import csv
from bs4 import BeautifulSoup
from tkinter import Tk, filedialog

# --- Step 0: ask for main keyword ---
mkwrd = input("Main keyword? ").strip()

# --- Step 1: ask user to select the HTML file ---
Tk().withdraw()
filename = filedialog.askopenfilename(
    title="Select HTML file",
    filetypes=[("HTML Files", "*.html"), ("All Files", "*.*")]
)
if not filename:
    print("❌ No file selected. Exiting.")
    exit()

# --- Step 2: read HTML file (UTF-8 with BOM support) ---
with open(filename, "r", encoding="utf-8") as f:
    soup = BeautifulSoup(f, "html.parser")

# --- Step 3: define CSV schema ---
headers = [
    "note_id", "Type", "Label", "URL", "Content", "Keywords",
    "Media URL", "Media Type", "Media File Name", "Emoji", "Position"
]
# add label_1,link_1 ... label_10,link_10
for i in range(1, 11):
    headers.append(f"label_{i}")
    headers.append(f"link_{i}")

rows = []

# --- Step 4: process <li> elements ---
for pos, li in enumerate(soup.find_all("li"), start=1):
    anchors = li.find_all("a")
    images = li.find_all("img")

    # First anchor = main Label + URL
    label = anchors[0].get_text(strip=True) if anchors else ""
    url = anchors[0]["href"] if anchors and anchors[0].has_attr("href") else ""

    # Other anchors = label_n + link_n
    link_data = []
    for a in anchors[1:11]:  # up to 10 additional
        lbl = a.get_text(strip=True)
        href = a["href"] if a.has_attr("href") else ""
        link_data.append((lbl, href))

    # pad missing slots with blanks
    while len(link_data) < 10:
        link_data.append(("", ""))

    # Image handling
    media_url = images[0]["src"] if images and images[0].has_attr("src") else ""
    media_type = "image" if media_url else ""
    media_file_name = media_url.split("/")[-1] if media_url else ""

    row = [
        "",  # note_id blank
        "link",  # default Type
        label,
        url,
        li.get_text(" ", strip=True),  # Content = text of li
        mkwrd,  # Keywords = main keyword
        media_url,
        media_type,
        media_file_name,
        "",  # Emoji
        pos   # Position
    ]

    # Add label_1,link_1 ... label_10,link_10
    for lbl, href in link_data:
        row.extend([lbl, href])

    # Replace "" with null
    row = [val if val != "" else "null" for val in row]

    rows.append(row)

# --- Step 5: write CSV with BOM for Excel ---
out_file = filename.rsplit(".", 1)[0] + "_converted.csv"
with open(out_file, "w", newline="", encoding="utf-8-sig") as csvfile:
    writer = csv.writer(csvfile)
    writer.writerow(headers)
    writer.writerows(rows)

print(f"✅ Conversion complete. CSV saved as: {out_file}")