1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
|
# -*- coding: utf-8 -*-
# Copyright 2025 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.
"""Extractors for https://comick.io/"""
from .common import ChapterExtractor, MangaExtractor, Message
from .. import text
from ..cache import memcache
BASE_PATTERN = r"(?:https?://)?(?:www\.)?comick\.io"
class ComickBase():
"""Base class for comick.io extractors"""
category = "comick"
root = "https://comick.io"
@memcache(keyarg=1)
def _manga_info(self, slug):
url = f"{self.root}/comic/{slug}"
page = self.request(url).text
data = self._extract_nextdata(page)
props = data["props"]["pageProps"]
comic = props["comic"]
genre = []
theme = []
format = ""
for item in comic["md_comic_md_genres"]:
item = item["md_genres"]
group = item["group"]
if group == "Genre":
genre.append(item["name"])
elif group == "Theme":
theme.append(item["name"])
else:
format = item["name"]
if mu := comic["mu_comics"]:
tags = [c["mu_categories"]["title"]
for c in mu["mu_comic_categories"]]
publisher = [p["mu_publishers"]["title"]
for p in mu["mu_comic_publishers"]]
else:
tags = publisher = ()
return {
"manga": comic["title"],
"manga_id": comic["id"],
"manga_hid": comic["hid"],
"manga_slug": slug,
"manga_titles": [t["title"] for t in comic["md_titles"]],
"artist": [a["name"] for a in props["artists"]],
"author": [a["name"] for a in props["authors"]],
"genre" : genre,
"theme" : theme,
"format": format,
"tags" : tags,
"publisher": publisher,
"published": text.parse_int(comic["year"]),
"description": comic["desc"],
"demographic": props["demographic"],
"origin": comic["iso639_1"],
"mature": props["matureContent"],
"rating": comic["content_rating"],
"rank" : comic["follow_rank"],
"score" : text.parse_float(comic["bayesian_rating"]),
"status": "Complete" if comic["status"] == 2 else "Ongoing",
"links" : comic["links"],
"_build_id": data["buildId"],
}
def _chapter_info(self, manga, chstr):
slug = manga['manga_slug']
url = (f"{self.root}/_next/data/{manga['_build_id']}"
f"/comic/{slug}/{chstr}.json")
params = {"slug": slug, "chapter": chstr}
return self.request_json(url, params=params)["pageProps"]
class ComickChapterExtractor(ComickBase, ChapterExtractor):
"""Extractor for comick.io manga chapters"""
archive_fmt = "{chapter_hid}_{page}"
pattern = BASE_PATTERN + r"/comic/([\w-]+)/(\w+-chapter-[^/?#]+)"
example = "https://comick.io/comic/MANGA/ID-chapter-123-en"
def metadata(self, page):
slug, chstr = self.groups
manga = self._manga_info(slug)
props = self._chapter_info(manga, chstr)
ch = props["chapter"]
self._images = ch["md_images"]
chapter, sep, minor = ch["chap"].partition(".")
return {
**manga,
"title" : props["chapTitle"],
"volume" : text.parse_int(ch["vol"]),
"chapter" : text.parse_int(chapter),
"chapter_minor" : sep + minor,
"chapter_id" : ch["id"],
"chapter_hid" : ch["hid"],
"chapter_string": chstr,
"group" : ch["group_name"],
"date" : text.parse_datetime(
ch["created_at"][:19], "%Y-%m-%dT%H:%M:%S"),
"date_updated" : text.parse_datetime(
ch["updated_at"][:19], "%Y-%m-%dT%H:%M:%S"),
"lang" : ch["lang"],
}
def images(self, page):
return [
("https://meo.comick.pictures/" + img["b2key"], {
"width" : img["w"],
"height" : img["h"],
"size" : img["s"],
"optimized": img["optimized"],
})
for img in self._images
]
class ComickMangaExtractor(ComickBase, MangaExtractor):
"""Extractor for comick.io manga"""
pattern = BASE_PATTERN + r"/comic/([\w-]+)/?(?:\?([^#]+))?"
example = "https://comick.io/comic/MANGA"
def items(self):
slug = self.groups[0]
manga = self._manga_info(slug)
for ch in self.chapters(manga):
url = (f"{self.root}/comic/{slug}"
f"/{ch['hid']}-chapter-{ch['chap']}-{ch['lang']}")
ch.update(manga)
chapter, sep, minor = ch["chap"].partition(".")
ch["chapter"] = text.parse_int(chapter)
ch["chapter_minor"] = sep + minor
ch["_extractor"] = ComickChapterExtractor
yield Message.Queue, url, ch
def chapters(self, manga):
info = True
slug, query = self.groups
url = f"https://api.comick.io/comic/{manga['manga_hid']}/chapters"
headers = {
"Origin": "https://comick.io",
"Sec-Fetch-Dest": "empty",
"Sec-Fetch-Mode": "cors",
"Sec-Fetch-Site": "same-site",
}
query = text.parse_query(query)
params = {"lang": query.get("lang") or None}
params["page"] = page = text.parse_int(query.get("page"), 1)
if date_order := query.get("date-order"):
params["date-order"] = date_order
elif chap_order := query.get("chap-order"):
params["chap-order"] = chap_order
else:
params["chap-order"] = \
"0" if self.config("chapter-reverse", False) else "1"
group = query.get("group", None)
if group == "0":
group = None
while True:
data = self.request_json(url, params=params, headers=headers)
limit = data["limit"]
if info:
info = False
total = data["total"] - limit * page
if total > limit:
self.log.info("Collecting %s chapters", total)
if group is None:
yield from data["chapters"]
else:
for ch in data["chapters"]:
if group in ch["group_name"]:
yield ch
if data["total"] <= limit * page:
return
params["page"] = page = page + 1
|
