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
|
# -*- coding: utf-8 -*-
# Copyright 2019-2020 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://www.lineblog.me/"""
from .livedoor import LivedoorBlogExtractor, LivedoorPostExtractor
from .. import text
class LineblogBase():
"""Base class for lineblog extractors"""
category = "lineblog"
root = "https://lineblog.me"
def _images(self, post):
imgs = []
body = post.pop("body")
for num, img in enumerate(text.extract_iter(body, "<img ", ">"), 1):
src = text.extr(img, 'src="', '"')
alt = text.extr(img, 'alt="', '"')
if not src:
continue
if src.startswith("https://obs.line-scdn.") and src.count("/") > 3:
src = src.rpartition("/")[0]
imgs.append(text.nameext_from_url(alt or src, {
"url" : src,
"num" : num,
"hash": src.rpartition("/")[2],
"post": post,
}))
return imgs
class LineblogBlogExtractor(LineblogBase, LivedoorBlogExtractor):
"""Extractor for a user's blog on lineblog.me"""
pattern = r"(?:https?://)?lineblog\.me/(\w+)/?(?:$|[?#])"
test = ("https://lineblog.me/mamoru_miyano/", {
"range": "1-20",
"count": 20,
"pattern": r"https://obs.line-scdn.net/[\w-]+$",
"keyword": {
"post": {
"categories" : tuple,
"date" : "type:datetime",
"description": str,
"id" : int,
"tags" : list,
"title" : str,
"user" : "mamoru_miyano"
},
"filename": str,
"hash" : r"re:\w{32,}",
"num" : int,
},
})
class LineblogPostExtractor(LineblogBase, LivedoorPostExtractor):
"""Extractor for blog posts on lineblog.me"""
pattern = r"(?:https?://)?lineblog\.me/(\w+)/archives/(\d+)"
test = ("https://lineblog.me/mamoru_miyano/archives/1919150.html", {
"url": "24afeb4044c554f80c374b52bf8109c6f1c0c757",
"keyword": "76a38e2c0074926bd3362f66f9fc0e6c41591dcb",
})
|
