#!/bin/env python

import re
import os
import sys
import tempfile


usage = """Usage:
    $ bot4chan "URL_BOARD_4CHAN" ["DIRECTORY"]

    DIRECTORY is optional and by default is "dump\""""

# Use http instead of https to avoid the overhead of encryption
PROTOCOL = 'http'
REGEX = '<a class="fileThumb" href="(.*?)" target="_blank"( data-m)?>'


if len(sys.argv) <= 1 or sys.argv[1] in ['-h', '--help']:
    print(usage)
    sys.exit(0)

new_file, filename = tempfile.mkstemp()
if not new_file:
    filename = "index.html"

dumpDir = "dump"
if len(sys.argv) >= 3:
    dumpDir = sys.argv[2]

# Download the board
os.system(f"wget {sys.argv[1]} -O {filename} -N -q")
# The result is on a single line so we put line feed after every link to space markup out
# We use sed instead of python to not read the whole file
os.system(f"sed -i 's/<\\/a>/<\\/a>\\n/g' {filename}")

# Create the output directory
os.system(f"mkdir -p {dumpDir}")

# We look for a image link on each line since one line should have a uniq link
with open(filename, 'r') as f:
    for line in f:
        yes = re.search(REGEX, line)
        if yes:
            image = yes.group(1)
            print(f"Téléchargement de : {image}")
            res = os.system(f"wget {PROTOCOL}:{image} -N -q")
            if res != 0:
                print(f"💀 Error downloading imgage : {image}")
                continue
            res = os.system(f"mv {image[image.rfind('/') + 1:]} {dumpDir}")
            if res != 0:
                print(f"💀 Error moving imgage to {dumpDir}")


os.remove(filename)