You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
32 lines
897 B
32 lines
897 B
# -*- coding: utf-8 -*-
|
|
|
|
# Copyright 2015-2023 Mike Fährmann
|
|
#
|
|
# This program is free software; you can redistribute it and/or modify
|
|
# it under the terms of the GNU General Public License version 2 as
|
|
# published by the Free Software Foundation.
|
|
|
|
"""Recursive extractor"""
|
|
|
|
from .common import Extractor, Message
|
|
import re
|
|
|
|
|
|
class RecursiveExtractor(Extractor):
|
|
"""Extractor that fetches URLs from a remote or local source"""
|
|
category = "recursive"
|
|
pattern = r"r(?:ecursive)?:"
|
|
example = "recursive:https://pastebin.com/raw/FLwrCYsT"
|
|
|
|
def items(self):
|
|
url = self.url.partition(":")[2]
|
|
|
|
if url.startswith("file://"):
|
|
with open(url[7:]) as fp:
|
|
page = fp.read()
|
|
else:
|
|
page = self.request(url).text
|
|
|
|
for match in re.finditer(r"https?://[^\s\"']+", page):
|
|
yield Message.Queue, match.group(0), {}
|