1
0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-23 11:12:40 +01:00
gallery-dl/gallery_dl/extractor/recursive.py

57 lines
1.7 KiB
Python
Raw Normal View History

2015-12-03 00:50:34 +01:00
# -*- coding: utf-8 -*-
# Copyright 2015-2020 Mike Fährmann
2015-12-03 00:50:34 +01:00
#
# 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.
2016-10-01 15:54:27 +02:00
"""Recursive extractor"""
2015-12-03 00:50:34 +01:00
from .common import Extractor, Message
from .. import extractor, util
import requests
import re
2015-12-03 00:50:34 +01:00
2017-02-01 00:53:19 +01:00
2016-10-01 15:54:27 +02:00
class RecursiveExtractor(Extractor):
"""Extractor that fetches URLs from a remote or local source"""
2016-10-01 15:54:27 +02:00
category = "recursive"
pattern = r"r(?:ecursive)?:"
test = ("recursive:https://pastebin.com/raw/FLwrCYsT", {
2016-10-01 15:54:27 +02:00
"url": "eee86d65c346361b818e8f4b2b307d9429f136a2",
})
2015-12-03 00:50:34 +01:00
def items(self):
blist = self.config(
"blacklist", {"directlink"} | util.SPECIAL_EXTRACTORS)
self.session.mount("file://", FileAdapter())
page = self.request(self.url.partition(":")[2]).text
del self.session.adapters["file://"]
2015-12-03 00:50:34 +01:00
yield Message.Version, 1
with extractor.blacklist(blist):
2017-05-24 12:51:18 +02:00
for match in re.finditer(r"https?://[^\s\"']+", page):
yield Message.Queue, match.group(0), {}
class FileAdapter(requests.adapters.BaseAdapter):
"""Requests adapter for local files"""
def send(self, request, **kwargs):
response = requests.Response()
try:
response.raw = open(request.url[7:], "rb")
except OSError:
import io
response.raw = io.BytesIO()
response.status_code = requests.codes.bad_request
else:
response.raw.release_conn = response.raw.close
response.status_code = requests.codes.ok
return response
def close(self):
pass