[dl:http] improve HTML signature check (#7697)

https://github.com/mikf/gallery-dl/issues/7697#issuecomment-2990734451 ignore leading whitespace
2025-06-20 14:39:32 +02:00
parent dba45923c8
commit bcfce6b7db
2 changed files with 3 additions and 1 deletions
--- a/gallery_dl/downloader/http.py
+++ b/gallery_dl/downloader/http.py
@@ -486,7 +486,8 @@ MIME_TYPES = {


 def _signature_html(s):
-    return b"<!doctype html".startswith(s[:14].lower())
+    s = s[:14].lstrip()
+    return s and b"<!doctype html".startswith(s.lower())


 # https://en.wikipedia.org/wiki/List_of_file_signatures
--- a/test/test_downloader.py
+++ b/test/test_downloader.py
@@ -370,6 +370,7 @@ SAMPLES = {
    ("heic", b"????ftypheix"),
    ("svg" , b"<?xml"),
    ("html", b"<!DOCTYPE html><html>...</html>"),
+    ("html", b"  \n  \n\r\t\n  <!DOCTYPE html><html>...</html>"),
    ("ico" , b"\x00\x00\x01\x00"),
    ("cur" , b"\x00\x00\x02\x00"),
    ("psd" , b"8BPS"),