mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-10-31 06:35:12 +00:00
Code Issues Projects Releases Wiki Activity

[cleanup] Misc cleanup

Browse Source
This commit is contained in:
pukkandan
2022-06-28 10:40:54 +05:30
parent 47046464fa
commit ae61d108dd
10 changed files with 65 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
yt_dlp/utils.py
View File

@@ -234,7 +234,7 @@ DATE_FORMATS_MONTH_FIRST.extend([
])
PACKED_CODES_RE = r"}\('(.+)',(\d+),(\d+),'([^']+)'\.split\('\|'\)"
JSON_LD_RE = r'(?is)<script[^>]+type=(["\']?)application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>'
JSON_LD_RE = r'(?is)<script[^>]+type=(["\']?)application/ld\+json\1[^>]*>\s*(?P<json_ld>{.+?})\s*</script>'
NUMBER_RE = r'\d+(?:\.\d+)?'
@@ -673,8 +673,8 @@ def sanitize_filename(s, restricted=False, is_id=NO_DEFAULT):
s = re.sub(r'[0-9]+(?::[0-9]+)+', lambda m: m.group(0).replace(':', '_'), s) # Handle timestamps
result = ''.join(map(replace_insane, s))
if is_id is NO_DEFAULT:
result = re.sub('(\0.)(?:(?=\\1)..)+', r'\1', result) # Remove repeated substitute chars
STRIP_RE = '(?:\0.|[ _-])*'
result = re.sub(r'(\0.)(?:(?=\1)..)+', r'\1', result) # Remove repeated substitute chars
STRIP_RE = r'(?:\0.|[ _-])*'
result = re.sub(f'^\0.{STRIP_RE}|{STRIP_RE}\0.$', '', result) # Remove substitute chars from start/end
result = result.replace('\0', '') or '_'
@@ -2400,8 +2400,7 @@ def remove_quotes(s):
def get_domain(url):
domain = re.match(r'(?:https?:\/\/)?(?:www\.)?(?P<domain>[^\n\/]+\.[^\n\/]+)(?:\/(.*))?', url)
return domain.group('domain') if domain else None
return '.'.join(urllib.parse.urlparse(url).netloc.rsplit('.', 2)[-2:])
def url_basename(url):