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
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
|
# -*- coding: utf-8 -*-
# Copyright 2019-2023 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 FoolFuuka 4chan archives"""
from .common import BaseExtractor, Message
from .. import text
import itertools
class FoolfuukaExtractor(BaseExtractor):
"""Base extractor for FoolFuuka based boards/archives"""
basecategory = "foolfuuka"
filename_fmt = "{timestamp_ms} {filename_media}.{extension}"
archive_fmt = "{board[shortname]}_{num}_{timestamp}"
external = "default"
def __init__(self, match):
BaseExtractor.__init__(self, match)
if self.category == "b4k":
self.remote = self._remote_direct
def items(self):
yield Message.Directory, self.metadata()
for post in self.posts():
media = post["media"]
if not media:
continue
url = media["media_link"]
if not url and "remote_media_link" in media:
url = self.remote(media)
if url.startswith("/"):
url = self.root + url
post["filename"], _, post["extension"] = \
media["media"].rpartition(".")
post["filename_media"] = media["media_filename"].rpartition(".")[0]
post["timestamp_ms"] = text.parse_int(
media["media_orig"].rpartition(".")[0])
yield Message.Url, url, post
def metadata(self):
"""Return general metadata"""
def posts(self):
"""Return an iterable with all relevant posts"""
def remote(self, media):
"""Resolve a remote media link"""
needle = '<meta http-equiv="Refresh" content="0; url='
page = self.request(media["remote_media_link"]).text
return text.extr(page, needle, '"')
@staticmethod
def _remote_direct(media):
return media["remote_media_link"]
BASE_PATTERN = FoolfuukaExtractor.update({
"4plebs": {
"root": "https://archive.4plebs.org",
"pattern": r"(?:archive\.)?4plebs\.org",
},
"archivedmoe": {
"root": "https://archived.moe",
"pattern": r"archived\.moe",
},
"archiveofsins": {
"root": "https://archiveofsins.com",
"pattern": r"(?:www\.)?archiveofsins\.com",
},
"b4k": {
"root": "https://arch.b4k.co",
"pattern": r"arch\.b4k\.co",
},
"desuarchive": {
"root": "https://desuarchive.org",
"pattern": r"desuarchive\.org",
},
"fireden": {
"root": "https://boards.fireden.net",
"pattern": r"boards\.fireden\.net",
},
"palanq": {
"root": "https://archive.palanq.win",
"pattern": r"archive\.palanq\.win",
},
"rbt": {
"root": "https://rbt.asia",
"pattern": r"(?:rbt\.asia|(?:archive\.)?rebeccablacktech\.com)",
},
"thebarchive": {
"root": "https://thebarchive.com",
"pattern": r"thebarchive\.com",
},
})
class FoolfuukaThreadExtractor(FoolfuukaExtractor):
"""Base extractor for threads on FoolFuuka based boards/archives"""
subcategory = "thread"
directory_fmt = ("{category}", "{board[shortname]}",
"{thread_num} {title|comment[:50]}")
pattern = BASE_PATTERN + r"/([^/?#]+)/thread/(\d+)"
example = "https://archived.moe/a/thread/12345/"
def __init__(self, match):
FoolfuukaExtractor.__init__(self, match)
self.board = match.group(match.lastindex-1)
self.thread = match.group(match.lastindex)
self.data = None
def metadata(self):
url = self.root + "/_/api/chan/thread/"
params = {"board": self.board, "num": self.thread}
self.data = self.request(url, params=params).json()[self.thread]
return self.data["op"]
def posts(self):
op = (self.data["op"],)
posts = self.data.get("posts")
if posts:
posts = list(posts.values())
posts.sort(key=lambda p: p["timestamp"])
return itertools.chain(op, posts)
return op
class FoolfuukaBoardExtractor(FoolfuukaExtractor):
"""Base extractor for FoolFuuka based boards/archives"""
subcategory = "board"
pattern = BASE_PATTERN + r"/([^/?#]+)/\d*$"
example = "https://archived.moe/a/"
def __init__(self, match):
FoolfuukaExtractor.__init__(self, match)
self.board = match.group(match.lastindex)
def items(self):
index_base = "{}/_/api/chan/index/?board={}&page=".format(
self.root, self.board)
thread_base = "{}/{}/thread/".format(self.root, self.board)
for page in itertools.count(1):
with self.request(index_base + format(page)) as response:
try:
threads = response.json()
except ValueError:
threads = None
if not threads:
return
for num, thread in threads.items():
thread["url"] = thread_base + format(num)
thread["_extractor"] = FoolfuukaThreadExtractor
yield Message.Queue, thread["url"], thread
class FoolfuukaSearchExtractor(FoolfuukaExtractor):
"""Base extractor for search results on FoolFuuka based boards/archives"""
subcategory = "search"
directory_fmt = ("{category}", "search", "{search}")
pattern = BASE_PATTERN + r"/([^/?#]+)/search((?:/[^/?#]+/[^/?#]+)+)"
example = "https://archived.moe/_/search/text/QUERY/"
request_interval = (0.5, 1.5)
def __init__(self, match):
FoolfuukaExtractor.__init__(self, match)
self.params = params = {}
args = match.group(match.lastindex).split("/")
key = None
for arg in args:
if key:
params[key] = text.unescape(arg)
key = None
else:
key = arg
board = match.group(match.lastindex-1)
if board != "_":
params["boards"] = board
def metadata(self):
return {"search": self.params.get("text", "")}
def posts(self):
url = self.root + "/_/api/chan/search/"
params = self.params.copy()
params["page"] = text.parse_int(params.get("page"), 1)
if "filter" not in params:
params["filter"] = "text"
while True:
try:
data = self.request(url, params=params).json()
except ValueError:
return
if isinstance(data, dict):
if data.get("error"):
return
posts = data["0"]["posts"]
elif isinstance(data, list):
posts = data[0]["posts"]
else:
return
yield from posts
if len(posts) <= 3:
return
params["page"] += 1
class FoolfuukaGalleryExtractor(FoolfuukaExtractor):
"""Base extractor for FoolFuuka galleries"""
subcategory = "gallery"
directory_fmt = ("{category}", "{board}", "gallery")
pattern = BASE_PATTERN + r"/([^/?#]+)/gallery(?:/(\d+))?"
example = "https://archived.moe/a/gallery"
def __init__(self, match):
FoolfuukaExtractor.__init__(self, match)
board = match.group(match.lastindex)
if board.isdecimal():
self.board = match.group(match.lastindex-1)
self.pages = (board,)
else:
self.board = board
self.pages = map(format, itertools.count(1))
def metadata(self):
return {"board": self.board}
def posts(self):
base = "{}/_/api/chan/gallery/?board={}&page=".format(
self.root, self.board)
for page in self.pages:
with self.request(base + page) as response:
posts = response.json()
if not posts:
return
yield from posts
|
