='sectiontable']"):
        for tr in table.select("tr"):
            if tr.select_one("a[target='jlist']") is not None:
                #python3.8未満でも動くように修正
                _img_url = urllib.parse.urljoin(root_image, re.sub(r"html$", "jpg", re.sub(r"games/", "", tr.select_one("a[target='jlist']").get("href"))))
                _img = requests.get(_img_url)
                
                _img_name = _img_url.split("/")[-1][:-4] + "__(" +  re.sub("^ ", "", _path_executable_kai(unicodedata.normalize("NFKD", (tr.select_one("td[class='col3']").get_text())))) + ")" + ".jpg"
                
                print(_img_url)
                print(_img_name)
                
                if _img.status_code == 200:
                    with open(_img_name, "wb") as f:
                        f.write(_img.content)
                else:
                    with open(_img_name, "wb") as f:
                        f.write(requests.get("https://psxdatacenter.com/images/covers/none.jpg").content)



if __name__ == "__main__":
    main()