# -*- coding: utf-8 -*- # Copyright 2016-2019 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. """Collection of extractors for various imagehosts""" from .common import Extractor, Message, SharedConfigMixin from .. import text, exception from ..cache import memcache from os.path import splitext class ImagehostImageExtractor(SharedConfigMixin, Extractor): """Base class for single-image extractors for various imagehosts""" basecategory = "imagehost" subcategory = "image" archive_fmt = "{token}" https = False method = "post" params = "simple" cookies = None encoding = None def __init__(self, match): Extractor.__init__(self, match) self.page_url = "http{}://{}".format( "s" if self.https else "", match.group(1)) 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 = {} self.method = "get" def items(self): page = self.request( self.page_url, method=self.method, data=self.params, cookies=self.cookies, encoding=self.encoding, ).text 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:] yield Message.Version, 1 yield Message.Directory, data yield Message.Url, url, data def get_info(self, page): """Find image-url and string to get filename from""" class ImxtoImageExtractor(ImagehostImageExtractor): """Extractor for single images from imx.to""" category = "imxto" pattern = (r"(?:https?://)?(?:www\.)?((?:imx\.to|img\.yt)" r"/(?:i/|img-)(\w+)(\.html)?)") test = ( ("https://imx.to/i/1qdeva", { # new-style URL "url": "ab2173088a6cdef631d7a47dec4a5da1c6a00130", "keyword": "1153a986c939d7aed599905588f5c940048bc517", "content": "0c8768055e4e20e7c7259608b67799171b691140", }), ("https://imx.to/img-57a2050547b97.html", { # old-style URL "url": "a83fe6ef1909a318c4d49fcf2caf62f36c3f9204", "keyword": "fd2240aee77a21b8252d5b829a1f7e542f927f09", "content": "54592f2635674c25677c6872db3709d343cdf92f", }), ("https://img.yt/img-57a2050547b97.html", { # img.yt domain "url": "a83fe6ef1909a318c4d49fcf2caf62f36c3f9204", }), ("https://imx.to/img-57a2050547b98.html", { "exception": exception.NotFoundError, }), ) https = True encoding = "utf-8" def __init__(self, match): ImagehostImageExtractor.__init__(self, match) if "/img-" in self.page_url: self.page_url = self.page_url.replace("img.yt", "imx.to") self.url_ext = True else: self.url_ext = False def get_info(self, page): url, pos = text.extract( page, '
', '', '<', pos) return url, text.unescape(filename) class TurboimagehostImageExtractor(ImagehostImageExtractor): """Extractor for single images from www.turboimagehost.com""" category = "turboimagehost" pattern = (r"(?:https?://)?((?:www\.)?turboimagehost\.com" r"/p/(\d+)/[^/?&#]+\.html)") test = ("https://www.turboimagehost.com/p/39078423/test--.png.html", { "url": "b94de43612318771ced924cb5085976f13b3b90e", "keyword": "704757ca8825f51cec516ec44c1e627c1f2058ca", "content": "0c8768055e4e20e7c7259608b67799171b691140", }) https = True params = None def get_info(self, page): url = text.extract(page, 'src="', '"', page.index("