[rawkuma] add support (#4571)
* Add rawkuma extractor * Fix flake8 warnings * Remove fstring * Fix regex call * update domain to rawkuma.net * fix 'manga' extractor * fix 'chapter' extractor * add tests * update docs/supportedsites --------- Co-authored-by: Mike Fährmann <mike_faehrmann@web.de>
This commit is contained in:
thatDudo
@@ -763,6 +763,12 @@ Consider all listed sites to potentially be NSFW.
|
||||
<td>Playlists, Posts, Tag Searches</td>
|
||||
<td></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Rawkuma</td>
|
||||
<td>https://rawkuma.net/</td>
|
||||
<td>Chapters, Manga</td>
|
||||
<td></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Read Comic Online</td>
|
||||
<td>https://readcomiconline.li/</td>
|
||||
|
||||
@@ -140,6 +140,7 @@ modules = [
|
||||
"pornhub",
|
||||
"pornpics",
|
||||
"postmill",
|
||||
"rawkuma",
|
||||
"reactor",
|
||||
"readcomiconline",
|
||||
"realbooru",
|
||||
|
||||
83
gallery_dl/extractor/rawkuma.py
Normal file
83
gallery_dl/extractor/rawkuma.py
Normal file
@@ -0,0 +1,83 @@
|
||||
# -*- 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://rawkuma.net/"""
|
||||
|
||||
from .common import MangaExtractor, ChapterExtractor
|
||||
from .. import text, util
|
||||
|
||||
BASE_PATTERN = r"(?:https?://)?rawkuma\.(?:net|com)"
|
||||
|
||||
|
||||
class RawkumaBase():
|
||||
"""Base class for rawkuma extractors"""
|
||||
category = "rawkuma"
|
||||
root = "https://rawkuma.net"
|
||||
|
||||
|
||||
class RawkumaChapterExtractor(RawkumaBase, ChapterExtractor):
|
||||
"""Extractor for manga chapters from rawkuma.net"""
|
||||
archive_fmt = "{chapter_id}_{page}"
|
||||
pattern = BASE_PATTERN + r"/([^/?#]+-chapter-\d+(?:-\d+)?)"
|
||||
example = "https://rawkuma.net/TITLE-chapter-123/"
|
||||
|
||||
def __init__(self, match):
|
||||
url = "{}/{}/".format(self.root, match.group(1))
|
||||
ChapterExtractor.__init__(self, match, url)
|
||||
|
||||
def metadata(self, page):
|
||||
item = util.json_loads(text.extr(page, ',"item":', "}};"))
|
||||
title = text.rextr(
|
||||
page, '<h1 class="entry-title', "</h1>").partition(" – ")[2]
|
||||
date = text.extr(page, 'datetime="', '"')
|
||||
chapter, sep, minor = item["c"].partition(".")
|
||||
|
||||
return {
|
||||
"manga" : item["s"],
|
||||
"manga_id" : text.parse_int(item["mid"]),
|
||||
"chapter" : text.parse_int(chapter),
|
||||
"chapter_minor": sep + minor,
|
||||
"chapter_id" : text.parse_int(item["cid"]),
|
||||
"title" : text.unescape(title),
|
||||
"date" : text.parse_datetime(
|
||||
date, "%Y-%m-%dWIB%H:%M:%S%z"),
|
||||
"thumbnail" : item.get("t"),
|
||||
"lang" : "ja",
|
||||
"language" : "Japanese",
|
||||
}
|
||||
|
||||
def images(self, page):
|
||||
images = util.json_loads(text.extr(page, '","images":', '}'))
|
||||
return [(url, None) for url in images]
|
||||
|
||||
|
||||
class RawkumaMangaExtractor(RawkumaBase, MangaExtractor):
|
||||
"""Extractor for manga from rawkuma.net"""
|
||||
chapterclass = RawkumaChapterExtractor
|
||||
pattern = BASE_PATTERN + r"/manga/([^/?#]+)"
|
||||
example = "https://rawkuma.net/manga/TITLE/"
|
||||
|
||||
def __init__(self, match):
|
||||
url = "{}/manga/{}/".format(self.root, match.group(1))
|
||||
MangaExtractor.__init__(self, match, url)
|
||||
|
||||
def chapters(self, page):
|
||||
manga = text.unescape(text.extr(page, "<title>", " – "))
|
||||
|
||||
results = []
|
||||
for chbox in text.extract_iter(
|
||||
page, '<li data-num="', "</a>"):
|
||||
info = text.extr(chbox, '', '"')
|
||||
chapter, _, title = info.partition(" - ")
|
||||
chapter, sep, minor = chapter.partition(".")
