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 2025 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://thehentaiworld.com/"""
from .common import Extractor, Message
from .. import text, util
import collections
BASE_PATTERN = r"(?:https?://)?(?:www\.)?thehentaiworld\.com"
class ThehentaiworldExtractor(Extractor):
"""Base class for thehentaiworld extractors"""
category = "thehentaiworld"
root = "https://thehentaiworld.com"
filename_fmt = "{title} ({id}{num:?-//}).{extension}"
archive_fmt = "{id}_{num}"
request_interval = (0.5, 1.5)
def items(self):
for url in self.posts():
try:
post = self._extract_post(url)
except Exception as exc:
self.status |= 1
self.log.warning("Failed to extract post %s (%s: %s)",
url, exc.__class__.__name__, exc)
continue
if "file_urls" in post:
urls = post["file_urls"]
post["count"] = len(urls)
yield Message.Directory, post
for post["num"], url in enumerate(urls, 1):
text.nameext_from_url(url, post)
yield Message.Url, url, post
else:
yield Message.Directory, post
url = post["file_url"]
text.nameext_from_url(url, post)
yield Message.Url, url, post
def _extract_post(self, url):
extr = text.extract_from(self.request(url).text)
post = {
"num" : 0,
"count" : 1,
"title" : text.unescape(extr("<title>", "<").strip()),
"id" : text.parse_int(extr(" postid-", " ")),
"slug" : extr(" post-", '"'),
"tags" : extr('id="tagsHead">', "</ul>"),
"date" : text.parse_datetime(extr(
"<li>Posted: ", "<"), "%Y-%m-%d"),
}
if "/videos/" in url:
post["type"] = "video"
post["width"] = post["height"] = 0
post["votes"] = text.parse_int(extr("(<strong>", "</strong>"))
post["score"] = text.parse_float(extr("<strong>", "<"))
post["file_url"] = extr('<source src="', '"')
else:
post["type"] = "image"
post["width"] = text.parse_int(extr("<li>Size: ", " "))
post["height"] = text.parse_int(extr("x ", "<"))
post["file_url"] = extr('a href="', '"')
post["votes"] = text.parse_int(extr("(<strong>", "</strong>"))
post["score"] = text.parse_float(extr("<strong>", "<"))
if doujin := extr('<a id="prev-page"', "</div></div><"):
repl = text.re(r"-220x\d+\.").sub
post["file_urls"] = [
repl(".", url)
for url in text.extract_iter(
doujin, 'class="border" src="', '"')
]
tags = collections.defaultdict(list)
pattern = text.re(r'<li><a class="([^"]*)" href="[^"]*">([^<]+)')
for tag_type, tag_name in pattern.findall(post["tags"]):
tags[tag_type].append(tag_name)
post["tags"] = tags_list = []
for key, value in tags.items():
tags_list.extend(value)
post[f"tags_{key}" if key else "tags_general"] = value
return post
def _pagination(self, endpoint):
base = f"{self.root}{endpoint}"
pnum = self.page_start
while True:
url = base if pnum < 2 else f"{base}page/{pnum}/"
page = self.request(url).text
yield from text.extract_iter(text.extr(
page, 'id="thumbContainer"', "<script"), ' href="', '"')
if 'class="next"' not in page:
return
pnum += 1
class ThehentaiworldPostExtractor(ThehentaiworldExtractor):
subcategory = "post"
pattern = (rf"{BASE_PATTERN}"
rf"(/(?:(?:3d-cgi-)?hentai-image|video)s/([^/?#]+))")
example = "https://thehentaiworld.com/hentai-images/SLUG/"
def posts(self):
return (f"{self.root}{self.groups[0]}/",)
class ThehentaiworldTagExtractor(ThehentaiworldExtractor):
subcategory = "tag"
per_page = 24
page_start = 1
post_start = 0
directory_fmt = ("{category}", "{search_tags}")
pattern = rf"{BASE_PATTERN}/tag/([^/?#]+)"
example = "https://thehentaiworld.com/tag/TAG/"
def posts(self):
self.kwdict["search_tags"] = tag = self.groups[0]
return util.advance(self._pagination(f"/tag/{tag}/"), self.post_start)
def skip(self, num):
pages, posts = divmod(num, self.per_page)
self.page_start += pages
self.post_start += posts
return num
|
