2016-11-03 15:46:04 +01:00
|
|
|
# -*- coding: utf-8 -*-
|
|
|
|
|
2019-01-09 14:21:19 +01:00
|
|
|
# Copyright 2016-2019 Mike Fährmann
|
2016-11-03 15:46:04 +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.
|
|
|
|
|
2016-11-03 18:14:33 +01:00
|
|
|
"""Collection of extractors for various imagehosts"""
|
2016-11-03 15:46:04 +01:00
|
|
|
|
2019-02-06 17:37:56 +01:00
|
|
|
from .common import Extractor, Message, SharedConfigMixin
|
2017-02-02 15:52:48 +01:00
|
|
|
from .. import text, exception
|
2018-02-22 23:50:50 +01:00
|
|
|
from ..cache import memcache
|
2016-11-03 15:46:04 +01:00
|
|
|
from os.path import splitext
|
|
|
|
|
2017-02-01 00:53:19 +01:00
|
|
|
|
2019-02-06 17:37:56 +01:00
|
|
|
class ImagehostImageExtractor(SharedConfigMixin, Extractor):
|
2016-11-03 18:14:33 +01:00
|
|
|
"""Base class for single-image extractors for various imagehosts"""
|
2019-02-06 17:37:56 +01:00
|
|
|
basecategory = "imagehost"
|
2016-11-03 15:46:04 +01:00
|
|
|
subcategory = "image"
|
2018-01-30 22:49:16 +01:00
|
|
|
archive_fmt = "{token}"
|
2016-11-03 15:46:04 +01:00
|
|
|
https = False
|
|
|
|
method = "post"
|
|
|
|
params = "simple"
|
2016-11-09 12:03:14 +01:00
|
|
|
cookies = None
|
2018-04-09 15:53:20 +02:00
|
|
|
encoding = None
|
2016-11-03 15:46:04 +01:00
|
|
|
|
|
|
|
def __init__(self, match):
|
2019-02-11 13:31:10 +01:00
|
|
|
Extractor.__init__(self, match)
|
2019-02-12 10:20:21 +01:00
|
|
|
self.page_url = "http{}://{}".format(
|
|
|
|
"s" if self.https else "", match.group(1))
|
2016-11-03 15:46:04 +01:00
|
|
|
self.token = match.group(2)
|
|
|
|
if self.params == "simple":
|
|
|
|
self.params = {
|
|
|
|
"imgContinue": "Continue+to+image+...+",
|
|
|
|
}
|
|
|
|
elif self.params == "complex":
|
|
|
|
self.params = {
|
|
|
|
"op": "view",
|
|
|
|
"id": self.token,
|
|
|
|
"pre": "1",
|
|
|
|
"adb": "1",
|
|
|
|
"next": "Continue+to+image+...+",
|
|
|
|
}
|
|
|
|
else:
|
|
|
|
self.params = {}
|
2016-11-04 09:33:38 +01:00
|
|
|
self.method = "get"
|
2016-11-03 15:46:04 +01:00
|
|
|
|
|
|
|
def items(self):
|
2018-04-09 15:53:20 +02:00
|
|
|
page = self.request(
|
2019-02-12 10:20:21 +01:00
|
|
|
self.page_url,
|
2018-04-09 15:53:20 +02:00
|
|
|
method=self.method,
|
|
|
|
data=self.params,
|
|
|
|
cookies=self.cookies,
|
|
|
|
encoding=self.encoding,
|
|
|
|
).text
|
|
|
|
|
2016-11-03 15:46:04 +01:00
|
|
|
url, filename = self.get_info(page)
|
|
|
|
data = text.nameext_from_url(filename, {"token": self.token})
|
|
|
|
if self.https and url.startswith("http:"):
|
|
|
|
url = "https:" + url[5:]
|
2018-04-09 15:53:20 +02:00
|
|
|
|
2016-11-03 15:46:04 +01:00
|
|
|
yield Message.Version, 1
|
|
|
|
yield Message.Directory, data
|
|
|
|
yield Message.Url, url, data
|
|
|
|
|
2016-11-03 18:14:33 +01:00
|
|
|
def get_info(self, page):
|
|
|
|
"""Find image-url and string to get filename from"""
|
|
|
|
|
2016-11-03 15:46:04 +01:00
|
|
|
|
2018-04-09 15:53:20 +02:00
|
|
|
class ImxtoImageExtractor(ImagehostImageExtractor):
|
|
|
|
"""Extractor for single images from imx.to"""
|
|
|
|
category = "imxto"
|
2019-02-08 13:45:40 +01:00
|
|
|
pattern = (r"(?:https?://)?(?:www\.)?((?:imx\.to|img\.yt)"
|
|
|
|
r"/(?:i/|img-)(\w+)(\.html)?)")
