# -*- 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://mangaread.org/""" from .common import ChapterExtractor, MangaExtractor from .. import text, exception import re class MangareadBase(): """Base class for Mangaread extractors""" category = "mangaread" root = "https://www.mangaread.org" @staticmethod def parse_chapter_string(chapter_string, data): match = re.match( r"(?:(.+)\s*-\s*)?[Cc]hapter\s*(\d+)(\.\d+)?(?:\s*-\s*(.+))?", text.unescape(chapter_string).strip()) manga, chapter, minor, title = match.groups() manga = manga.strip() if manga else "" data["manga"] = data.pop("manga", manga) data["chapter"] = text.parse_int(chapter) data["chapter_minor"] = minor or "" data["title"] = title or "" data["lang"] = "en" data["language"] = "English" class MangareadChapterExtractor(MangareadBase, ChapterExtractor): """Extractor for manga-chapters from mangaread.org""" pattern = (r"(?:https?://)?(?:www\.)?mangaread\.org" r"(/manga/[^/?#]+/[^/?#]+)") example = "https://www.mangaread.org/manga/MANGA/chapter-01/" def metadata(self, page): tags = text.extr(page, 'class="wp-manga-tags-list">', '') data = {"tags": list(text.split_html(tags)[::2])} info = text.extr(page, '

', "

") if not info: raise exception.NotFoundError("chapter") self.parse_chapter_string(info, data) return data def images(self, page): page = text.extr( page, '
', '
"): url , pos = text.extract(chapter, '", "", pos) self.parse_chapter_string(info, data) result.append((url, data.copy())) return result def metadata(self, page): extr = text.extract_from(text.extr( page, 'class="summary_content">', 'class="manga-action"')) return { "manga" : text.extr(page, "

", "

").strip(), "description": text.unescape(text.remove_html(text.extract( page, ">", "
", page.index("summary__content"))[0])), "rating" : text.parse_float( extr('total_votes">', "").strip()), "manga_alt" : text.remove_html( extr("Alternative \n
", "")).split("; "), "author" : list(text.extract_iter( extr('class="author-content">', ""), '"tag">', "")), "artist" : list(text.extract_iter( extr('class="artist-content">', ""), '"tag">', "")), "genres" : list(text.extract_iter( extr('class="genres-content">', ""), '"tag">', "")), "type" : text.remove_html( extr("Type \n", "")), "release" : text.parse_int(text.remove_html( extr("Release \n", ""))), "status" : text.remove_html( extr("Status \n", "")), }