Laeb alla fotoalbum.ee albumeid

fotoalbum-dl.py

import urllib.request
import re

base_url = "http://fotoalbum.ee"

album = input("Sisesta fotoalbum.ee albumi link:")
album = album.split("?")[0]
if not "/sets/" in album:
    print("Hoiatus: Link pole album ning võib seetõttu valesti toimida")
pildid = []

def sanitize_filename(s, restricted=False, is_id=False):
    """Sanitizes a string so it could be used as part of a filename.
    If restricted is set, use a stricter subset of allowed characters.
    Set is_id if this is not an arbitrary string, but an ID that should be kept
    if possible.
    """
    def replace_insane(char):
        if restricted and char in ACCENT_CHARS:
            return ACCENT_CHARS[char]
        if char == '?' or ord(char) < 32 or ord(char) == 127:
            return ''
        elif char == '"':
            return '' if restricted else '\''
        elif char == ':':
            return '_-' if restricted else ' -'
        elif char in '\\/|*<>':
            return '_'
        if restricted and (char in '!&\'()[]{}$;`^,#' or char.isspace()):
            return '_'
        if restricted and ord(char) > 127:
            return '_'
        return char

    # Handle timestamps
    s = re.sub(r'[0-9]+(?::[0-9]+)+', lambda m: m.group(0).replace(':', '_'), s)
    result = ''.join(map(replace_insane, s))
    if not is_id:
        while '__' in result:
            result = result.replace('__', '_')
        result = result.strip('_')
        # Common case of "Foreign band name - English song title"
        if restricted and result.startswith('-_'):
            result = result[2:]
        if result.startswith('-'):
            result = '_' + result[len('-'):]
        result = result.lstrip('.')
        if not result:
            result = '_'
    return result

i = 1
while True:
    print(f"Laeb albumi lehte {i}")
    r = urllib.request.urlopen(f"{album}?page={i}").read().decode("utf-8")
    lingid = re.findall(r"/photos/[^\/]+/[0-9]+",r)
    pildid += lingid
    if len(lingid) == 0:
        break
    i+=1

print(f"Leitud {len(pildid)} pilti")

for pilt in pildid:
    r = urllib.request.urlopen(f"{base_url}{pilt}").read().decode("utf-8")
    results = re.search(r'<img src="([^"]*)" border="[0-9]*" alt="([^"]*)" vspace="[0-9]*">', r)
    dlurl = f"http:{results.group(1)}"
    filename = sanitize_filename(results.group(2))
    print(filename)
    ext = dlurl.split(".")[-1]
    if not filename.endswith(f".{ext}"):
        filename += f".{ext}"
    urllib.request.urlretrieve (dlurl, filename)