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
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
|
# -*- 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.
"""Extractors for https://www.weasyl.com/"""
from .common import Extractor, Message
from .. import text
BASE_PATTERN = r"(?:https://)?(?:www\.)?weasyl.com/"
class WeasylExtractor(Extractor):
category = "weasyl"
directory_fmt = ("{category}", "{owner_login}")
filename_fmt = "{submitid} {title}.{extension}"
archive_fmt = "{submitid}"
root = "https://www.weasyl.com"
@staticmethod
def populate_submission(data):
# Some submissions don't have content and can be skipped
if "submission" in data["media"]:
data["url"] = data["media"]["submission"][0]["url"]
data["date"] = text.parse_datetime(
data["posted_at"][:19], "%Y-%m-%dT%H:%M:%S")
text.nameext_from_url(data["url"], data)
return True
return False
def request_submission(self, submitid):
return self.request(
"{}/api/submissions/{}/view".format(self.root, submitid)).json()
def retrieve_journal(self, journalid):
data = self.request(
"{}/api/journals/{}/view".format(self.root, journalid)).json()
data["extension"] = "html"
data["html"] = "text:" + data["content"]
data["date"] = text.parse_datetime(data["posted_at"])
return data
def submissions(self, owner_login, folderid=None):
url = "{}/api/users/{}/gallery".format(self.root, owner_login)
params = {
"nextid" : None,
"folderid": folderid,
}
while True:
data = self.request(url, params=params).json()
for submission in data["submissions"]:
if self.populate_submission(submission):
submission["folderid"] = folderid
# Do any submissions have more than one url? If so
# a urllist of the submission array urls would work.
yield Message.Url, submission["url"], submission
if not data["nextid"]:
return
params["nextid"] = data["nextid"]
class WeasylSubmissionExtractor(WeasylExtractor):
subcategory = "submission"
pattern = BASE_PATTERN + r"(?:~[\w-]+/submissions|submission)/(\d+)"
test = (
("https://www.weasyl.com/~fiz/submissions/2031/a-wesley", {
"pattern": "https://cdn.weasyl.com/~fiz/submissions/2031/41ebc1c29"
"40be928532785dfbf35c37622664d2fbb8114c3b063df969562fc5"
"1/fiz-a-wesley.png",
"keyword": {
"comments" : int,
"date" : "dt:2012-04-20 00:38:04",
"description" : "<p>(flex)</p>",
"favorites" : int,
"folder_name" : "Wesley Stuff",
"folderid" : 2081,
"friends_only": False,
"owner" : "Fiz",
"owner_login" : "fiz",
"rating" : "general",
"submitid" : 2031,
"subtype" : "visual",
"tags" : list,
"title" : "A Wesley!",
"type" : "submission",
"views" : int,
},
}),
("https://www.weasyl.com/submission/2031/a-wesley"),
)
def __init__(self, match):
WeasylExtractor.__init__(self, match)
self.submitid = match.group(1)
def items(self):
data = self.request_submission(self.submitid)
if self.populate_submission(data):
yield Message.Directory, data
yield Message.Url, data["url"], data
class WeasylSubmissionsExtractor(WeasylExtractor):
subcategory = "submissions"
pattern = BASE_PATTERN + r"(?:~|submissions/)([\w-]+)/?$"
test = (
("https://www.weasyl.com/~tanidareal", {
"count": ">= 200"
}),
("https://www.weasyl.com/submissions/tanidareal"),
)
def __init__(self, match):
WeasylExtractor.__init__(self, match)
self.owner_login = match.group(1)
def items(self):
yield Message.Version, 1
yield Message.Directory, {"owner_login": self.owner_login}
yield from self.submissions(self.owner_login)
class WeasylFolderExtractor(WeasylExtractor):
subcategory = "folder"
directory_fmt = ("{category}", "{owner_login}", "{folder_name}")
pattern = BASE_PATTERN + r"submissions/([\w-]+)\?folderid=(\d+)"
test = ("https://www.weasyl.com/submissions/tanidareal?folderid=7403", {
"count": ">= 12"
})
def __init__(self, match):
WeasylExtractor.__init__(self, match)
self.owner_login, self.folderid = match.groups()
def items(self):
yield Message.Version, 1
iter = self.submissions(self.owner_login, self.folderid)
# Folder names are only on single submission api calls
msg, url, data = next(iter)
details = self.request_submission(data["submitid"])
yield Message.Directory, details
yield msg, url, data
yield from iter
class WeasylJournalExtractor(WeasylExtractor):
subcategory = "journal"
filename_fmt = "{journalid} {title}.{extension}"
archive_fmt = "{journalid}"
pattern = BASE_PATTERN + r"journal/(\d+)"
test = ("https://www.weasyl.com/journal/17647/bbcode", {
"keyword": {
"title" : "BBCode",
"date" : "dt:2013-09-19 23:11:23",
"content": "<p><a>javascript:alert(42);</a></p>"
"<p>No more of that!</p>",
},
})
def __init__(self, match):
WeasylExtractor.__init__(self, match)
self.journalid = match.group(1)
def items(self):
data = self.retrieve_journal(self.journalid)
yield Message.Version, 1
yield Message.Directory, data
yield Message.Url, data["html"], data
class WeasylJournalsExtractor(WeasylExtractor):
subcategory = "journals"
filename_fmt = "{journalid} {title}.{extension}"
archive_fmt = "{journalid}"
pattern = BASE_PATTERN + r"journals/([\w-]+)"
test = ("https://www.weasyl.com/journals/charmander", {
"count": ">= 2",
})
def __init__(self, match):
WeasylExtractor.__init__(self, match)
self.owner_login = match.group(1)
def items(self):
yield Message.Version, 1
yield Message.Directory, {"owner_login": self.owner_login}
url = "{}/journals/{}".format(self.root, self.owner_login)
page = self.request(url).text
for journalid in text.extract_iter(page, 'href="/journal/', '/'):
data = self.retrieve_journal(journalid)
yield Message.Url, data["html"], data
class WeasylFavoriteExtractor(WeasylExtractor):
subcategory = "favorite"
directory_fmt = ("{category}", "{owner_login}", "Favorites")
pattern = BASE_PATTERN + r"favorites\?userid=(\d+)&feature=submit"
test = ("https://www.weasyl.com/favorites?userid=184616&feature=submit", {
"count": ">= 5",
})
def __init__(self, match):
WeasylExtractor.__init__(self, match)
self.userid = match.group(1)
def items(self):
owner_login = lastid = None
url = self.root + "/favorites"
params = {
"userid" : self.userid,
"feature": "submit",
}
while True:
page = self.request(url, params=params).text
pos = page.index('id="favorites-content"')
if not owner_login:
owner_login = text.extract(page, '<a href="/~', '"')[0]
yield Message.Directory, {"owner_login": owner_login}
for submitid in text.extract_iter(page, "/submissions/", "/", pos):
if submitid == lastid:
continue
lastid = submitid
submission = self.request_submission(submitid)
if self.populate_submission(submission):
yield Message.Url, submission["url"], submission
if "&nextid=" not in page:
return
params["nextid"] = submitid
|