|
2019-02-06 17:37:56 +01:00
|
|
|
test = (
|
2018-04-09 15:53:20 +02:00
|
|
|
("https://imx.to/i/1qdeva", { # new-style URL
|
|
|
|
"url": "ab2173088a6cdef631d7a47dec4a5da1c6a00130",
|
2019-02-14 16:07:17 +01:00
|
|
|
"keyword": "1153a986c939d7aed599905588f5c940048bc517",
|
2018-04-09 15:53:20 +02:00
|
|
|
"content": "0c8768055e4e20e7c7259608b67799171b691140",
|
|
|
|
}),
|
|
|
|
("https://imx.to/img-57a2050547b97.html", { # old-style URL
|
|
|
|
"url": "a83fe6ef1909a318c4d49fcf2caf62f36c3f9204",
|
2019-02-14 16:07:17 +01:00
|
|
|
"keyword": "fd2240aee77a21b8252d5b829a1f7e542f927f09",
|
2017-02-02 15:52:48 +01:00
|
|
|
"content": "54592f2635674c25677c6872db3709d343cdf92f",
|
|
|
|
}),
|
2018-04-09 15:53:20 +02:00
|
|
|
("https://img.yt/img-57a2050547b97.html", { # img.yt domain
|
|
|
|
"url": "a83fe6ef1909a318c4d49fcf2caf62f36c3f9204",
|
|
|
|
}),
|
|
|
|
("https://imx.to/img-57a2050547b98.html", {
|
2017-02-02 15:52:48 +01:00
|
|
|
"exception": exception.NotFoundError,
|
|
|
|
}),
|
2019-02-06 17:37:56 +01:00
|
|
|
)
|
2016-11-03 15:46:04 +01:00
|
|
|
https = True
|
2018-04-09 15:53:20 +02:00
|
|
|
encoding = "utf-8"
|
|
|
|
|
|
|
|
def __init__(self, match):
|
|
|
|
ImagehostImageExtractor.__init__(self, match)
|
2019-02-12 10:20:21 +01:00
|
|
|
if "/img-" in self.page_url:
|
|
|
|
self.page_url = self.page_url.replace("img.yt", "imx.to")
|
|
|
|
self.url_ext = True
|
2018-04-09 15:53:20 +02:00
|
|
|
else:
|
2019-02-12 10:20:21 +01:00
|
|
|
self.url_ext = False
|
2016-11-03 15:46:04 +01:00
|
|
|
|
|
|
|
def get_info(self, page):
|
2018-04-09 15:53:20 +02:00
|
|
|
url, pos = text.extract(
|
|
|
|
page, '<div style="text-align:center;"><a href="', '"')
|
2017-02-02 15:52:48 +01:00
|
|
|
if not url:
|
|
|
|
raise exception.NotFoundError("image")
|
2018-04-09 15:53:20 +02:00
|
|
|
filename, pos = text.extract(page, ' title="', '"', pos)
|
2019-02-12 10:20:21 +01:00
|
|
|
if self.url_ext and filename:
|
2018-04-09 15:53:20 +02:00
|
|
|
filename += splitext(url)[1]
|
|
|
|
return url, filename or url
|
2016-11-03 15:46:04 +01:00
|
|
|
|
2017-02-01 00:53:19 +01:00
|
|
|
|
2018-04-09 15:53:20 +02:00
|
|
|
class AcidimgImageExtractor(ImagehostImageExtractor):
|
2017-09-09 15:17:51 +02:00
|
|
|
"""Extractor for single images from acidimg.cc"""
|
|
|
|
category = "acidimg"
|
2019-02-08 13:45:40 +01:00
|
|
|
pattern = r"(?:https?://)?((?:www\.)?acidimg\.cc/img-([a-z0-9]+)\.html)"
|
2019-02-06 17:37:56 +01:00
|
|
|
