Last active
June 2, 2023 14:07
-
-
Save amane-katagiri/7402ed1ddabf9050868c013a45690087 to your computer and use it in GitHub Desktop.
CSVっぽいテキストからAtomフィードを生成する
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
# ##### つかいかた ##### | |
# | |
# 実行前に `pip install feedgenerator` でライブラリをインストールしてください | |
# | |
# 例1: ./feedgen.py | |
# => サンプル入力からフィードを生成して標準出力に表示します | |
# 例2: ./feedgen.py input.txt | |
# => input.txtの内容からフィードを生成して標準出力に表示します | |
# 例3: ./feedgen.py input.txt output.txt | |
# => input.txtの内容からフィードを生成してoutput.txtに書き出します | |
from datetime import datetime | |
import sys | |
import xml.dom.minidom | |
from feedgenerator import Atom1Feed, get_tag_uri | |
def _load_config(config: str) -> [dict, dict]: | |
site_metadata, items = config.strip().split("\n\n", 1) | |
site_metadata = dict( | |
map( | |
lambda x: x.split(": "), site_metadata.split("\n") | |
) | |
) | |
header, items = items.split("\n", 1) | |
header = header.split(",") | |
items = list( | |
map( | |
lambda x: dict( | |
zip( | |
header, | |
map(lambda x: x.strip('"'), x.split('","')) | |
) | |
), items.split("\n") | |
) | |
) | |
return site_metadata, items | |
def generate_feed(config: str) -> str: | |
site_metadata, items = _load_config(config) | |
feed = Atom1Feed( | |
title=site_metadata["TITLE"], | |
link=site_metadata["LINK"], | |
feed_url=site_metadata["FEED_URL"], | |
description=site_metadata["DESCRIPTION"] | |
) | |
for item in reversed(sorted(items, key=lambda x: x["date"])): | |
pubdate = datetime.fromisoformat(item["date"]) | |
feed.add_item( | |
title=item["title"], | |
link=item["link"], | |
unique_id=get_tag_uri(item["link"], pubdate), | |
description=item["description"], | |
author_name=item["author"], | |
pubdate=pubdate | |
) | |
return xml.dom.minidom.parseString( | |
feed.writeString("utf-8") | |
).toprettyxml() | |
if __name__ == "__main__": | |
if len(sys.argv) > 1: | |
with open(sys.argv[1], encoding="utf-8") as f: | |
result = generate_feed(f.read()) | |
else: | |
result = generate_feed( | |
""" | |
TITLE: サイトタイトル | |
LINK: https://example.com/ | |
FEED_URL: https://example.com/feed.xml | |
DESCRIPTION: サイトの説明 | |
date,title,author,link,description | |
"2021-01-01 00:00:00+09:00","タイトル1","作者名","https://example.com/post/1","面白い記事です" | |
"2022-12-31 12:34:56+09:00","タイトル2","作者名","https://example.com/post/2","楽しい記事です" | |
"2023-05-27 01:23:45+09:00","タイトル3","作者名","https://example.com/post/3","最新の記事です" | |
""" | |
) | |
if len(sys.argv) > 2: | |
with open(sys.argv[2], "w", encoding="utf-8") as f: | |
f.write(result) | |
else: | |
print(result) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment