# -*- coding: utf-8 -*- # Copyright 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. """Extractors for https://www.pornhub.com/""" from .common import Extractor, Message from .. import text, exception BASE_PATTERN = r"(?:https?://)?(?:[^.]+\.)?pornhub\.com" class PornhubExtractor(Extractor): """Base class for pornhub extractors""" category = "pornhub" root = "https://www.pornhub.com" class PornhubGalleryExtractor(PornhubExtractor): """Extractor for image galleries on pornhub.com""" subcategory = "gallery" directory_fmt = ("{category}", "{user}", "{gallery[id]} {gallery[title]}") filename_fmt = "{num:>03}_{id}.{extension}" archive_fmt = "{id}" pattern = BASE_PATTERN + r"/album/(\d+)" test = ( ("https://www.pornhub.com/album/1708982", { "pattern": r"https://\w+.phncdn.com/pics/albums/\d+/\d+/\d+/\d+/", "count": 93, "keyword": { "id": int, "num": int, "score": int, "views": int, "caption": str, "user": "Unknown", "gallery": { "id" : 1708982, "score": int, "views": int, "tags" : list, "title": "Random Hentai", }, }, }), ("https://www.pornhub.com/album/37180171", { "exception": exception.AuthorizationError, }), ) def __init__(self, match): PornhubExtractor.__init__(self, match) self.gallery_id = match.group(1) self._first = None def items(self): data = self.metadata() yield Message.Version, 1 yield Message.Directory, data for num, image in enumerate(self.images(), 1): url = image["url"] image.update(data) image["num"] = num yield Message.Url, url, text.nameext_from_url(url, image) def metadata(self): url = "{}/album/{}".format( self.root, self.gallery_id) extr = text.extract_from(self.request(url).text) title = extr("