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
|
# -*- coding: utf-8 -*-
# Copyright 2016-2023 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://www.pixnet.net/"""
from .common import Extractor, Message
from .. import text, exception
BASE_PATTERN = r"(?:https?://)?(?!www\.)([\w-]+)\.pixnet.net"
class PixnetExtractor(Extractor):
"""Base class for pixnet extractors"""
category = "pixnet"
filename_fmt = "{num:>03}_{id}.{extension}"
archive_fmt = "{id}"
def __init__(self, match):
Extractor.__init__(self, match)
self.blog, self.item_id = self.groups
self.root = f"https://{self.blog}.pixnet.net"
def items(self):
url = self.url_fmt.format(self.root, self.item_id)
page = self.request(url, encoding="utf-8").text
user = text.extr(page, '<meta name="author" content="', '";')
data = {
"blog": self.blog,
"user": user.rpartition(" (")[0],
}
for info in self._pagination(page):
url, pos = text.extract(info, ' href="', '"')
alt, pos = text.extract(info, ' alt="', '"', pos)
item = {
"id" : text.parse_int(url.rpartition("/")[2]),
"title" : text.unescape(alt),
"_extractor": (PixnetFolderExtractor if "/folder/" in url else
PixnetSetExtractor),
}
item.update(data)
yield Message.Queue, url, item
def _pagination(self, page):
while True:
yield from text.extract_iter(page, '<li id="', '</li>')
pnext = text.extr(page, 'class="nextBtn"', '>')
if pnext is None and 'name="albumpass">' in page:
raise exception.AbortExtraction(
f"Album {self.item_id} is password-protected.")
if "href" not in pnext:
return
url = self.root + text.extr(pnext, 'href="', '"')
page = self.request(url, encoding="utf-8").text
class PixnetImageExtractor(PixnetExtractor):
"""Extractor for a single photo from pixnet.net"""
subcategory = "image"
filename_fmt = "{id}.{extension}"
directory_fmt = ("{category}", "{blog}")
pattern = BASE_PATTERN + r"/album/photo/(\d+)"
example = "https://USER.pixnet.net/album/photo/12345"
def items(self):
url = "https://api.pixnet.cc/oembed"
params = {
"url": (f"https://{self.blog}.pixnet.net"
f"/album/photo/{self.item_id}"),
"format": "json",
}
data = self.request_json(url, params=params)
data["id"] = text.parse_int(
data["url"].rpartition("/")[2].partition("-")[0])
data["filename"], _, data["extension"] = data["title"].rpartition(".")
data["blog"] = self.blog
data["user"] = data.pop("author_name")
yield Message.Directory, data
yield Message.Url, data["url"], data
class PixnetSetExtractor(PixnetExtractor):
"""Extractor for images from a pixnet set"""
subcategory = "set"
directory_fmt = ("{category}", "{blog}",
"{folder_id} {folder_title}", "{set_id} {set_title}")
pattern = BASE_PATTERN + r"/album/set/(\d+)"
example = "https://USER.pixnet.net/album/set/12345"
def items(self):
url = f"{self.root}/album/set/{self.item_id}"
page = self.request(url, encoding="utf-8").text
data = self.metadata(page)
yield Message.Directory, data
for num, info in enumerate(self._pagination(page), 1):
url, pos = text.extract(info, ' href="', '"')
src, pos = text.extract(info, ' src="', '"', pos)
alt, pos = text.extract(info, ' alt="', '"', pos)
photo = {
"id": text.parse_int(url.rpartition("/")[2].partition("#")[0]),
"url": src.replace("_s.", "."),
"num": num,
"filename": alt,
"extension": src.rpartition(".")[2],
}
photo.update(data)
yield Message.Url, photo["url"], photo
def metadata(self, page):
user , pos = text.extract(page, '<meta name="author" content="', '";')
_ , pos = text.extract(page, 'id="breadcrumb"', '', pos)
fid , pos = text.extract(page, '/folder/', '"', pos)
fname, pos = text.extract(page, '>', '<', pos)
sid , pos = text.extract(page, '/set/', '"', pos)
sname, pos = text.extract(page, '>', '<', pos)
return {
"blog": self.blog,
"user": user.rpartition(" (")[0],
"folder_id" : text.parse_int(fid, ""),
"folder_title": text.unescape(fname).strip(),
"set_id" : text.parse_int(sid),
"set_title" : text.unescape(sname),
}
class PixnetFolderExtractor(PixnetExtractor):
"""Extractor for all sets in a pixnet folder"""
subcategory = "folder"
url_fmt = "{}/album/folder/{}"
pattern = BASE_PATTERN + r"/album/folder/(\d+)"
example = "https://USER.pixnet.net/album/folder/12345"
class PixnetUserExtractor(PixnetExtractor):
"""Extractor for all sets and folders of a pixnet user"""
subcategory = "user"
url_fmt = "{}{}/album/list"
pattern = BASE_PATTERN + r"()(?:/blog|/album(?:/list)?)?/?(?:$|[?#])"
example = "https://USER.pixnet.net/"
|
