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
|
# -*- 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.
"""Extract images from http://www.bobx.com/dark/"""
from .common import Extractor, Message
from .. import text
from ..cache import memcache
import random
import time
class BobxExtractor(Extractor):
"""Base class for bobx extractors"""
category = "bobx"
root = "http://www.bobx.com"
cookiedomain = ".bobx.com"
per_page = 80
def __init__(self, match):
Extractor.__init__(self, match)
self.path = match.group(1)
def login(self):
if not self._check_cookies(("BobXUser",)):
self._update_cookies(self._login_impl())
@memcache()
def _login_impl(self):
"""Generate a randomized 'BobXUser' cookie"""
rand = random.randrange
tnow = time.time() - rand(60, 3600)
return {"BobXUser": "{}.{}.{}.{}.{}.{}".format(
int(tnow),
rand(128, 192), rand(0, 256), rand(0, 256), rand(0, 256),
tnow + 622080000, # timestamp in 7200 days
)}
class BobxGalleryExtractor(BobxExtractor):
"""Extractor for individual image galleries on bobx.com"""
subcategory = "gallery"
directory_fmt = ("{category}", "{model}", "{title}")
filename_fmt = "{model}_{image_id}_{num:>03}.{extension}"
archive_fmt = "{image_id}"
pattern = (r"(?:https?://)?(?:www\.)?bobx\.com"
r"/([^/]+/[^/]+/photoset/[\w-]+)-\d+-\d+-\d+\.html")
test = (
(("http://www.bobx.com/idol/mikoto-hibi"
"/photoset/wpb-2018-_11-0-2-8.html"), {
"url": "93972d6a661f6627e963d62c9d15531e6b36a389",
"keyword": "6c620862db494ed05e69356ba30e604b167b0670",
"content": "3f176b7fe752524cec21a763aa55567e41181e07",
}),
(("http://www.bobx.com/idol/nashiko-momotsuki"
"/photoset/wpb-net-_221---2018-08---magic-of-summer-0-10-10.html"), {
"url": "f5d6c0cd0881ae6f504c21a90d86e3464dc54e8e",
"keyword": "f4819c75f494044348889ecd27771508464c0f5f",
}),
)
def items(self):
self.login()
num = 0
while True:
url = "{}/{}-{}-10-8.html".format(self.root, self.path, num)
page = self.request(url, encoding="utf-8").text
if num == 0:
data = self.metadata(page)
yield Message.Version, 1
yield Message.Directory, data
data["num"] = 0
for url in self.images(page):
url = text.urljoin(self.root, url.replace("-preview-", "-"))
data = text.nameext_from_url(url, data)
data["image_id"] = text.parse_int(
data["filename"].rpartition("-")[2])
data["num"] += 1
yield Message.Url, url, data
num += self.per_page
if num >= data["count"]:
return
@staticmethod
def metadata(page):
"""Collect metadata for extractor-job"""
info = text.extract(page, "<title>", "</title>")[0]
model, _, info = info.partition(" in ")
info, _, count = info.rpartition(" of ")
title = info.rpartition(" - @")[0]
return {
"title": text.unquote(title),
"model": text.unquote(model),
"count": text.parse_int(count),
}
@staticmethod
def images(page):
"""Extract all image-urls"""
page = text.extract(page, "<table CELLPADDING=", "<script ")[0]
return text.extract_iter(page, '<img src="/thumbnail', '"')
class BobxIdolExtractor(BobxExtractor):
"""Extractor for an idol's image galleries on bobx.com"""
subcategory = "idol"
pattern = r"(?:https?://)?(?:www\.)?bobx\.com/([^/]+/[^/?&#]+)/?$"
test = ("http://www.bobx.com/idol/rin-okabe/", {
"pattern": BobxGalleryExtractor.pattern,
"count": ">= 6",
})
def items(self):
self.login()
url = "{}/{}/".format(self.root, self.path)
data = {"_extractor": BobxGalleryExtractor}
page = self.request(url).text
skip = True
yield Message.Version, 1
for part in text.extract_iter(page, '="photoset/', '"'):
# skip every other entry
skip = not skip
if not skip:
yield Message.Queue, "{}photoset/{}".format(url, part), data
|
