# -*- coding: utf-8 -*- # Copyright 2016-2017 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. """Extract images from http://imagefap.com/""" from .common import Extractor, Message from .. import text import json class ImagefapGalleryExtractor(Extractor): """Extractor for image galleries from imagefap.com""" category = "imagefap" subcategory = "gallery" directory_fmt = ["{category}", "{gallery_id} {title}"] filename_fmt = "{category}_{gallery_id}_{name}.{extension}" pattern = [(r"(?:https?://)?(?:www\.)?imagefap\.com/" r"(?:gallery\.php\?gid=|gallery/|pictures/)(\d+)")] test = [ ("http://www.imagefap.com/gallery/6318447", { "url": "f63e6876df83a40e1a98dad70e46952dd9edb7a7", "keyword": "275857d113bb007245de705ae7bd0dff7d677874", "content": "38e50699db9518ae68648c45ecdd6be614efc324", }), ("http://www.imagefap.com/gallery/5486966", { "url": "eace9b33be99f87f3382c87bd915cf495a865d6e", "keyword": "b84da0543c2d1f848bf5e4c2950dd4f4543a1e0c", }), ] def __init__(self, match): Extractor.__init__(self) self.gid = match.group(1) self.image_id = "" def items(self): url = "http://www.imagefap.com/pictures/" + self.gid + "/" page = self.request(url).text data = self.get_job_metadata(page) yield Message.Version, 1 yield Message.Directory, data for url, image in self.get_images(): data.update(image) yield Message.Url, url, data def get_job_metadata(self, page): """Collect metadata for extractor-job""" data, pos = text.extract_all(page, ( ("section" , 'Porn pics of ', ' (Page 1)'), ("uploader", '>Uploaded by ', ''), ("count" , ' 1 of ', ' pics"'), ), values={"gallery_id": self.gid}) self.image_id = text.extract(page, 'id="img_ed_', '"', pos)[0] data["title"] = text.unescape(data["title"]) return data def get_images(self): """Collect image-urls and -metadata""" num = 0 url = "http://www.imagefap.com/photo/" + self.image_id + "/" params = {"gid": self.gid, "idx": 0, "partial": "true"} while True: pos = 0 page = self.request(url, params=params).text for _ in range(24): imgurl, pos = text.extract(page, '', '', pos ) json_dict = json.loads(json_data) json_dict["section"] = section return json_dict class ImagefapUserExtractor(Extractor): """Extractor for all galleries from a user at imagefap.com""" category = "imagefap" subcategory = "user" directory_fmt = ["{category}", "{gallery_id} {title}"] filename_fmt = "{category}_{gallery_id}_{name}.{extension}" pattern = [(r"(?:https?://)?(?:www\.)?imagefap\.com/" r"profile(?:\.php\?user=|/)([^/]+)"), (r"(?:https?://)?(?:www\.)?imagefap\.com/" r"usergallery\.php\?userid=(\d+)")] test = [("http://www.imagefap.com/profile/Mr Bad Example/galleries", { "url": "145e98a8648c7695c150800ff8fd578ab26c28c1", })] def __init__(self, match): Extractor.__init__(self) try: self.user_id = int(match.group(1)) self.user = None except ValueError: self.user_id = None self.user = match.group(1) def items(self): yield Message.Version, 1 for gallery in self.get_gallery_ids(): yield Message.Queue, "http://www.imagefap.com/gallery/" + gallery def get_gallery_ids(self): """Yield all gallery_ids of a specific user""" folders = self.get_gallery_folders() url = "http://www.imagefap.com/ajax_usergallery_folder.php" params = {"userid": self.user_id} for folder_id in folders: params["id"] = folder_id page = self.request(url, params=params).text yield from text.extract_iter(page, '