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
|
# -*- coding: utf-8 -*-
# Copyright 2019-2020 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://comics.8muses.com/"""
from .common import Extractor, Message
from .. import text
import json
class _8musesAlbumExtractor(Extractor):
"""Extractor for image albums on comics.8muses.com"""
category = "8muses"
subcategory = "album"
directory_fmt = ("{category}", "{album[path]}")
filename_fmt = "{page:>03}.{extension}"
archive_fmt = "{hash}"
root = "https://comics.8muses.com"
pattern = (r"(?:https?://)?(?:comics\.|www\.)?8muses\.com"
r"(/comics/album/[^?&#]+)(\?[^#]+)?")
test = (
("https://comics.8muses.com/comics/album/Fakku-Comics/mogg/Liar", {
"url": "6286ac33087c236c5a7e51f8a9d4e4d5548212d4",
"pattern": r"https://comics.8muses.com/image/fl/[\w-]+",
"keyword": {
"url" : str,
"hash" : str,
"page" : int,
"count": 6,
"album": {
"id" : 10467,
"title" : "Liar",
"path" : "Fakku Comics/mogg/Liar",
"private": False,
"url" : str,
"parent" : 10464,
"views" : int,
"likes" : int,
"date" : "dt:2018-07-10 00:00:00",
},
},
}),
("https://www.8muses.com/comics/album/Fakku-Comics/santa", {
"count": ">= 3",
"pattern": pattern,
"keyword": {
"url" : str,
"name" : str,
"private": False,
},
}),
("https://www.8muses.com/comics/album/Fakku-Comics/8?sort=az", {
"count": ">= 70",
"keyword": {"name": r"re:^[R-Zr-z]"},
}),
)
def __init__(self, match):
Extractor.__init__(self, match)
self.path = match.group(1)
self.params = match.group(2) or ""
def items(self):
url = self.root + self.path + self.params
while True:
data = self._unobfuscate(text.extract(
self.request(url).text,
'id="ractive-public" type="text/plain">', '</script>')[0])
images = data.get("pictures")
if images:
count = len(images)
album = self._make_album(data["album"])
yield Message.Directory, {"album": album, "count": count}
for num, image in enumerate(images, 1):
url = self.root + "/image/fl/" + image["publicUri"]
img = {
"url" : url,
"page" : num,
"hash" : image["publicUri"],
"count" : count,
"album" : album,
"extension": "jpg",
}
yield Message.Url, url, img
albums = data.get("albums")
if albums:
for album in albums:
url = self.root + "/comics/album/" + album["permalink"]
album = {
"url" : url,
"name" : album["name"],
"private": album["isPrivate"],
}
yield Message.Queue, url, album
if data["page"] >= data["pages"]:
return
path, _, num = self.path.rstrip("/").rpartition("/")
path = path if num.isdecimal() else self.path
url = "{}{}/{}{}".format(
self.root, path, data["page"] + 1, self.params)
def _make_album(self, album):
return {
"id" : album["id"],
"path" : album["path"],
"title" : album["name"],
"private": album["isPrivate"],
"url" : self.root + album["permalink"],
"parent" : text.parse_int(album["parentId"]),
"views" : text.parse_int(album["numberViews"]),
"likes" : text.parse_int(album["numberLikes"]),
"date" : text.parse_datetime(
album["updatedAt"], "%Y-%m-%dT%H:%M:%S.%fZ"),
}
@staticmethod
def _unobfuscate(data):
return json.loads("".join([
chr(33 + (ord(c) + 14) % 94) if c != " " else c
for c in text.unescape(data.strip("\t\n\r !"))
]))
|