test = ("https://acidimg.cc/img-5acb6b9de4640.html", {
|
2018-04-09 15:53:20 +02:00
|
|
|
"url": "f132a630006e8d84f52d59555191ed82b3b64c04",
|
2019-02-14 16:07:17 +01:00
|
|
|
"keyword": "a8bb9ab8b2f6844071945d31f8c6e04724051f37",
|
2018-04-09 15:53:20 +02:00
|
|
|
"content": "0c8768055e4e20e7c7259608b67799171b691140",
|
2019-02-06 17:37:56 +01:00
|
|
|
})
|
2018-04-09 15:53:20 +02:00
|
|
|
https = True
|
|
|
|
encoding = "utf-8"
|
|
|
|
|
|
|
|
def get_info(self, page):
|
|
|
|
url, pos = text.extract(page, "<img class='centred' src='", "'")
|
|
|
|
if not url:
|
|
|
|
raise exception.NotFoundError("image")
|
|
|
|
filename, pos = text.extract(page, " alt='", "'", pos)
|
|
|
|
return url, (filename + splitext(url)[1]) if filename else url
|
2017-09-09 15:17:51 +02:00
|
|
|
|
|
|
|
|
2016-11-28 22:30:00 +01:00
|
|
|
class ImagevenueImageExtractor(ImagehostImageExtractor):
|
|
|
|
"""Extractor for single images from imagevenue.com"""
|
|
|
|
category = "imagevenue"
|
2019-02-08 13:45:40 +01:00
|
|
|
pattern = (r"(?:https?://)?(img\d+\.imagevenue\.com"
|
|
|
|
r"/img\.php\?image=(?:[a-z]+_)?(\d+)_[^&#]+)")
|
2019-02-06 17:37:56 +01:00
|
|
|
test = (("http://img28116.imagevenue.com/img.php"
|
|
|
|
"?image=th_52709_test_122_64lo.jpg"), {
|
|
|
|
"url": "46812995d557f2c6adf0ebd0e631e6e4e45facde",
|
|
|
|
"content": "59ec819cbd972dd9a71f25866fbfc416f2f215b3",
|
|
|
|
})
|
2016-11-28 22:30:00 +01:00
|
|
|
params = None
|
|
|
|
|
|
|
|
def get_info(self, page):
|
2019-02-06 17:37:56 +01:00
|
|
|
url = text.extract(page, "SRC='", "'")[0]
|
2019-02-12 10:20:21 +01:00
|
|
|
return text.urljoin(self.page_url, url), url
|
2016-11-28 22:30:00 +01:00
|
|
|
|
|
|
|
|
2016-11-04 09:33:38 +01:00
|
|
|
class ImagetwistImageExtractor(ImagehostImageExtractor):
|
|
|
|
"""Extractor for single images from imagetwist.com"""
|
|
|
|
category = "imagetwist"
|
2019-02-08 13:45:40 +01:00
|
|
|
pattern = r"(?:https?://)?((?:www\.)?imagetwist\.com/([a-z0-9]{12}))"
|
2019-02-06 17:37:56 +01:00
|
|
|
test = ("https://imagetwist.com/4e46hv31tu0q/test.jpg", {
|
2017-06-24 16:21:00 +02:00
|
|
|
"url": "c999dc1a5dec0525ac9eb8c092f173dfe6dba0b0",
|
2019-02-14 16:07:17 +01:00
|
|
|
"keyword": "a9f2e01757ec96d4ee4752cbd8446ede80f7935e",
|
2016-11-04 09:33:38 +01:00
|
|
|
"content": "96b1fd099b06faad5879fce23a7e4eb8290d8810",
|
2019-02-06 17:37:56 +01:00
|
|
|
})
|
2017-06-24 16:21:00 +02:00
|
|
|
https = True
|
2016-11-03 15:46:04 +01:00
|
|
|
params = None
|
|
|
|
|
