github/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[mangapark] fix metadata extraction

Browse Source
This commit is contained in:
Mike Fährmann
2020-03-27 22:07:42 +01:00
parent 6ecb0a19cf
commit 4203dc0bdc
3 changed files with 40 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/supportedsites.rst
View File

@@ -74,7 +74,7 @@ Manga Here https://www.mangahere.cc/ Chapters, Manga
Manga Stream https://readms.net/ Chapters Manga Stream https://readms.net/ Chapters
MangaDex https://mangadex.org/ Chapters, Manga MangaDex https://mangadex.org/ Chapters, Manga
Mangapanda https://www.mangapanda.com/ Chapters, Manga Mangapanda https://www.mangapanda.com/ Chapters, Manga
MangaPark https://mangapark.me/ Chapters, Manga MangaPark https://mangapark.net/ Chapters, Manga
Mangareader https://www.mangareader.net/ Chapters, Manga Mangareader https://www.mangareader.net/ Chapters, Manga
Mangoxo https://www.mangoxo.com/ Albums, Channels Optional Mangoxo https://www.mangoxo.com/ Albums, Channels Optional
Naver https://blog.naver.com/ Blogs, Posts Naver https://blog.naver.com/ Blogs, Posts

57
gallery_dl/extractor/mangapark.py
View File

@@ -1,16 +1,17 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
# Copyright 2015-2019 Mike Fährmann # Copyright 2015-2020 Mike Fährmann
# #
# This program is free software; you can redistribute it and/or modify # 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 # it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation. # published by the Free Software Foundation.
"""Extract manga-chapters and entire manga from https://mangapark.me/""" """Extractors for https://mangapark.net/"""
from .common import ChapterExtractor, MangaExtractor from .common import ChapterExtractor, MangaExtractor
from .. import text, exception from .. import text, exception
import json import json
import re
class MangaparkBase(): class MangaparkBase():
@@ -37,26 +38,35 @@ class MangaparkBase():
elif key == "e": elif key == "e":
data["chapter_minor"] = "v" + value data["chapter_minor"] = "v" + value
@staticmethod
def parse_chapter_title(title, data):
match = re.search(r"(?i)(?:vol(?:ume)?[ .]*(\d+) )?"
r"ch(?:apter)?[ .]*(\d+)(\.\w+)?", title)
if match:
vol, ch, data["chapter_minor"] = match.groups()
data["volume"] = text.parse_int(vol)
data["chapter"] = text.parse_int(ch)
class MangaparkChapterExtractor(MangaparkBase, ChapterExtractor): class MangaparkChapterExtractor(MangaparkBase, ChapterExtractor):
"""Extractor for manga-chapters from mangapark.me""" """Extractor for manga-chapters from mangapark.net"""
pattern = (r"(?:https?://)?(?:www\.)?mangapark\.(me|net|com)" pattern = (r"(?:https?://)?(?:www\.)?mangapark\.(me|net|com)"
r"/manga/([^?&#]+/i\d+)") r"/manga/([^?&#]+/i\d+)")
test = ( test = (
("https://mangapark.me/manga/gosu/i811615/c55/1", { ("https://mangapark.net/manga/gosu/i811615/c55/1", {
"count": 50, "count": 50,
"keyword": "373d678048d29492f9763743ccaa9b6d840f17cf", "keyword": "373d678048d29492f9763743ccaa9b6d840f17cf",
}), }),
(("https://mangapark.me/manga" (("https://mangapark.net/manga"
"/ad-astra-per-aspera-hata-kenjirou/i662054/c001.2/1"), { "/ad-astra-per-aspera-hata-kenjirou/i662054/c001.2/1"), {
"count": 40, "count": 40,
"keyword": "8e9cce4ed0e25d12a45e02f840d6f32ef838e257", "keyword": "8e9cce4ed0e25d12a45e02f840d6f32ef838e257",
}), }),
("https://mangapark.me/manga/gekkan-shoujo-nozaki-kun/i655476/c70/1", { ("https://mangapark.net/manga/gekkan-shoujo-nozaki-kun/i655476/c70", {
"count": 15, "count": 15,
"keyword": "19f730617074d65f91c0781f429de324890925bf", "keyword": "19f730617074d65f91c0781f429de324890925bf",
}), }),
("https://mangapark.net/manga/gosu/i811615/c55/1"), ("https://mangapark.me/manga/gosu/i811615/c55/1"),
