# -*- coding: utf-8 -*- # 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://sturdychan.help/""" from .common import Extractor, Message from .. import text BASE_PATTERN = r"(?:https?://)?(?:sturdychan.help|2chen\.(?:moe|club))" class _2chenThreadExtractor(Extractor): """Extractor for 2chen threads""" category = "2chen" subcategory = "thread" root = "https://sturdychan.help" directory_fmt = ("{category}", "{board}", "{thread} {title}") filename_fmt = "{time} {filename}.{extension}" archive_fmt = "{board}_{thread}_{hash}_{time}" pattern = BASE_PATTERN + r"/([^/?#]+)/(\d+)" test = ( ("https://sturdychan.help/tv/268929", { "pattern": r"https://sturdychan\.help/assets/images" r"/src/\w{40}\.\w+$", "count": ">= 179", "keyword": { "board": "tv", "date": "type:datetime", "hash": r"re:[0-9a-f]{40}", "name": "Anonymous", "no": r"re:\d+", "thread": "268929", "time": int, "title": "「/ttg/ #118: 🇧🇷 edition」", "url": str, }, }), ("https://2chen.club/tv/1"), ("https://2chen.moe/jp/303786"), ) def __init__(self, match): Extractor.__init__(self, match) self.board, self.thread = match.groups() def items(self): url = "{}/{}/{}".format(self.root, self.board, self.thread) page = self.request(url, encoding="utf-8", notfound="thread").text data = self.metadata(page) yield Message.Directory, data for post in self.posts(page): url = post["url"] if not url: continue if url[0] == "/": url = self.root + url post["url"] = url = url.partition("?")[0] post.update(data) post["time"] = text.parse_int(post["date"].timestamp()) yield Message.Url, url, text.nameext_from_url( post["filename"], post) def metadata(self, page): board, pos = text.extract(page, 'class="board">/', '/<') title = text.extract(page, "