2017-02-08 22:59:00 +01:00
|
|
|
@property
|
2019-03-14 22:21:49 +01:00
|
|
|
@memcache(maxage=3*3600)
|
2017-02-08 22:59:00 +01:00
|
|
|
def cookies(self):
|
2019-02-12 10:20:21 +01:00
|
|
|
return self.request(self.page_url).cookies
|
2017-02-08 22:59:00 +01:00
|
|
|
|
2016-11-03 15:46:04 +01:00
|
|
|
def get_info(self, page):
|
2016-11-04 09:33:38 +01:00
|
|
|
url , pos = text.extract(page, 'center;"><img src="', '"')
|
|
|
|
filename, pos = text.extract(page, ' alt="', '"', pos)
|
2016-11-03 15:46:04 +01:00
|
|
|
return url, filename
|
|
|
|
|
2016-11-04 09:33:38 +01:00
|
|
|
|
|
|
|
class ImgspiceImageExtractor(ImagehostImageExtractor):
|
|
|
|
"""Extractor for single images from imgspice.com"""
|
|
|
|
category = "imgspice"
|
2019-02-08 13:45:40 +01:00
|
|
|
pattern = r"(?:https?://)?((?:www\.)?imgspice\.com/([^/?&#]+))"
|
2019-03-09 20:29:23 +01:00
|
|
|
test = ("https://imgspice.com/nwfwtpyog50y/test.png.html", {
|
|
|
|
"url": "b8c30a8f51ee1012959a4cfd46197fabf14de984",
|
|
|
|
"keyword": "100e310a19a2fa22d87e1bbc427ecb9f6501e0c0",
|
|
|
|
"content": "0c8768055e4e20e7c7259608b67799171b691140",
|
2019-02-06 17:37:56 +01:00
|
|
|
})
|
2016-11-04 09:33:38 +01:00
|
|
|
https = True
|
|
|
|
params = None
|
|
|
|
|
|
|
|
def get_info(self, page):
|
2019-03-09 20:29:23 +01:00
|
|
|
pos = page.find('id="imgpreview"')
|
|
|
|
if pos < 0:
|
|
|
|
raise exception.NotFoundError("image")
|
|
|
|
url , pos = text.extract(page, 'src="', '"', pos)
|
|
|
|
name, pos = text.extract(page, 'alt="', '"', pos)
|
|
|
|
return url, text.unescape(name)
|
2017-03-21 15:47:51 +01:00
|
|
|
|
|
|
|
|
2016-11-09 12:03:14 +01:00
|
|
|
class PixhostImageExtractor(ImagehostImageExtractor):
|
2018-05-23 18:32:34 +02:00
|
|
|
"""Extractor for single images from pixhost.to"""
|
2016-11-09 12:03:14 +01:00
|
|
|
category = "pixhost"
|
2019-02-08 13:45:40 +01:00
|
|
|
pattern = (r"(?:https?://)?((?:www\.)?pixhost\.(?:to|org)"
|
|
|
|
r"/show/\d+/(\d+)_[^/?&#]+)")
|
2019-02-06 17:37:56 +01:00
|
|
|
test = ("https://pixhost.to/show/224/96246707_test-.png", {
|
|
|
|
"url": "8f3d41fdd2dbec4c844e5ee45bf49961fbd79c67",
|
2019-02-14 16:07:17 +01:00
|
|
|
"keyword": "ecefe2d5814286f9d1dff3d88d9bdc78dd456c5d",
|
2019-02-06 17:37:56 +01:00
|
|
|
"content": "0c8768055e4e20e7c7259608b67799171b691140",
|
|
|
|
})
|
2016-12-06 10:03:33 +01:00
|
|
|
https = True
|
2016-11-09 12:03:14 +01:00
|
|
|
params = None
|
|
|
|
cookies = {"pixhostads": "1", "pixhosttest": "1"}
|
|
