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
|
# -*- 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://www.vogue.com/photovogue/"""
from .common import Extractor, Message
from .. import text
BASE_PATTERN = r"(?:https?://)?(?:www\.)?vogue\.com/photovogue"
class PhotovogueUserExtractor(Extractor):
category = "photovogue"
subcategory = "user"
directory_fmt = ("{category}", "{photographer[id]} {photographer[name]}")
filename_fmt = "{id} {title}.{extension}"
archive_fmt = "{id}"
pattern = rf"{BASE_PATTERN}/photographers/(\d+)"
example = "https://www.vogue.com/photovogue/photographers/12345"
def __init__(self, match):
Extractor.__init__(self, match)
self.user_id = match[1]
def items(self):
for photo in self.photos():
url = photo["gallery_image"]
photo["title"] = photo["title"].strip()
photo["date"] = self.parse_datetime_iso(photo["date"])
yield Message.Directory, "", photo
yield Message.Url, url, text.nameext_from_url(url, photo)
def photos(self):
url = "https://api.vogue.com/production/photos"
params = {
"count": "50",
"order_by": "DESC",
"page": 0,
"photographer_id": self.user_id,
}
while True:
data = self.request_json(url, params=params)
yield from data["items"]
if not data["has_next"]:
break
params["page"] += 1
|
