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
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
|
# -*- coding: utf-8 -*-
# Copyright 2022 Ailothaen
# Copyright 2024 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 Wikimedia sites"""
from .common import BaseExtractor, Message
from .. import text
class WikimediaExtractor(BaseExtractor):
"""Base class for wikimedia extractors"""
basecategory = "wikimedia"
filename_fmt = "{filename} ({sha1[:8]}).{extension}"
directory_fmt = ("{category}", "{page}")
archive_fmt = "{sha1}"
request_interval = (1.0, 2.0)
def __init__(self, match):
BaseExtractor.__init__(self, match)
path = match.group(match.lastindex)
if self.category == "wikimedia":
self.category = self.root.split(".")[-2]
elif self.category == "fandom":
self.category = \
"fandom-" + self.root.partition(".")[0].rpartition("/")[2]
if path.startswith("wiki/"):
path = path[5:]
pre, sep, _ = path.partition(":")
prefix = pre.lower() if sep else None
self.title = path = text.unquote(path)
if prefix:
self.subcategory = prefix
if prefix == "category":
self.params = {
"generator": "categorymembers",
"gcmtitle" : path,
"gcmtype" : "file",
}
elif prefix == "file":
self.params = {
"titles" : path,
}
else:
self.params = {
"generator": "images",
"titles" : path,
}
def _init(self):
api_path = self.config_instance("api-path")
if api_path:
if api_path[0] == "/":
self.api_url = self.root + api_path
else:
self.api_url = api_path
else:
self.api_url = self.root + "/api.php"
def items(self):
for info in self._pagination(self.params):
image = info["imageinfo"][0]
image["metadata"] = {
m["name"]: m["value"]
for m in image["metadata"]}
image["commonmetadata"] = {
m["name"]: m["value"]
for m in image["commonmetadata"]}
filename = image["canonicaltitle"]
image["filename"], _, image["extension"] = \
filename.partition(":")[2].rpartition(".")
image["date"] = text.parse_datetime(
image["timestamp"], "%Y-%m-%dT%H:%M:%SZ")
image["page"] = self.title
yield Message.Directory, image
yield Message.Url, image["url"], image
def _pagination(self, params):
"""
https://www.mediawiki.org/wiki/API:Query
https://opendata.stackexchange.com/questions/13381
"""
url = self.api_url
params["action"] = "query"
params["format"] = "json"
params["prop"] = "imageinfo"
params["iiprop"] = (
"timestamp|user|userid|comment|canonicaltitle|url|size|"
"sha1|mime|metadata|commonmetadata|extmetadata|bitdepth"
)
while True:
data = self.request(url, params=params).json()
try:
pages = data["query"]["pages"]
except KeyError:
pass
else:
yield from pages.values()
try:
continuation = data["continue"]
except KeyError:
break
params.update(continuation)
BASE_PATTERN = WikimediaExtractor.update({
"wikimedia": {
"root": None,
"pattern": r"[a-z]{2,}\."
r"wik(?:i(?:pedia|quote|books|source|news|versity|data"
r"|voyage)|tionary)"
r"\.org",
"api-path": "/w/api.php",
},
"wikispecies": {
"root": "https://species.wikimedia.org",
"pattern": r"species\.wikimedia\.org",
"api-path": "/w/api.php",
},
"wikimediacommons": {
"root": "https://commons.wikimedia.org",
"pattern": r"commons\.wikimedia\.org",
"api-path": "/w/api.php",
},
"mediawiki": {
"root": "https://www.mediawiki.org",
"pattern": r"(?:www\.)?mediawiki\.org",
"api-path": "/w/api.php",
},
"fandom": {
"root": None,
"pattern": r"[\w-]+\.fandom\.com",
},
"mariowiki": {
"root": "https://www.mariowiki.com",
"pattern": r"(?:www\.)?mariowiki\.com",
},
"bulbapedia": {
"root": "https://bulbapedia.bulbagarden.net",
"pattern": r"(?:bulbapedia|archives)\.bulbagarden\.net",
"api-path": "/w/api.php",
},
"pidgiwiki": {
"root": "https://www.pidgi.net",
"pattern": r"(?:www\.)?pidgi\.net",
"api-path": "/wiki/api.php",
},
"azurlanewiki": {
"root": "https://azurlane.koumakan.jp",
"pattern": r"azurlane\.koumakan\.jp",
"api-path": "/w/api.php",
},
})
class WikimediaArticleExtractor(WikimediaExtractor):
"""Extractor for wikimedia articles"""
subcategory = "article"
pattern = BASE_PATTERN + r"/(?!static/)([^?#]+)"
example = "https://en.wikipedia.org/wiki/TITLE"
|
