gallery-dl/gallery_dl/extractor/imagehosts.py

# -*- coding: utf-8 -*-

# Copyright 2016 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
from .. import text
from os.path import splitext

class ImagehostImageExtractor(Extractor):
    """Base class for single-image extractors for various imagehosts"""
    subcategory = "image"
    directory_fmt = ["{category}"]
    filename_fmt = "{filename}"
    https = False
    method = "post"
    params = "simple"

    def __init__(self, match):
        Extractor.__init__(self)
        self.url = ("https://" if self.https else "http://") + 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.url, method=self.method, data=self.params).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"""
        return "url", "filename"


class ImgytImageExtractor(ImagehostImageExtractor):
    """Extractor for single images from img.yt"""
    category = "imgyt"
    pattern = [r"(?:https?://)?((?:www\.)?img\.yt/img-([a-z0-9]+)\.html)"]
    test = [("https://img.yt/img-57a2050547b97.html", {
        "url": "6801fac1ff8335bd27a1665ad27ad64cace2cd84",
        "keyword": "7548cc9915f90f5d7ffbafa079085457ae34562c",
        "content": "54592f2635674c25677c6872db3709d343cdf92f",
    })]
    https = True

    def get_info(self, page):
        url     , pos = text.extract(page, "<img class='centred' src='", "'")
        filename, pos = text.extract(page, " alt='", "'", pos)
        return url, filename + splitext(url)[1]

class RapidimgImageExtractor(ImgytImageExtractor):
    """Extractor for single images from rapidimg.net"""
    category = "rapidimg"
    pattern = [r"(?:https?://)?((?:www\.)?rapidimg\.net/img-([a-z0-9]+)\.html)"]
    test = []
    https = False


class ChronosImageExtractor(ImagehostImageExtractor):
    """Extractor for single images from chronos.to"""
    category = "chronos"
    pattern = [r"(?:https?://)?((?:www\.)?chronos\.to/([a-z0-9]{12}))"]
    test = [("http://chronos.to/bdrmq7rw7v4y", {
        "url": "7fcb3fe315c94283644d25ef47a644c2dc8da944",
        "keyword": "04dbc71a1154728d01c931308184050d61c5da55",
        "content": "0c8768055e4e20e7c7259608b67799171b691140",
    })]
    https = False
    params = "complex"

    def get_info(self, page):
        url     , pos = text.extract(page, '<br><img src="', '"')
        filename, pos = text.extract(page, ' alt="', '"', pos)
        return url, filename

class CoreimgImageExtractor(ChronosImageExtractor):
    """Extractor for single images from coreimg.net"""
    category = "coreimg"
    pattern = [r"(?:https?://)?((?:www\.)?coreimg\.net/([a-z0-9]{12}))"]
    test = [("http://coreimg.net/ykcl5al8uzvg", {
        "url": "2b32596a2ea66b7cc784e20f3749f75f20998d78",
        "keyword": "8d71e5b820bc7177baee33ca529c91ae4521299f",
        "content": "0c8768055e4e20e7c7259608b67799171b691140",
    })]

class PicmaniacImageExtractor(ChronosImageExtractor):
    """Extractor for single images from pic-maniac.com"""
    category = "picmaniac"
    pattern = [r"(?:https?://)?((?:www\.)?pic-maniac\.com/([a-z0-9]{12}))"]
    test = []


class HosturimageImageExtractor(ImagehostImageExtractor):
    """Extractor for single images from hosturimage.com"""
    category = "hosturimage"
    pattern = [(r"(?:https?://)?((?:www\.)?hosturimage\.com/"
                r"img-([a-z0-9]+)\.html)")]
    test = [("https://hosturimage.com/img-581ca97112bf8.html", {
        "url": "c672a3fd7fd48e5506d020aa19c4ac91ba078671",
        "keyword": "c3c94340b8e395e07b5145cf17534b5871ec8593",
        "content": "0c8768055e4e20e7c7259608b67799171b691140",
    })]
    https = True

    def get_info(self, page):
        _  , pos = text.extract(page, '<div id="image_details">', '')
        url, pos = text.extract(page, "src='", "'", pos)
        return url, url

class ImageontimeImageExtractor(HosturimageImageExtractor):
    """Extractor for single images from imageontime.org"""
    category = "imageontime"
    pattern = [(r"(?:https?://)?((?:www\.)?imageontime\.org/"
                r"img-([a-z0-9]+)\.html)")]
    test = []
    https = False

class Img4everImageExtractor(HosturimageImageExtractor):
    """Extractor for single images from img4ever.net"""
    category = "img4ever"
    pattern = [(r"(?:https?://)?((?:www\.)?img4ever\.net/"
                r"img-([a-z0-9]+)\.html)")]
    test = []
    https = True

class ImguploadImageExtractor(HosturimageImageExtractor):
    """Extractor for single images from imgupload.yt"""
    category = "imgupload"
    pattern = [(r"(?:https?://)?((?:www\.)?imgupload\.yt/"
                r"img-([a-z0-9]+)\.html)")]
    test = []
    https = True


