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
|
# -*- coding: utf-8 -*-
# Copyright 2021-2025 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.
"""Extractors for https://unsplash.com/"""
from .common import Extractor, Message
from .. import text, util
BASE_PATTERN = r"(?:https?://)?unsplash\.com"
class UnsplashExtractor(Extractor):
"""Base class for unsplash extractors"""
category = "unsplash"
directory_fmt = ("{category}", "{user[username]}")
filename_fmt = "{id}.{extension}"
archive_fmt = "{id}"
root = "https://unsplash.com"
page_start = 1
per_page = 20
def __init__(self, match):
Extractor.__init__(self, match)
self.item = match[1]
def items(self):
fmt = self.config("format") or "raw"
metadata = self.metadata()
for photo in self.photos():
util.delete_items(
photo, ("current_user_collections", "related_collections"))
url = photo["urls"][fmt]
text.nameext_from_url(url, photo)
if metadata:
photo.update(metadata)
photo["extension"] = "jpg"
photo["date"] = self.parse_datetime_iso(photo["created_at"])
if "tags" in photo:
photo["tags"] = [t["title"] for t in photo["tags"]]
yield Message.Directory, "", photo
yield Message.Url, url, photo
def metadata(self):
return None
def skip(self, num):
pages = num // self.per_page
self.page_start += pages
return pages * self.per_page
def _pagination(self, url, params, results=False):
params["per_page"] = self.per_page
params["page"] = self.page_start
while True:
photos = self.request_json(url, params=params)
if results:
photos = photos["results"]
yield from photos
if len(photos) < self.per_page:
return
params["page"] += 1
class UnsplashImageExtractor(UnsplashExtractor):
"""Extractor for a single unsplash photo"""
subcategory = "image"
pattern = BASE_PATTERN + r"/photos/([^/?#]+)"
example = "https://unsplash.com/photos/ID"
def photos(self):
url = f"{self.root}/napi/photos/{self.item}"
return (self.request_json(url),)
class UnsplashUserExtractor(UnsplashExtractor):
"""Extractor for all photos of an unsplash user"""
subcategory = "user"
pattern = BASE_PATTERN + r"/@(\w+)/?$"
example = "https://unsplash.com/@USER"
def photos(self):
url = f"{self.root}/napi/users/{self.item}/photos"
params = {"order_by": "latest"}
return self._pagination(url, params)
class UnsplashFavoriteExtractor(UnsplashExtractor):
"""Extractor for all likes of an unsplash user"""
subcategory = "favorite"
pattern = BASE_PATTERN + r"/@(\w+)/likes"
example = "https://unsplash.com/@USER/likes"
def photos(self):
url = f"{self.root}/napi/users/{self.item}/likes"
params = {"order_by": "latest"}
return self._pagination(url, params)
class UnsplashCollectionExtractor(UnsplashExtractor):
"""Extractor for an unsplash collection"""
subcategory = "collection"
pattern = BASE_PATTERN + r"/collections/([^/?#]+)(?:/([^/?#]+))?"
example = "https://unsplash.com/collections/12345/TITLE"
def __init__(self, match):
UnsplashExtractor.__init__(self, match)
self.title = match[2] or ""
def metadata(self):
return {"collection_id": self.item, "collection_title": self.title}
def photos(self):
url = f"{self.root}/napi/collections/{self.item}/photos"
params = {"order_by": "latest"}
return self._pagination(url, params)
class UnsplashSearchExtractor(UnsplashExtractor):
"""Extractor for unsplash search results"""
subcategory = "search"
pattern = BASE_PATTERN + r"/s/photos/([^/?#]+)(?:\?([^#]+))?"
example = "https://unsplash.com/s/photos/QUERY"
def __init__(self, match):
UnsplashExtractor.__init__(self, match)
self.query = match[2]
def photos(self):
url = self.root + "/napi/search/photos"
params = {"query": text.unquote(self.item.replace('-', ' '))}
if self.query:
params.update(text.parse_query(self.query))
return self._pagination(url, params, True)
|
