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
74
75
76
77
78
79
80
81
82
83
|
# -*- coding: utf-8 -*-
# Copyright 2019-2023 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://issuu.com/"""
from .common import GalleryExtractor, Extractor, Message
from .. import text, util
class IssuuBase():
"""Base class for issuu extractors"""
category = "issuu"
root = "https://issuu.com"
class IssuuPublicationExtractor(IssuuBase, GalleryExtractor):
"""Extractor for a single publication"""
subcategory = "publication"
directory_fmt = ("{category}", "{document[username]}",
"{document[date]:%Y-%m-%d} {document[title]}")
filename_fmt = "{num:>03}.{extension}"
archive_fmt = "{document[publicationId]}_{num}"
pattern = r"(?:https?://)?issuu\.com(/[^/?#]+/docs/[^/?#]+)"
example = "https://issuu.com/issuu/docs/TITLE/"
def metadata(self, page):
pos = page.rindex('id="initial-data"')
data = util.json_loads(text.rextract(
page, '<script data-json="', '"', pos)[0].replace(""", '"'))
doc = data["initialDocumentData"]["document"]
doc["date"] = text.parse_datetime(
doc["originalPublishDateInISOString"], "%Y-%m-%dT%H:%M:%S.%fZ")
self._cnt = text.parse_int(doc["pageCount"])
self._tpl = "https://{}/{}-{}/jpg/page_{{}}.jpg".format(
data["config"]["hosts"]["image"],
doc["revisionId"],
doc["publicationId"],
)
return {"document": doc}
def images(self, page):
fmt = self._tpl.format
return [(fmt(i), None) for i in range(1, self._cnt + 1)]
class IssuuUserExtractor(IssuuBase, Extractor):
"""Extractor for all publications of a user/publisher"""
subcategory = "user"
pattern = r"(?:https?://)?issuu\.com/([^/?#]+)(?:/(\d*))?$"
example = "https://issuu.com/USER"
def items(self):
user, pnum = self.groups
base = self.root + "/" + user
pnum = text.parse_int(pnum, 1)
while True:
url = base + "/" + str(pnum) if pnum > 1 else base
try:
html = self.request(url).text
data = util.json_loads(text.unescape(text.extr(
html, '</main></div><script data-json="', '" id="')))
docs = data["docs"]
except Exception as exc:
self.log.debug("", exc_info=exc)
return
for publication in docs:
url = self.root + "/" + publication["uri"]
publication["_extractor"] = IssuuPublicationExtractor
yield Message.Queue, url, publication
if len(docs) < 48:
return
pnum += 1
|
