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
|
# -*- 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.
"""Extractor for https://telegra.ph/"""
from .common import GalleryExtractor
from .. import text
class TelegraphGalleryExtractor(GalleryExtractor):
"""Extractor for articles from telegra.ph"""
category = "telegraph"
root = "https://telegra.ph"
directory_fmt = ("{category}", "{slug}")
filename_fmt = "{num_formatted}_{filename}.{extension}"
archive_fmt = "{slug}_{num}"
pattern = r"(?:https?://)(?:www\.)??telegra\.ph(/[^/?#]+)"
example = "https://telegra.ph/TITLE"
def metadata(self, page):
extr = text.extract_from(page)
data = {
"title": text.unescape(extr(
'property="og:title" content="', '"')),
"description": text.unescape(extr(
'property="og:description" content="', '"')),
"date": self.parse_datetime_iso(extr(
'property="article:published_time" content="', '"')),
"author": text.unescape(extr(
'property="article:author" content="', '"')),
"post_url": text.unescape(extr(
'rel="canonical" href="', '"')),
}
data["slug"] = data["post_url"][19:]
return data
def images(self, page):
figures = (tuple(text.extract_iter(page, "<figure>", "</figure>")) or
tuple(text.extract_iter(page, "<img", ">")))
num_zeroes = len(str(len(figures)))
num = 0
results = []
for figure in figures:
url, pos = text.extract(figure, 'src="', '"')
if url.startswith("/embed/"):
continue
elif url[0] == "/":
url = self.root + url
caption, pos = text.extract(figure, "<figcaption>", "<", pos)
num += 1
results.append((url, {
"url" : url,
"caption" : text.unescape(caption) if caption else "",
"num" : num,
"num_formatted": str(num).zfill(num_zeroes),
}))
return results
|
