From 91ad8ac2b38c2f0670e3160eb33009d0b7dbe3f9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= Date: Sat, 1 Apr 2017 21:42:36 +0200 Subject: [PATCH] [mangastream] adapt to domain-change to readms.net --- gallery_dl/extractor/mangastream.py | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/gallery_dl/extractor/mangastream.py b/gallery_dl/extractor/mangastream.py index cb664173..f01b025f 100644 --- a/gallery_dl/extractor/mangastream.py +++ b/gallery_dl/extractor/mangastream.py @@ -1,15 +1,16 @@ # -*- coding: utf-8 -*- -# Copyright 2015 Mike Fährmann +# Copyright 2015-2017 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 manga-chapters from https://www.mangastream.com/""" +"""Extract manga-chapters from https://mangastream.com/""" from .common import AsynchronousExtractor, Message from .. import text +from urllib.parse import urljoin class MangastreamChapterExtractor(AsynchronousExtractor): @@ -18,26 +19,26 @@ class MangastreamChapterExtractor(AsynchronousExtractor): subcategory = "chapter" directory_fmt = ["{category}", "{manga}", "c{chapter} - {title}"] filename_fmt = "{manga}_c{chapter}_{page:>03}.{extension}" - pattern = [(r"(?:https?://)?(?:www\.)?(?:readms|mangastream)\.com/" + pattern = [(r"(?:https?://)?(?:www\.)?(?:readms|mangastream)\.(?:com|net)/" r"r(?:ead)?/([^/]*/([^/]+)/(\d+))")] - url_base = "https://mangastream.com/r/" + root = "https://readms.net/r/" def __init__(self, match): AsynchronousExtractor.__init__(self) self.part, self.chapter, self.ch_id = match.groups() def items(self): - page = self.request(self.url_base + self.part).text + page = self.request(self.root + self.part).text data = self.get_job_metadata(page) next_url = None yield Message.Version, 1 yield Message.Directory, data - for i in range(int(data["count"])): + for data["page"] in range(1, int(data["count"])+1): if next_url: page = self.request(next_url).text next_url, image_url = self.get_page_metadata(page) text.nameext_from_url(image_url, data) - data["page"] = i+1 + image_url = urljoin(self.root, image_url) yield Message.Url, image_url, data.copy() def get_job_metadata(self, page):