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
|
# -*- coding: utf-8 -*-
# Copyright 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.
"""Extractor for https://are.na/"""
from .common import GalleryExtractor
class ArenaChannelExtractor(GalleryExtractor):
"""Extractor for are.na channels"""
category = "arena"
subcategory = "channel"
root = "https://are.na"
directory_fmt = ("{category}", "{user[full_name]} ({user[id]})",
"{channel[title]} ({channel[id]})")
filename_fmt = "{num:>03}{block[id]:? //}.{extension}"
archive_fmt = "{channel[id]}/{block[id]}"
pattern = r"(?:https?://)?(?:www\.)?are\.na/[^/?#]+/([^/?#]+)"
example = "https://are.na/evan-collins-1522646491/cassette-futurism"
def metadata(self, page):
channel = self.request_json(
f"https://api.are.na/v2/channels/{self.groups[0]}")
channel["date"] = self.parse_datetime_iso(
channel["created_at"])
channel["date_updated"] = self.parse_datetime_iso(
channel["updated_at"])
channel.pop("contents", None)
return {
"count" : channel.get("length"),
"user" : channel.pop("user", None),
"owner" : channel.pop("owner", None),
"channel": channel,
}
def images(self, page):
api = f"https://api.are.na/v2/channels/{self.groups[0]}/contents"
limit = 100
params = {"page": 1, "per": limit}
while True:
data = self.request_json(api, params=params)
contents = data.get("contents")
if not contents:
return
for block in contents:
url = None
# Attachments (e.g., PDFs, files)
if attachment := block.get("attachment"):
url = attachment.get("url")
# Images
elif image := block.get("image"):
# Prefer original image
if original := image.get("original"):
url = original.get("url")
# Fallback to display/large image if present
elif display := image.get("display"):
url = display.get("url")
elif large := image.get("large"):
url = large.get("url")
# Some Links/Channels may not have downloadable media
if not url:
continue
block["date"] = self.parse_datetime_iso(
block["created_at"])
block["date_updated"] = self.parse_datetime_iso(
block["updated_at"])
yield url, {
"block" : block,
"source": block.pop("source", None),
}
if len(contents) < limit:
return
params["page"] += 1
|
