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
|
# -*- 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://fantia.jp/"""
from .common import Extractor, Message
from .. import text, util
class FantiaExtractor(Extractor):
"""Base class for Fantia extractors"""
category = "fantia"
root = "https://fantia.jp"
directory_fmt = ("{category}", "{fanclub_id}")
filename_fmt = "{post_id}_{file_id}.{extension}"
archive_fmt = "{post_id}_{file_id}"
_warning = True
def _init(self):
self.headers = {
"Accept" : "application/json, text/plain, */*",
"X-Requested-With": "XMLHttpRequest",
}
self._empty_plan = {
"id" : 0,
"price": 0,
"limit": 0,
"name" : "",
"description": "",
"thumb": self.root + "/images/fallback/plan/thumb_default.png",
}
if self._warning:
if not self.cookies_check(("_session_id",)):
self.log.warning("no '_session_id' cookie set")
FantiaExtractor._warning = False
def items(self):
for post_id in self.posts():
post = self._get_post_data(post_id)
post["num"] = 0
contents = self._get_post_contents(post)
post["content_count"] = len(contents)
post["content_num"] = 0
for content in contents:
files = self._process_content(post, content)
yield Message.Directory, post
if content["visible_status"] != "visible":
self.log.warning(
"Unable to download '%s' files from "
"%s#post-content-id-%s", content["visible_status"],
post["post_url"], content["id"])
for file in files:
post.update(file)
post["num"] += 1
text.nameext_from_url(
post["content_filename"] or file["file_url"], post)
yield Message.Url, file["file_url"], post
post["content_num"] += 1
def posts(self):
"""Return post IDs"""
def _pagination(self, url):
params = {"page": 1}
while True:
page = self.request(url, params=params).text
self._csrf_token(page)
post_id = None
for post_id in text.extract_iter(
page, 'class="link-block" href="/posts/', '"'):
yield post_id
if not post_id:
return
params["page"] += 1
def _csrf_token(self, page=None):
if not page:
page = self.request(self.root + "/").text
self.headers["X-CSRF-Token"] = text.extr(
page, 'name="csrf-token" content="', '"')
def _get_post_data(self, post_id):
"""Fetch and process post data"""
url = self.root+"/api/v1/posts/"+post_id
resp = self.request(url, headers=self.headers).json()["post"]
return {
"post_id": resp["id"],
"post_url": self.root + "/posts/" + str(resp["id"]),
"post_title": resp["title"],
"comment": resp["comment"],
"rating": resp["rating"],
"posted_at": resp["posted_at"],
"date": text.parse_datetime(
resp["posted_at"], "%a, %d %b %Y %H:%M:%S %z"),
"fanclub_id": resp["fanclub"]["id"],
"fanclub_user_id": resp["fanclub"]["user"]["id"],
"fanclub_user_name": resp["fanclub"]["user"]["name"],
"fanclub_name": resp["fanclub"]["name"],
"fanclub_url": self.root+"/fanclubs/"+str(resp["fanclub"]["id"]),
"tags": [t["name"] for t in resp["tags"]],
"_data": resp,
}
def _get_post_contents(self, post):
contents = post["_data"]["post_contents"]
try:
url = post["_data"]["thumb"]["original"]
except Exception:
pass
else:
contents.insert(0, {
"id": "thumb",
"title": "thumb",
"category": "thumb",
"download_uri": url,
"visible_status": "visible",
"plan": None,
})
return contents
def _process_content(self, post, content):
post["content_category"] = content["category"]
post["content_title"] = content["title"]
post["content_filename"] = content.get("filename") or ""
post["content_id"] = content["id"]
post["content_comment"] = content.get("comment") or ""
post["content_num"] += 1
post["plan"] = content["plan"] or self._empty_plan
files = []
if "post_content_photos" in content:
for photo in content["post_content_photos"]:
files.append({"file_id" : photo["id"],
"file_url": photo["url"]["original"]})
if "download_uri" in content:
url = content["download_uri"]
if url[0] == "/":
url = self.root + url
files.append({"file_id" : content["id"],
"file_url": url})
if content["category"] == "blog" and "comment" in content:
comment_json = util.json_loads(content["comment"])
blog_text = ""
for op in comment_json.get("ops") or ():
insert = op.get("insert")
if isinstance(insert, str):
blog_text += insert
elif isinstance(insert, dict) and "fantiaImage" in insert:
img = insert["fantiaImage"]
files.append({"file_id" : img["id"],
"file_url": self.root + img["original_url"]})
post["blogpost_text"] = blog_text
else:
post["blogpost_text"] = ""
return files
class FantiaCreatorExtractor(FantiaExtractor):
"""Extractor for a Fantia creator's works"""
subcategory = "creator"
pattern = r"(?:https?://)?(?:www\.)?fantia\.jp/fanclubs/(\d+)"
example = "https://fantia.jp/fanclubs/12345"
def __init__(self, match):
FantiaExtractor.__init__(self, match)
self.creator_id = match.group(1)
def posts(self):
url = "{}/fanclubs/{}/posts".format(self.root, self.creator_id)
return self._pagination(url)
class FantiaPostExtractor(FantiaExtractor):
"""Extractor for media from a single Fantia post"""
subcategory = "post"
pattern = r"(?:https?://)?(?:www\.)?fantia\.jp/posts/(\d+)"
example = "https://fantia.jp/posts/12345"
def __init__(self, match):
FantiaExtractor.__init__(self, match)
self.post_id = match.group(1)
def posts(self):
self._csrf_token()
return (self.post_id,)
|
