Files
forth_bootslop/fetch_blog.py
2026-02-19 16:09:48 -05:00

44 lines
1.4 KiB
Python

import csv
import os
import requests
from markdownify import markdownify as md
CSV_PATH = "C:/projects/forth/bootslop/references/TimothyLottesBlog.csv"
OUT_DIR = "C:/projects/forth/bootslop/references/TimothyLottesBlog"
os.makedirs(OUT_DIR, exist_ok=True)
with open(CSV_PATH, "r", encoding="utf-8") as f:
reader = csv.reader(f)
for row in reader:
if len(row) < 2:
continue
title = row[0].strip()
url = row[1].strip()
# Clean up title for filename
filename = "".join(c for c in title if c.isalnum() or c in (' ', '-', '_')).strip()
filename = filename.replace(' ', '_') + ".md"
out_path = os.path.join(OUT_DIR, filename)
if os.path.exists(out_path):
print(f"Already exists: {filename}")
continue
print(f"Fetching: {title}")
try:
response = requests.get(url)
response.raise_for_status()
# Convert HTML to markdown
markdown_text = md(response.text, heading_style="ATX")
with open(out_path, "w", encoding="utf-8") as out_f:
out_f.write(f"# {title}\n\n")
out_f.write(f"**Source:** {url}\n\n")
out_f.write(markdown_text)
print(f"Saved: {filename}")
except Exception as e:
print(f"Failed to fetch {title}: {e}")