|
|
|
|
|
|
def get_info(self, page):
|
2017-04-21 13:54:10 +02:00
|
|
|
url , pos = text.extract(page, "class=\"image-img\" src=\"", "\"")
|
|
|
|
filename, pos = text.extract(page, "alt=\"", "\"", pos)
|
2016-12-06 10:03:33 +01:00
|
|
|
return url, filename
|
2016-11-09 12:03:14 +01:00
|
|
|
|
|
|
|
|
2016-12-06 12:46:41 +01:00
|
|
|
class PostimgImageExtractor(ImagehostImageExtractor):
|
2019-01-30 16:18:22 +01:00
|
|
|
"""Extractor for single images from postimages.org"""
|
2016-12-06 12:46:41 +01:00
|
|
|
category = "postimg"
|
2019-02-08 13:45:40 +01:00
|
|
|
pattern = (r"(?:https?://)?((?:www\.)?(?:postimg|pixxxels)\.(?:cc|org)"
|
|
|
|
r"/(?:image/)?([^/?&#]+)/?)")
|
2019-02-06 17:37:56 +01:00
|
|
|
test = ("https://postimg.cc/Wtn2b3hC", {
|
|
|
|
"url": "0794cfda9b8951a8ac3aa692472484200254ab86",
|
2019-02-14 16:07:17 +01:00
|
|
|
"keyword": "2d05808d04e4e83e33200db83521af06e3147a84",
|
2019-02-06 17:37:56 +01:00
|
|
|
"content": "cfaa8def53ed1a575e0c665c9d6d8cf2aac7a0ee",
|
|
|
|
})
|
2016-12-06 12:46:41 +01:00
|
|
|
https = True
|
|
|
|
params = None
|
|
|
|
|
|
|
|
def get_info(self, page):
|
2019-02-06 17:37:56 +01:00
|
|
|
url , pos = text.extract(page, 'id="main-image" src="', '"')
|
|
|
|
filename, pos = text.extract(page, 'class="imagename">', '<', pos)
|
|
|
|
return url, text.unescape(filename)
|
2016-12-06 12:46:41 +01:00
|
|
|
|
|
|
|
|
2016-11-04 09:33:38 +01:00
|
|
|
class TurboimagehostImageExtractor(ImagehostImageExtractor):
|
2019-02-08 20:08:16 +01:00
|
|
|
"""Extractor for single images from www.turboimagehost.com"""
|
2016-11-04 09:33:38 +01:00
|
|
|
category = "turboimagehost"
|
2019-02-08 13:45:40 +01:00
|
|
|
pattern = (r"(?:https?://)?((?:www\.)?turboimagehost\.com"
|
|
|
|
r"/p/(\d+)/[^/?&#]+\.html)")
|
2019-02-06 17:37:56 +01:00
|
|
|
test = ("https://www.turboimagehost.com/p/39078423/test--.png.html", {
|
2018-08-02 14:51:51 +02:00
|
|
|
"url": "b94de43612318771ced924cb5085976f13b3b90e",
|
2019-02-14 16:07:17 +01:00
|
|
|
"keyword": "704757ca8825f51cec516ec44c1e627c1f2058ca",
|
2016-11-04 09:33:38 +01:00
|
|
|
"content": "0c8768055e4e20e7c7259608b67799171b691140",
|
2019-02-06 17:37:56 +01:00
|
|
|
})
|
2018-03-06 14:25:10 +01:00
|
|
|
https = True
|
2016-11-04 09:33:38 +01:00
|
|
|
params = None
|
|
|
|
|
|
|
|
def get_info(self, page):
|
2018-10-23 21:01:51 +02:00
|
|
|
url = text.extract(page, 'src="', '"', page.index("<img "))[0]
|
2016-11-04 09:33:38 +01:00
|
|
|
return url, url
|