p-i- · October 15, 2024 18:47
diff --git a/messages.md b/messages.md
diff --git a/scrape.py b/scrape.py
 # pip install requests beautifulsoup4

 import requests
 from bs4 import BeautifulSoup
 import time

 BASE_URL = "https://lists.apple.com/archives/coreaudio-api"
 START_YEAR = 2000
 END_YEAR = 2024  # Update to the current year
 MONTHS = ["Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"]

 # Function to scrape messages from a single month
 def scrape_year_month(year, month):
    url = f"{BASE_URL}/{year}/{month}/index.html"

    try:
        print(f"⚡️ Fetching: {url}")
        response = requests.get(url)
        if response.status_code != 200:
            print(f"❌ Page not found: {url}")
            return []

        soup = BeautifulSoup(response.text, 'html.parser')
        topic_list = []

        # The topics are in <li> elements inside <ul>
        for li in soup.find_all('li'):
            topic_link = li.find('a')
            if topic_link:
                topic_name = topic_link.get_text().strip()

                # Only scrape topics that are valid messages and do not start with "Re:" or "Fwd:"
                if 'msg' in topic_link['href'] and not (topic_name.lower().startswith("re:") or topic_name.lower().startswith("fwd:")):
                    topic_url = f"{BASE_URL}/{year}/{month}/{topic_link['href']}"  # Full URL assembly
                    topic_list.append({
                        "topic": topic_name,
                        "url": topic_url
                    })

        return topic_list

    except Exception as e:
        print(f"❌ Error accessing {url}: {e}")
        return []

 # Function to scrape all years and months, and write the results to messages.md
 def scrape_all_years():
    with open("messages.md", "w") as f:
        for year in range(START_YEAR, END_YEAR + 1):
            year_has_content = False  # Track if there are messages for this year

            for month in MONTHS:
                topics = scrape_year_month(year, month)

                if topics:
                    # Write the year header only once
                    if not year_has_content:
                        f.write(f"# 🔸{year}\n")
                        year_has_content = True

                    # Write the month header
                    f.write(f"### 🔹{month} {year}\n")

                    # Write each topic as a markdown link
                    for topic in topics:
                        f.write(f"[{topic['topic']}]({topic['url']})\n")

                    # Pause to avoid overwhelming the server
                    time.sleep(1)

 if __name__ == "__main__":
    scrape_all_years()
    print("Scraping complete. Results written to messages.md")
	# pip install requests beautifulsoup4

	import requests
	from bs4 import BeautifulSoup
	import time

	BASE_URL = "https://lists.apple.com/archives/coreaudio-api"
	START_YEAR = 2000
	END_YEAR = 2024 # Update to the current year
	MONTHS = ["Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"]

	# Function to scrape messages from a single month
	def scrape_year_month(year, month):
	url = f"{BASE_URL}/{year}/{month}/index.html"

	try:
	print(f"⚡️ Fetching: {url}")
	response = requests.get(url)
	if response.status_code != 200:
	print(f"❌ Page not found: {url}")
	return []

	soup = BeautifulSoup(response.text, 'html.parser')
	topic_list = []

	# The topics are in <li> elements inside <ul>
	for li in soup.find_all('li'):
	topic_link = li.find('a')
	if topic_link:
	topic_name = topic_link.get_text().strip()

	# Only scrape topics that are valid messages and do not start with "Re:" or "Fwd:"
	if 'msg' in topic_link['href'] and not (topic_name.lower().startswith("re:") or topic_name.lower().startswith("fwd:")):
	topic_url = f"{BASE_URL}/{year}/{month}/{topic_link['href']}" # Full URL assembly
	topic_list.append({
	"topic": topic_name,
	"url": topic_url
	})

	return topic_list

	except Exception as e:
	print(f"❌ Error accessing {url}: {e}")
	return []

	# Function to scrape all years and months, and write the results to messages.md
	def scrape_all_years():
	with open("messages.md", "w") as f:
	for year in range(START_YEAR, END_YEAR + 1):
	year_has_content = False # Track if there are messages for this year

	for month in MONTHS:
	topics = scrape_year_month(year, month)

	if topics:
	# Write the year header only once
	if not year_has_content:
	f.write(f"# 🔸{year}\n")
	year_has_content = True

	# Write the month header
	f.write(f"### 🔹{month} {year}\n")

	# Write each topic as a markdown link
	for topic in topics:
	f.write(f"[{topic['topic']}]({topic['url']})\n")

	# Pause to avoid overwhelming the server
	time.sleep(1)

	if __name__ == "__main__":
	scrape_all_years()
	print("Scraping complete. Results written to messages.md")