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
|
# -*- coding: utf-8 -*-
# Copyright 2015-2025 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://dynasty-scans.com/"""
from .common import ChapterExtractor, MangaExtractor, Extractor, Message
from .. import text, util
BASE_PATTERN = r"(?:https?://)?(?:www\.)?dynasty-scans\.com"
class DynastyscansBase():
"""Base class for dynastyscans extractors"""
category = "dynastyscans"
root = "https://dynasty-scans.com"
def _parse_image_page(self, image_id):
url = f"{self.root}/images/{image_id}"
extr = text.extract_from(self.request(url).text)
date = extr("class='create_at'>", "</span>")
tags = extr("class='tags'>", "</span>")
src = extr("class='btn-group'>", "</div>")
url = extr(' src="', '"')
src = text.extr(src, 'href="', '"') if "Source<" in src else ""
return {
"url" : self.root + url,
"image_id": text.parse_int(image_id),
"tags" : text.split_html(tags),
"date" : text.remove_html(date),
"source" : text.unescape(src),
}
class DynastyscansChapterExtractor(DynastyscansBase, ChapterExtractor):
"""Extractor for manga-chapters from dynasty-scans.com"""
pattern = BASE_PATTERN + r"(/chapters/[^/?#]+)"
example = "https://dynasty-scans.com/chapters/NAME"
def metadata(self, page):
extr = text.extract_from(page)
match = util.re(
r"(?:<a[^>]*>)?([^<]+)(?:</a>)?" # manga name
r"(?: ch(\d+)([^:<]*))?" # chapter info
r"(?:: (.+))?" # title
).match(extr("<h3 id='chapter-title'><b>", "</b>"))
author = extr(" by ", "</a>")
group = extr('"icon-print"></i> ', '</span>')
return {
"manga" : text.unescape(match[1]),
"chapter" : text.parse_int(match[2]),
"chapter_minor": match[3] or "",
"title" : text.unescape(match[4] or ""),
"author" : text.remove_html(author),
"group" : (text.remove_html(group) or
text.extr(group, ' alt="', '"')),
"date" : text.parse_datetime(extr(
'"icon-calendar"></i> ', '<'), "%b %d, %Y"),
"tags" : text.split_html(extr(
"class='tags'>", "<div id='chapter-actions'")),
"lang" : "en",
"language": "English",
}
def images(self, page):
data = text.extr(page, "var pages = ", ";\n")
return [
(self.root + img["image"], None)
for img in util.json_loads(data)
]
class DynastyscansMangaExtractor(DynastyscansBase, MangaExtractor):
chapterclass = DynastyscansChapterExtractor
reverse = False
pattern = BASE_PATTERN + r"(/series/[^/?#]+)"
example = "https://dynasty-scans.com/series/NAME"
def chapters(self, page):
return [
(self.root + path, {})
for path in text.extract_iter(page, '<dd>\n<a href="', '"')
]
class DynastyscansSearchExtractor(DynastyscansBase, Extractor):
"""Extrator for image search results on dynasty-scans.com"""
subcategory = "search"
directory_fmt = ("{category}", "Images")
filename_fmt = "{image_id}.{extension}"
archive_fmt = "i_{image_id}"
pattern = BASE_PATTERN + r"/images/?(?:\?([^#]+))?$"
example = "https://dynasty-scans.com/images?QUERY"
def __init__(self, match):
Extractor.__init__(self, match)
self.query = match[1] or ""
def items(self):
yield Message.Directory, {}
for image_id in self.images():
image = self._parse_image_page(image_id)
url = image["url"]
yield Message.Url, url, text.nameext_from_url(url, image)
def images(self):
url = self.root + "/images?" + self.query.replace("[]", "%5B%5D")
params = {"page": 1}
while True:
page = self.request(url, params=params).text
yield from text.extract_iter(page, '"/images/', '"')
if 'rel="next"' not in page:
return
params["page"] += 1
class DynastyscansImageExtractor(DynastyscansSearchExtractor):
"""Extractor for individual images on dynasty-scans.com"""
subcategory = "image"
pattern = BASE_PATTERN + r"/images/(\d+)"
example = "https://dynasty-scans.com/images/12345"
def images(self):
return (self.query,)
class DynastyscansAnthologyExtractor(DynastyscansSearchExtractor):
"""Extractor for dynasty-scans anthologies"""
subcategory = "anthology"
pattern = BASE_PATTERN + r"/anthologies/([^/?#]+)"
example = "https://dynasty-scans.com/anthologies/TITLE"
def items(self):
url = f"{self.root}/anthologies/{self.groups[0]}.atom"
root = self.request_xml(url, xmlns=False)
data = {
"_extractor": DynastyscansChapterExtractor,
"anthology" : root[3].text[28:],
}
if self.config("metadata", False):
page = self.request(url[:-5]).text
alert = text.extr(page, "<div class='alert", "</div>")
data["alert"] = text.split_html(alert)[1:] if alert else ()
data["status"] = text.extr(
page, "<small>— ", "</small>")
data["description"] = text.extr(
page, "<div class='description'>", "</div>")
for element in root:
if element.tag != "entry":
continue
content = element[6][0]
data["author"] = content[0].text[8:]
data["scanlator"] = content[1].text[11:]
data["tags"] = content[2].text[6:].lower().split(", ")
data["title"] = element[5].text
data["date"] = text.parse_datetime(
element[1].text, "%Y-%m-%dT%H:%M:%S%z")
data["date_updated"] = text.parse_datetime(
element[2].text, "%Y-%m-%dT%H:%M:%S%z")
yield Message.Queue, element[4].text, data
|
