# -*- coding: utf-8 -*- # Copyright 2021 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 Gelbooru v0.1 sites""" from . import booru from .. import text class GelbooruV01Extractor(booru.BooruExtractor): basecategory = "gelbooru_v01" per_page = 20 def _parse_post(self, post_id): url = "{}/index.php?page=post&s=view&id={}".format( self.root, post_id) page = self.request(url).text post = text.extract_all(page, ( ("created_at", 'Posted: ', ' <'), ("uploader" , 'By: ', ' <'), ("width" , 'Size: ', 'x'), ("height" , '', ' <'), ("source" , 'Source: ', '<'), ))[0] post["id"] = post_id post["md5"] = post["file_url"].rpartition("/")[2].partition(".")[0] post["rating"] = (post["rating"] or "?")[0].lower() post["tags"] = text.unescape(post["tags"]) post["date"] = text.parse_datetime( post["created_at"], "%Y-%m-%d %H:%M:%S") return post BASE_PATTERN = GelbooruV01Extractor.update({ "thecollection" : {"root": "https://the-collection.booru.org"}, "illusioncardsbooru": {"root": "https://illusioncards.booru.org"}, "allgirlbooru" : {"root": "https://allgirl.booru.org"}, }) class GelbooruV01TagExtractor(GelbooruV01Extractor): subcategory = "tag" directory_fmt = ("{category}", "{search_tags}") archive_fmt = "t_{search_tags}_{id}" pattern = BASE_PATTERN + r"/index\.php\?page=post&s=list&tags=([^&#]+)" test = ( (("https://the-collection.booru.org" "/index.php?page=post&s=list&tags=parody"), { "range": "1-25", "count": 25, }), (("https://illusioncards.booru.org" "/index.php?page=post&s=list&tags=koikatsu"), { "range": "1-25", "count": 25, }), ("https://allgirl.booru.org/index.php?page=post&s=list&tags=dress", { "range": "1-25", "count": 25, }), ) def __init__(self, match): GelbooruV01Extractor.__init__(self, match) self.tags = match.group(match.lastindex) def metadata(self): return {"search_tags": text.unquote(self.tags.replace("+", " "))} def posts(self): url = "{}/index.php?page=post&s=list&tags={}&pid=".format( self.root, self.tags) pid = self.page_start while True: page = self.request(url + str(pid)).text cnt = 0 for post_id in text.extract_iter( page, 'class="thumb">