Ignore BOM in batch files (Fixes #2450)

test/test_utils.py

@@ -9,6 +9,7 @@
 
 
 # Various small unit tests
+import io
 import xml.etree.ElementTree
 
 #from youtube_dl.utils import htmlentity_transform
@@ -21,6 +22,7 @@
     orderedSet,
     PagedList,
     parse_duration,
+    read_batch_urls,
     sanitize_filename,
     shell_quote,
     smuggle_url,
@@ -250,5 +252,14 @@ def get_page(pagenum):
     def test_struct_unpack(self):
         self.assertEqual(struct_unpack(u'!B', b'\x00'), (0,))
 
+    def test_read_batch_urls(self):
+        f = io.StringIO(u'''\xef\xbb\xbf foo
+            bar\r
+            baz
+            # More after this line\r
+            ; or after this
+            bam''')
+        self.assertEqual(read_batch_urls(f), [u'foo', u'bar', u'baz', u'bam'])
+
 if __name__ == '__main__':
     unittest.main()

youtube_dl/__init__.py

@@ -71,6 +71,7 @@
     get_cachedir,
     MaxDownloadsReached,
     preferredencoding,
+    read_batch_urls,
     SameFileError,
     setproctitle,
     std_headers,
@@ -552,21 +553,19 @@ def _real_main(argv=None):
         sys.exit(0)
 
     # Batch file verification
-    batchurls = []
+    batch_urls = []
     if opts.batchfile is not None:
         try:
             if opts.batchfile == '-':
                 batchfd = sys.stdin
             else:
-                batchfd = open(opts.batchfile, 'r')
-            batchurls = batchfd.readlines()
-            batchurls = [x.strip() for x in batchurls]
-            batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]
+                batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore')
+            batch_urls = read_batch_urls(batchfd)
             if opts.verbose:
-                write_string(u'[debug] Batch file urls: ' + repr(batchurls) + u'\n')
+                write_string(u'[debug] Batch file urls: ' + repr(batch_urls) + u'\n')
         except IOError:
             sys.exit(u'ERROR: batch file could not be read')
-    all_urls = batchurls + args
+    all_urls = batch_urls + args
     all_urls = [url.strip() for url in all_urls]
     _enc = preferredencoding()
     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]

youtube_dl/utils.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
+import contextlib
 import ctypes
 import datetime
 import email.utils
@@ -1245,3 +1246,19 @@ def struct_unpack(spec, *args):
 else:
     struct_pack = struct.pack
     struct_unpack = struct.unpack
+
+
+def read_batch_urls(batch_fd):
+    def fixup(url):
+        if not isinstance(url, compat_str):
+            url = url.decode('utf-8', 'replace')
+        BOM_UTF8 = u'\xef\xbb\xbf'
+        if url.startswith(BOM_UTF8):
+            url = url[len(BOM_UTF8):]
+        url = url.strip()
+        if url.startswith(('#', ';', ']')):
+            return False
+        return url
+
+    with contextlib.closing(batch_fd) as fd:
+        return [url for url in map(fixup, fd) if url]