class ImagetwistImageExtractor(ImagehostImageExtractor):
    """Extractor for single images from imagetwist.com"""
    category = "imagetwist"
    pattern = [r"(?:https?://)?((?:www\.)?imagetwist\.com/([a-z0-9]{12}))"]
    test = [("http://imagetwist.com/4e46hv31tu0q/test.jpg", {
        "url": "6b3fc0bd1105b698d2d5844658ca674d66b1e2e7",
        "keyword": "30dd34dcb06b5b51c6cfff199c610b24edb7b9bc",
        "content": "96b1fd099b06faad5879fce23a7e4eb8290d8810",
    })]
    params = None

    def get_info(self, page):
        url     , pos = text.extract(page, 'center;"><img src="', '"')
        filename, pos = text.extract(page, ' alt="', '"', pos)
        return url, filename


class ImgcandyImageExtractor(ImagehostImageExtractor):
    """Extractor for single images from imgcandy.net"""
    category = "imgcandy"
    pattern = [(r"(?:https?://)?((?:www\.)?imgcandy\.net/img-([a-z0-9]+)"
                r"(?:_.+)?\.html)")]
    test = [("http://imgcandy.net/img-57d02527efee8_test-テスト.png.html", {
        "url": "bc3c9207b10dbfe8e65ccef5b9e3194a7427b4fa",
        "keyword": "1ed1587ef38a6b26ce28b35857a78417239d197a",
        "content": "0c8768055e4e20e7c7259608b67799171b691140",
    })]

    def get_info(self, page):
        url = text.extract(page, "<img class='centred' src='", "'")[0]
        pos = self.url.find("_")
        return url, self.url[pos+1:-5] if pos != -1 else url


class ImgclickImageExtractor(ImagehostImageExtractor):
    """Extractor for single images from imgclick.net"""
    category = "imgclick"
    pattern = [r"(?:https?://)?((?:www\.)?imgclick\.net/([^/]+))"]
    test = [("http://imgclick.net/4tbrre1oxew9/test-_-_.png.html", {
        "url": "140dcb250a325f2d26b2d918c18b8ac6a2a0f6ab",
        "keyword": "c086439336eea3bdf773d761c32b0edb29af0ebd",
        "content": "0c8768055e4e20e7c7259608b67799171b691140",
    })]
    params = "complex"

    def get_info(self, page):
        url     , pos = text.extract(page, '<img  src="', '"')
        filename, pos = text.extract(page, 'alt="', '"', pos)
        return url, filename


class ImgspiceImageExtractor(ImagehostImageExtractor):
    """Extractor for single images from imgspice.com"""
    category = "imgspice"
    pattern = [r"(?:https?://)?((?:www\.)?imgspice\.com/([^/]+))"]
    test = [("https://imgspice.com/zop38mvvq29u/", {
        "url": "a45833733c02b64d105363ffd8fd19f06992a2f7",
        "keyword": "5218f63195e6a487c0881fd1cda78c535c61b462",
        "content": "0c8768055e4e20e7c7259608b67799171b691140",
    })]
    https = True
    params = None

    def get_info(self, page):
        filename, pos = text.extract(page, '<td nowrap>', '</td>')
        url     , pos = text.extract(page, '<img src="', '"', pos)
        return url, text.unescape(filename)


class ImgtrexImageExtractor(ImagehostImageExtractor):
    """Extractor for single images from imgtrex.com"""
    category = "imgtrex"
    pattern = [r"(?:https?://)?((?:www\.)?imgtrex\.com/([^/]+))"]
    test = [("http://imgtrex.com/im0ypxq0rke4/test-テスト-&<a>.png", {
        "url": "c000618bddda42bd599a590b7972c7396d19d8fe",
        "keyword": "58905795a9cd3f17d5ff024fc4d63645795ba23c",
        "content": "0c8768055e4e20e7c7259608b67799171b691140",
    })]
    params = None

    def get_info(self, page):
        filename, pos = text.extract(page, '<title>ImgTrex: ', '</title>')
        url     , pos = text.extract(page, '<br>\n<img src="', '"', pos)
        return url, filename


class TurboimagehostImageExtractor(ImagehostImageExtractor):
    """Extractor for single images from turboimagehost.com"""
    category = "turboimagehost"
    pattern = [(r"(?:https?://)?((?:www\.)?turboimagehost\.com/p/(\d+)"
                r"/[^/]+\.html)")]
    test = [("http://www.turboimagehost.com/p/29690902/test--.png.html", {
        "url": "c624dc7784de515342117a2678fee6ecf1032d79",
        "keyword": "a4527f14675e4512ef317ee0401940c711fbe012",
        "content": "0c8768055e4e20e7c7259608b67799171b691140",
    })]
    params = None

    def get_info(self, page):
        needle = '<a href="http://www.turboimagehost.com"><img src="'
        url = text.extract(page, needle, '"')[0]
        return url, url