mirror of
https://github.com/pirate/ArchiveBox.git
synced 2025-08-11 17:14:38 +02:00
only add url-list lines that are real urls
This commit is contained in:
@@ -1,12 +1,15 @@
|
|||||||
__package__ = 'archivebox.parsers'
|
__package__ = 'archivebox.parsers'
|
||||||
__description__ = 'URL list'
|
__description__ = 'URL list'
|
||||||
|
|
||||||
|
import re
|
||||||
|
|
||||||
from typing import IO, Iterable
|
from typing import IO, Iterable
|
||||||
from datetime import datetime
|
from datetime import datetime
|
||||||
|
|
||||||
from ..index.schema import Link
|
from ..index.schema import Link
|
||||||
from ..util import (
|
from ..util import (
|
||||||
enforce_types
|
enforce_types,
|
||||||
|
URL_REGEX,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
@@ -17,7 +20,7 @@ def parse_url_list(text_file: IO[str], **_kwargs) -> Iterable[Link]:
|
|||||||
text_file.seek(0)
|
text_file.seek(0)
|
||||||
for line in text_file.readlines():
|
for line in text_file.readlines():
|
||||||
url = line.strip()
|
url = line.strip()
|
||||||
if not url:
|
if (not url) or not re.findall(URL_REGEX, url):
|
||||||
continue
|
continue
|
||||||
|
|
||||||
yield Link(
|
yield Link(
|
||||||
|
Reference in New Issue
Block a user