("https://mangapark.com/manga/gosu/i811615/c55/1"), ("https://mangapark.com/manga/gosu/i811615/c55/1"),
) )
@@ -78,7 +88,10 @@ class MangaparkChapterExtractor(MangaparkBase, ChapterExtractor):
if not data["path"]: if not data["path"]:
raise exception.NotFoundError("chapter") raise exception.NotFoundError("chapter")
self.parse_chapter_path(data["path"], data) self.parse_chapter_path(data["path"], data)
if "chapter" not in data:
self.parse_chapter_title(data["title"], data)
data["manga"], _, data["type"] = data["manga"].rpartition(" ") data["manga"], _, data["type"] = data["manga"].rpartition(" ")
data["manga"] = text.unescape(data["manga"]) data["manga"] = text.unescape(data["manga"])
@@ -89,8 +102,7 @@ class MangaparkChapterExtractor(MangaparkBase, ChapterExtractor):
return data return data
def images(self, page): def images(self, page):
data = json.loads(text.extract( data = json.loads(text.extract(page, "var _load_pages =", ";")[0])
page, "var _load_pages =", ";")[0] or "[]")
return [ return [
(text.urljoin(self.root, item["u"]), { (text.urljoin(self.root, item["u"]), {
"width": text.parse_int(item["w"]), "width": text.parse_int(item["w"]),
@@ -101,16 +113,16 @@ class MangaparkChapterExtractor(MangaparkBase, ChapterExtractor):
class MangaparkMangaExtractor(MangaparkBase, MangaExtractor): class MangaparkMangaExtractor(MangaparkBase, MangaExtractor):
"""Extractor for manga from mangapark.me""" """Extractor for manga from mangapark.net"""
chapterclass = MangaparkChapterExtractor chapterclass = MangaparkChapterExtractor
pattern = (r"(?:https?://)?(?:www\.)?mangapark\.(me|net|com)" pattern = (r"(?:https?://)?(?:www\.)?mangapark\.(me|net|com)"
r"(/manga/[^/?&#]+)/?$") r"(/manga/[^/?&#]+)/?$")
test = ( test = (
("https://mangapark.me/manga/aria", { ("https://mangapark.net/manga/aria", {
"url": "a58be23ef3874fe9705b0b41dd462b67eaaafd9a", "url": "9b0b31e4992260876f56d7bfc8ff0ae71295c4f4",
"keyword": "b3b5a30aa2a326bc0ca8b74c65b5ecd4bf676ebf", "keyword": "6e44744a28d01b889b1e8291847abd84b591590d",
}), }),
("https://mangapark.net/manga/aria"), ("https://mangapark.me/manga/aria"),
("https://mangapark.com/manga/aria"), ("https://mangapark.com/manga/aria"),
) )
@@ -128,13 +140,22 @@ class MangaparkMangaExtractor(MangaparkBase, MangaExtractor):
data["stream"] = text.parse_int(text.extract(stream, '', '"')[0]) data["stream"] = text.parse_int(text.extract(stream, '', '"')[0])
for chapter in text.extract_iter(stream, '<li ', '</li>'): for chapter in text.extract_iter(stream, '<li ', '</li>'):
path , pos = text.extract(chapter, 'href="', '"') path , pos = text.extract(chapter, 'href="', '"')
title, pos = text.extract(chapter, '>: </span>', '<', pos) title1, pos = text.extract(chapter, '>', '<', pos)
count, pos = text.extract(chapter, ' of ', ' ', pos) title2, pos = text.extract(chapter, '>: </span>', '<', pos)
count , pos = text.extract(chapter, ' of ', ' ', pos)
self.parse_chapter_path(path[8:], data) self.parse_chapter_path(path[8:], data)
data["title"] = title.strip() if title else "" if "chapter" not in data:
self.parse_chapter_title(title1, data)
if title2:
data["title"] = title2.strip()
else:
data["title"] = title1.partition(":")[2].strip()
data["count"] = text.parse_int(count) data["count"] = text.parse_int(count)
results.append((self.root + path, data.copy())) results.append((self.root + path, data.copy()))
data.pop("chapter", None)
return results return results

1
test/test_results.py
View File

@@ -27,7 +27,6 @@ TRAVIS_SKIP = {
# temporary issues, etc. # temporary issues, etc.
BROKEN = { BROKEN = {
"mangapark",
"photobucket", "photobucket",
"worldthree", "worldthree",
} }