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
|
# -*- coding: utf-8 -*-
# Copyright 2020 Leonardo Taccari
#
# 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://speakerdeck.com/"""
from .common import GalleryExtractor
from .. import text, util
class SpeakerdeckPresentationExtractor(GalleryExtractor):
"""Extractor for images from a presentation on speakerdeck.com"""
category = "speakerdeck"
subcategory = "presentation"
directory_fmt = ("{category}", "{user}")
filename_fmt = "{presentation}-{num:>02}.{extension}"
archive_fmt = "{presentation}_{num}"
root = "https://speakerdeck.com"
pattern = r"(?:https?://)?(?:www\.)?speakerdeck\.com/([^/?#]+)/([^/?#]+)"
example = "https://speakerdeck.com/USER/PRESENTATION"
def metadata(self, _):
user, presentation = self.groups
url = self.root + "/oembed.json"
params = {
"url": f"{self.root}/{user}/{presentation}",
}
data = self.request_json(url, params=params)
self.presentation_id = text.extr(
data["html"], 'src="//speakerdeck.com/player/', '"')
return {
"user": user,
"presentation": presentation,
"presentation_id": self.presentation_id,
"title": data["title"],
"author": data["author_name"],
}
def images(self, _):
url = f"{self.root}/player/{self.presentation_id}"
page = self.request(url).text
page = util.re(r"\s+").sub(" ", page)
return [
(url, None)
for url in text.extract_iter(page, 'js-sd-slide" data-url="', '"')
]
|
