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
|
# -*- coding: utf-8 -*-
# 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://lightroom.adobe.com/"""
from .common import Extractor, Message
from .. import text, util
class LightroomGalleryExtractor(Extractor):
"""Extractor for an image gallery on lightroom.adobe.com"""
category = "lightroom"
subcategory = "gallery"
directory_fmt = ("{category}", "{user}", "{title}")
filename_fmt = "{num:>04}_{id}.{extension}"
archive_fmt = "{id}"
pattern = r"(?:https?://)?lightroom\.adobe\.com/shares/([0-9a-f]+)"
example = "https://lightroom.adobe.com/shares/0123456789abcdef"
def __init__(self, match):
Extractor.__init__(self, match)
self.href = match[1]
def items(self):
# Get config
url = "https://lightroom.adobe.com/shares/" + self.href
response = self.request(url)
album = util.json_loads(
text.extr(response.text, "albumAttributes: ", "\n")
)
images = self.images(album)
for img in images:
url = img["url"]
yield Message.Directory, img
yield Message.Url, url, text.nameext_from_url(url, img)
def metadata(self, album):
payload = album["payload"]
story = payload.get("story") or {}
return {
"gallery_id": self.href,
"user": story.get("author", ""),
"title": story.get("title", payload["name"]),
}
def images(self, album):
album_md = self.metadata(album)
base_url = album["base"]
next_url = album["links"]["/rels/space_album_images_videos"]["href"]
num = 1
while next_url:
url = base_url + next_url
page = self.request(url).text
# skip 1st line as it's a JS loop
data = util.json_loads(page[page.index("\n") + 1:])
base_url = data["base"]
for res in data["resources"]:
img_url, img_size = None, 0
for key, value in res["asset"]["links"].items():
if not key.startswith("/rels/rendition_type/"):
continue
size = text.parse_int(key.split("/")[-1])
if size > img_size:
img_size = size
img_url = value["href"]
if img_url:
img = {
"id": res["asset"]["id"],
"num": num,
"url": base_url + img_url,
}
img.update(album_md)
yield img
num += 1
try:
next_url = data["links"]["next"]["href"]
except KeyError:
next_url = None
|
