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
|
# -*- coding: utf-8 -*-
# Copyright 2021-2023 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://www.erome.com/"""
from .common import Extractor, Message
from .. import text, util, exception
from ..cache import cache
import itertools
BASE_PATTERN = r"(?:https?://)?(?:www\.)?erome\.com"
class EromeExtractor(Extractor):
category = "erome"
directory_fmt = ("{category}", "{user}")
filename_fmt = "{album_id} {title} {num:>02}.{extension}"
archive_fmt = "{album_id}_{num}"
root = "https://www.erome.com"
def __init__(self, match):
Extractor.__init__(self, match)
self.item = match.group(1)
self.__cookies = True
def items(self):
for album_id in self.albums():
url = "{}/a/{}".format(self.root, album_id)
try:
page = self.request(url).text
except exception.HttpError as exc:
self.log.warning(
"Unable to fetch album '%s' (%s)", album_id, exc)
continue
title, pos = text.extract(
page, 'property="og:title" content="', '"')
pos = page.index('<div class="user-profile', pos)
user, pos = text.extract(
page, 'href="https://www.erome.com/', '"', pos)
tags, pos = text.extract(
page, '<p class="mt-10"', '</p>', pos)
urls = []
date = None
groups = page.split('<div class="media-group"')
for group in util.advance(groups, 1):
url = (text.extr(group, '<source src="', '"') or
text.extr(group, 'data-src="', '"'))
if url:
urls.append(url)
if not date:
ts = text.extr(group, '?v=', '"')
if len(ts) > 1:
date = text.parse_timestamp(ts)
data = {
"album_id": album_id,
"title" : text.unescape(title),
"user" : text.unquote(user),
"count" : len(urls),
"date" : date,
"tags" : [t.replace("+", " ")
for t in text.extract_iter(tags, "?q=", '"')],
"_http_headers": {"Referer": url},
}
yield Message.Directory, data
for data["num"], url in enumerate(urls, 1):
yield Message.Url, url, text.nameext_from_url(url, data)
def albums(self):
return ()
def request(self, url, **kwargs):
if self.__cookies:
self.__cookies = False
self.cookies.update(_cookie_cache())
for _ in range(5):
response = Extractor.request(self, url, **kwargs)
if response.cookies:
_cookie_cache.update("", response.cookies)
if response.content.find(
b"<title>Please wait a few moments</title>", 0, 600) < 0:
return response
self.sleep(5.0, "check")
def _pagination(self, url, params):
for params["page"] in itertools.count(1):
page = self.request(url, params=params).text
album_ids = EromeAlbumExtractor.pattern.findall(page)[::2]
yield from album_ids
if len(album_ids) < 36:
return
class EromeAlbumExtractor(EromeExtractor):
"""Extractor for albums on erome.com"""
subcategory = "album"
pattern = BASE_PATTERN + r"/a/(\w+)"
example = "https://www.erome.com/a/ID"
def albums(self):
return (self.item,)
class EromeUserExtractor(EromeExtractor):
subcategory = "user"
pattern = BASE_PATTERN + r"/(?!a/|search\?)([^/?#]+)"
example = "https://www.erome.com/USER"
def albums(self):
url = "{}/{}".format(self.root, self.item)
return self._pagination(url, {})
class EromeSearchExtractor(EromeExtractor):
subcategory = "search"
pattern = BASE_PATTERN + r"/search\?q=([^&#]+)"
example = "https://www.erome.com/search?q=QUERY"
def albums(self):
url = self.root + "/search"
params = {"q": text.unquote(self.item)}
return self._pagination(url, params)
@cache()
def _cookie_cache():
return ()
|