|
||||
|
||||
results.append((text.extr(chbox, 'href="', '"'), {
|
||||
"manga" : manga,
|
||||
"chapter" : text.parse_int(chapter),
|
||||
"chapter-minor": sep + minor,
|
||||
"title" : title,
|
||||
}))
|
||||
return results
|
||||
65
test/results/rawkuma.py
Normal file
65
test/results/rawkuma.py
Normal file
@@ -0,0 +1,65 @@
|
||||
# -*- 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.
|
||||
|
||||
from gallery_dl.extractor import rawkuma
|
||||
|
||||
|
||||
__tests__ = (
|
||||
{
|
||||
"#url" : "https://rawkuma.net/hitman-chapter-127/",
|
||||
"#class" : rawkuma.RawkumaChapterExtractor,
|
||||
"#pattern" : r"https://cdn.kumacdn.club/wp-content/uploads/images/h/hitman/chapter-127/.+\.jpg$",
|
||||
"#count" : 18,
|
||||
|
||||
"chapter" : 127,
|
||||
"chapter_id" : 313750,
|
||||
"chapter_minor": "",
|
||||
"count" : 18,
|
||||
"date" : "dt:2021-07-01 07:07:27",
|
||||
"extension" : "jpg",
|
||||
"filename" : str,
|
||||
"lang" : "ja",
|
||||
"language" : "Japanese",
|
||||
"manga" : "Hitman",
|
||||
"manga_id" : 47920,
|
||||
"page" : range(1, 18),
|
||||
"thumbnail" : "https://rawkuma.net/wp-content/uploads/2020/10/Hitman-10.jpg",
|
||||
"title" : "End",
|
||||
},
|
||||
|
||||
{
|
||||
"#url" : "https://rawkuma.net/saikyou-inyoushi-no-isekai-tenseiki-chapter-8-1/",
|
||||
"#class" : rawkuma.RawkumaChapterExtractor,
|
||||
"#pattern" : r"https://cdn.kumacdn.club/wp-content/uploads/images/s/saikyou-inyoushi-no-isekai-tenseiki/chapter-8-1/.+\.jpg$",
|
||||
|
||||
"chapter" : 8,
|
||||
"chapter_id" : 85076,
|
||||
"chapter_minor": ".1",
|
||||
"count" : 11,
|
||||
"date" : "dt:2023-11-21 06:27:19",
|
||||
"extension" : "jpg",
|
||||
"filename" : str,
|
||||
"lang" : "ja",
|
||||
"language" : "Japanese",
|
||||
"manga" : "Saikyou Inyoushi no Isekai Tenseiki",
|
||||
"manga_id" : 20781,
|
||||
"page" : range(1, 11),
|
||||
"thumbnail" : "https://rawkuma.net/wp-content/uploads/2020/06/Saikyou-Inyoushi-no-Isekai-Tenseiki-cover.jpg",
|
||||
"title" : "",
|
||||
},
|
||||
|
||||
{
|
||||
"#url" : "https://rawkuma.net/manga/hitman/",
|
||||
"#class" : rawkuma.RawkumaMangaExtractor,
|
||||
"#pattern" : rawkuma.RawkumaChapterExtractor.pattern,
|
||||
|
||||
"chapter" : range(1, 127),
|
||||
"chapter-minor": {"", ".5"},
|
||||
"manga" : "Hitman",
|
||||
"title" : {"", "End"},
|
||||
},
|
||||
|
||||
)
|
||||
Reference in New Issue
Block a user