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
|
# -*- 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.
"""Extract images from https://speakerdeck.com/"""
from .common import Extractor, Message
from .. import text
class SpeakerdeckPresentationExtractor(Extractor):
"""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}"
pattern = (r"(?:https?://)?(?:www\.)?speakerdeck\.com"
r"/([^/?&#]+)/([^/?&#]+)")
test = (
(("https://speakerdeck.com/speakerdeck/introduction-to-speakerdeck"), {
"pattern": r"https://files.speakerdeck.com/presentations/"
r"50021f75cf1db900020005e7/slide_\d+.jpg",
"content": "75c7abf0969b0bcab23e0da9712c95ee5113db3a",
"count": 6,
}),
)
def __init__(self, match):
Extractor.__init__(self, match)
self.user, self.presentation = match.groups()
self.presentation_id = None
def items(self):
data = self.get_job_metadata()
imgs = self.get_image_urls()
data["count"] = len(imgs)
yield Message.Version, 1
yield Message.Directory, data
for data["num"], url in enumerate(imgs, 1):
yield Message.Url, url, text.nameext_from_url(url, data)
def get_job_metadata(self):
"""Collect metadata for extractor-job"""
url = "https://speakerdeck.com/oembed.json"
params = {
"url": "https://speakerdeck.com/" + self.user +
"/" + self.presentation,
}
data = self.request(url, params=params).json()
self.presentation_id, pos = \
text.extract(data["html"], 'src="//speakerdeck.com/player/', '"')
return {
"user": self.user,
"presentation": self.presentation,
"presentation_id": self.presentation_id,
"title": data["title"],
"author": data["author_name"],
}
def get_image_urls(self):
"""Extract and return a list of all image-urls"""
page = self.request("https://speakerdeck.com/player/" +
self.presentation_id).text
return list(text.extract_iter(page, 'js-sd-slide" data-url="', '"'))
|
