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/directlink.py

57 lines
2.1 KiB
Python
Raw Normal View History

2017-05-24 12:51:18 +02:00
# -*- coding: utf-8 -*-
# Copyright 2017-2019 Mike Fährmann
2017-05-24 12:51:18 +02:00
#
# 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.
"""Direct link handling"""
from .common import Extractor, Message
from .. import text
class DirectlinkExtractor(Extractor):
"""Extractor for direct links to images and other media files"""
2017-05-24 12:51:18 +02:00
category = "directlink"
filename_fmt = "{domain}/{path}"
2018-02-12 23:09:34 +01:00
archive_fmt = "{domain}/{path}"
pattern = (r"(?i)https?://(?P<domain>[^/?&#]+)/(?P<path>[^?&#]+\."
2017-08-02 21:06:49 +02:00
r"(?:jpe?g|jpe|png|gif|web[mp]|mp4|mkv|og[gmv]|opus))"
r"(?:\?(?P<query>[^/?#]*))?(?:#(?P<fragment>.*))?$")
test = (
(("https://en.wikipedia.org/static/images/project-logos/enwiki.png"), {
"url": "18c5d00077332e98e53be9fed2ee4be66154b88d",
"keyword": "e81b9fe3022e971365dd859f38e4ef717a6c69ed",
2017-08-02 21:06:49 +02:00
}),
2018-02-26 02:12:47 +01:00
# more complex example
2017-08-02 21:06:49 +02:00
("https://example.org/path/file.webm?que=1&ry=2#fragment", {
"url": "fd4aec8a32842343394e6078a06c3e6b647bf671",
"keyword": "ff75764b1ae66615b723a6357b8193fa2de84678",
2017-08-02 21:06:49 +02:00
}),
2018-02-26 02:12:47 +01:00
# percent-encoded characters
("https://example.org/%27%3C%23/%23%3E%27.jpg?key=%3C%26%3E", {
2018-02-26 03:01:23 +01:00
"url": "2627e8140727fdf743f86fe18f69f99a052c9718",
"keyword": "4d19dc12e41ffcb4cbec2013e335cf482377c35e",
2018-02-26 02:12:47 +01:00
}),
# upper case file extension (#296)
("https://post-phinf.pstatic.net/MjAxOTA1MjlfMTQ4/MDAxNTU5MTI2NjcyNTkw"
".JUzkGb4V6dj9DXjLclrOoqR64uDxHFUO5KDriRdKpGwg.88mCtd4iT1NHlpVKSCaUpP"
"mZPiDgT8hmQdQ5K_gYyu0g.JPEG/2.JPG"),
)
2017-05-24 12:51:18 +02:00
def __init__(self, match):
Extractor.__init__(self, match)
2017-08-02 21:06:49 +02:00
self.data = match.groupdict()
2017-05-24 12:51:18 +02:00
def items(self):
2017-08-02 21:06:49 +02:00
text.nameext_from_url(self.url, self.data)
2018-02-26 02:12:47 +01:00
for key, value in self.data.items():
if value:
self.data[key] = text.unquote(value)
2017-05-24 12:51:18 +02:00
yield Message.Version, 1
2017-08-02 21:06:49 +02:00
yield Message.Directory, self.data
yield Message.Url, self.url, self.data