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
|
# -*- coding: utf-8 -*-
# Copyright 2018-2019 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.newgrounds.com/"""
from .common import Extractor, Message
from .. import text
import json
class NewgroundsExtractor(Extractor):
"""Base class for newgrounds extractors"""
category = "newgrounds"
directory_fmt = ("{category}", "{user}")
filename_fmt = "{category}_{index}_{title}.{extension}"
archive_fmt = "{index}"
def __init__(self, match):
Extractor.__init__(self, match)
self.user = match.group(1)
self.root = "https://{}.newgrounds.com".format(self.user)
def items(self):
data = self.get_metadata()
yield Message.Version, 1
yield Message.Directory, data
for page_url in self.get_page_urls():
image = self.parse_page_data(page_url)
image.update(data)
url = image["url"]
yield Message.Url, url, text.nameext_from_url(url, image)
def get_metadata(self):
"""Collect metadata for extractor-job"""
return {"user": self.user}
def get_page_urls(self):
"""Return urls of all relevant image pages"""
def parse_page_data(self, page_url):
"""Collect url and metadata from an image page"""
extr = text.extract_from(self.request(page_url).text)
full = text.extract_from(json.loads(extr('"full_image_text":', '});')))
data = {
"title" : text.unescape(extr('"og:title" content="', '"')),
"description": text.unescape(extr(':description" content="', '"')),
"date" : text.parse_datetime(extr(
'itemprop="datePublished" content="', '"')),
"rating" : extr('class="rated-', '"'),
"favorites" : text.parse_int(extr('id="faves_load">', '<')),
"score" : text.parse_float(extr('id="score_number">', '<')),
"tags" : text.split_html(extr(
'<dd class="tags momag">', '</dd>')),
"url" : full('src="', '"'),
"width" : text.parse_int(full('width="', '"')),
"height" : text.parse_int(full('height="', '"')),
}
data["tags"].sort()
data["index"] = text.parse_int(
data["url"].rpartition("/")[2].partition("_")[0])
return data
def _pagination(self, url):
headers = {
"Referer": self.root,
"X-Requested-With": "XMLHttpRequest",
"Accept": "application/json, text/javascript, */*; q=0.01",
}
while True:
data = self.request(url, headers=headers).json()
for year in data["sequence"]:
for item in data["years"][str(year)]["items"]:
page_url = text.extract(item, 'href="', '"')[0]
yield text.urljoin(self.root, page_url)
if not data["more"]:
return
url = text.urljoin(self.root, data["more"])
class NewgroundsUserExtractor(NewgroundsExtractor):
"""Extractor for all images of a newgrounds user"""
subcategory = "user"
pattern = r"(?:https?://)?([^.]+)\.newgrounds\.com(?:/art)?/?$"
test = (
("https://blitzwuff.newgrounds.com/art", {
"url": "24b19c4a135a09889fac7b46a74e427e4308d02b",
"keyword": "62981f7bdd66e1f1c72ab1d9b932423c156bc9a1",
}),
("https://blitzwuff.newgrounds.com/"),
)
def get_page_urls(self):
return self._pagination(self.root + "/art/page/1")
class NewgroundsImageExtractor(NewgroundsExtractor):
"""Extractor for a single image from newgrounds.com"""
subcategory = "image"
pattern = (r"(?:https?://)?(?:"
r"(?:www\.)?newgrounds\.com/art/view/([^/?&#]+)/[^/?&#]+"
r"|art\.ngfiles\.com/images/\d+/\d+_([^_]+)_([^.]+))")
test = (
("https://www.newgrounds.com/art/view/blitzwuff/ffx", {
"url": "e7778c4597a2fb74b46e5f04bb7fa1d80ca02818",
"keyword": "cbe90f8f32da4341938f59b08d70f76137028a7e",
"content": "cb067d6593598710292cdd340d350d14a26fe075",
}),
("https://art.ngfiles.com/images/587000/587551_blitzwuff_ffx.png", {
"url": "e7778c4597a2fb74b46e5f04bb7fa1d80ca02818",
"keyword": "cbe90f8f32da4341938f59b08d70f76137028a7e",
}),
)
def __init__(self, match):
NewgroundsExtractor.__init__(self, match)
if match.group(2):
self.user = match.group(2)
self.page_url = "https://www.newgrounds.com/art/view/{}/{}".format(
self.user, match.group(3))
else:
self.page_url = match.group(0)
def get_page_urls(self):
return (self.page_url,)
class NewgroundsVideoExtractor(NewgroundsExtractor):
"""Extractor for all videos of a newgrounds user"""
subcategory = "video"
filename_fmt = "{category}_{index}.{extension}"
pattern = r"(?:https?://)?([^.]+)\.newgrounds\.com/movies/?$"
test = ("https://tomfulp.newgrounds.com/movies", {
"pattern": r"ytdl:https?://www\.newgrounds\.com/portal/view/\d+",
"count": ">= 32",
})
def get_page_urls(self):
return self._pagination(self.root + "/movies/page/1")
def parse_page_data(self, page_url):
return {
"url" : "ytdl:" + page_url,
"index": text.parse_int(page_url.rpartition("/")[2]),
}
|
