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
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
|
# -*- coding: utf-8 -*-
# Copyright 2016-2020 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.
"""Extract images from https://seiga.nicovideo.jp/"""
from .common import Extractor, Message
from .. import text, util, exception
from ..cache import cache
class SeigaExtractor(Extractor):
"""Base class for seiga extractors"""
category = "seiga"
archive_fmt = "{image_id}"
cookiedomain = ".nicovideo.jp"
root = "https://seiga.nicovideo.jp"
def __init__(self, match):
Extractor.__init__(self, match)
self.start_image = 0
def items(self):
self.login()
images = iter(self.get_images())
data = next(images)
yield Message.Version, 1
yield Message.Directory, data
for image in util.advance(images, self.start_image):
data.update(image)
data["extension"] = None
yield Message.Url, self.get_image_url(data["image_id"]), data
def get_images(self):
"""Return iterable containing metadata and images"""
def get_image_url(self, image_id):
"""Get url for an image with id 'image_id'"""
url = "{}/image/source/{}".format(self.root, image_id)
response = self.request(
url, method="HEAD", allow_redirects=False, notfound="image")
return response.headers["Location"].replace("/o/", "/priv/", 1)
def login(self):
"""Login and set necessary cookies"""
if not self._check_cookies(("user_session",)):
username, password = self._get_auth_info()
self._update_cookies(self._login_impl(username, password))
@cache(maxage=7*24*3600, keyarg=1)
def _login_impl(self, username, password):
if not username or not password:
raise exception.AuthenticationError(
"Username and password required")
self.log.info("Logging in as %s", username)
url = "https://account.nicovideo.jp/api/v1/login"
data = {"mail_tel": username, "password": password}
self.request(url, method="POST", data=data)
if "user_session" not in self.session.cookies:
raise exception.AuthenticationError()
del self.session.cookies["nicosid"]
return self.session.cookies
class SeigaUserExtractor(SeigaExtractor):
"""Extractor for images of a user from seiga.nicovideo.jp"""
subcategory = "user"
directory_fmt = ("{category}", "{user[id]}")
filename_fmt = "{category}_{user[id]}_{image_id}.{extension}"
pattern = (r"(?:https?://)?(?:www\.|(?:sp\.)?seiga\.)?nicovideo\.jp/"
r"user/illust/(\d+)(?:\?(?:[^&]+&)*sort=([^&#]+))?")
test = (
("https://seiga.nicovideo.jp/user/illust/39537793", {
"pattern": r"https://lohas\.nicoseiga\.jp/priv/[0-9a-f]+/\d+/\d+",
"count": ">= 4",
"keyword": {
"user": {
"id": 39537793,
"message": str,
"name": str,
},
"clips": int,
"comments": int,
"count": int,
"extension": None,
"image_id": int,
"title": str,
"views": int,
},
}),
("https://seiga.nicovideo.jp/user/illust/79433", {
"exception": exception.NotFoundError,
}),
("https://seiga.nicovideo.jp/user/illust/39537793"
"?sort=image_view&target=illust_all"),
("https://sp.seiga.nicovideo.jp/user/illust/39537793"),
)
def __init__(self, match):
SeigaExtractor.__init__(self, match)
self.user_id, self.order = match.groups()
self.start_page = 1
def skip(self, num):
pages, images = divmod(num, 40)
self.start_page += pages
self.start_image += images
return num
def get_metadata(self, page):
"""Collect metadata from 'page'"""
data = text.extract_all(page, (
("name" , '<img alt="', '"'),
("msg" , '<li class="user_message">', '</li>'),
(None , '<span class="target_name">すべて</span>', ''),
("count", '<span class="count ">', '</span>'),
))[0]
if not data["name"] and "ユーザー情報が取得出来ませんでした" in page:
raise exception.NotFoundError("user")
return {
"user": {
"id": text.parse_int(self.user_id),
"name": data["name"],
"message": (data["msg"] or "").strip(),
},
"count": text.parse_int(data["count"]),
}
def get_images(self):
url = "{}/user/illust/{}".format(self.root, self.user_id)
params = {"sort": self.order, "page": self.start_page,
"target": "illust_all"}
while True:
cnt = 0
page = self.request(url, params=params).text
if params["page"] == self.start_page:
yield self.get_metadata(page)
for info in text.extract_iter(
page, '<li class="list_item', '</a></li> '):
data = text.extract_all(info, (
("image_id", '/seiga/im', '"'),
("title" , '<li class="title">', '</li>'),
("views" , '</span>', '</li>'),
("comments", '</span>', '</li>'),
("clips" , '</span>', '</li>'),
))[0]
for key in ("image_id", "views", "comments", "clips"):
data[key] = text.parse_int(data[key])
yield data
cnt += 1
if cnt < 40:
return
params["page"] += 1
class SeigaImageExtractor(SeigaExtractor):
"""Extractor for single images from seiga.nicovideo.jp"""
subcategory = "image"
filename_fmt = "{category}_{image_id}.{extension}"
pattern = (r"(?:https?://)?(?:"
r"(?:seiga\.|www\.)?nicovideo\.jp/(?:seiga/im|image/source/)"
r"|sp\.seiga\.nicovideo\.jp/seiga/#!/im"
r"|lohas\.nicoseiga\.jp/(?:thumb|(?:priv|o)/[^/]+/\d+)/)(\d+)")
test = (
("https://seiga.nicovideo.jp/seiga/im5977527", {
"keyword": "c8339781da260f7fc44894ad9ada016f53e3b12a",
"content": "d9202292012178374d57fb0126f6124387265297",
}),
("https://seiga.nicovideo.jp/seiga/im123", {
"exception": exception.NotFoundError,
}),
("https://seiga.nicovideo.jp/image/source/5977527"),
("https://sp.seiga.nicovideo.jp/seiga/#!/im5977527"),
("https://lohas.nicoseiga.jp/thumb/5977527i"),
("https://lohas.nicoseiga.jp/priv"
"/759a4ef1c639106ba4d665ee6333832e647d0e4e/1549727594/5977527"),
("https://lohas.nicoseiga.jp/o"
"/759a4ef1c639106ba4d665ee6333832e647d0e4e/1549727594/5977527"),
)
def __init__(self, match):
SeigaExtractor.__init__(self, match)
self.image_id = match.group(1)
def skip(self, num):
self.start_image += num
return num
def get_images(self):
url = "{}/seiga/im{}".format(self.root, self.image_id)
page = self.request(url, notfound="image").text
data = text.extract_all(page, (
("date" , '<li class="date"><span class="created">', '<'),
("title" , '<h1 class="title">', '</h1>'),
("description" , '<p class="discription">', '</p>'),
))[0]
data["user"] = text.extract_all(page, (
("id" , '<a href="/user/illust/' , '"'),
("name", '<span itemprop="title">', '<'),
))[0]
data["description"] = text.remove_html(data["description"])
data["image_id"] = text.parse_int(self.image_id)
data["date"] = text.parse_datetime(
data["date"] + ":00+0900", "%Y年%m月%d日 %H:%M:%S%z")
return (data, data)
|
