2015-05-04 20:40:53 +02:00
|
|
|
# -*- coding: utf-8 -*-
|
|
|
|
|
2016-03-06 21:07:00 +01:00
|
|
|
# Copyright 2015, 2016 Mike Fährmann
|
2015-05-04 20:40:53 +02:00
|
|
|
#
|
|
|
|
# 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 https://nijie.info/"""
|
|
|
|
|
2015-10-03 15:43:02 +02:00
|
|
|
from .common import AsynchronousExtractor, Message
|
2016-07-20 14:21:13 +02:00
|
|
|
from .. import config, text, exception
|
2016-03-06 21:07:00 +01:00
|
|
|
from ..cache import cache
|
2015-05-04 20:40:53 +02:00
|
|
|
|
2016-09-19 08:51:49 +02:00
|
|
|
class NijieExtractor(AsynchronousExtractor):
|
|
|
|
"""Base class for nijie extractors"""
|
2015-11-21 04:26:30 +01:00
|
|
|
category = "nijie"
|
|
|
|
directory_fmt = ["{category}", "{artist-id}"]
|
|
|
|
filename_fmt = "{category}_{artist-id}_{image-id}_p{index:>02}.{extension}"
|
2015-05-04 20:40:53 +02:00
|
|
|
popup_url = "https://nijie.info/view_popup.php?id="
|
|
|
|
|
2016-09-19 08:51:49 +02:00
|
|
|
def __init__(self):
|
2015-10-05 15:35:48 +02:00
|
|
|
AsynchronousExtractor.__init__(self)
|
2016-09-19 08:51:49 +02:00
|
|
|
self.session.headers["Referer"] = "https://nijie.info/"
|
|
|
|
self.artist_id = ""
|
2015-05-04 20:40:53 +02:00
|
|
|
|
|
|
|
def items(self):
|
2016-03-06 21:07:00 +01:00
|
|
|
self.session.cookies = self.login(
|
2016-07-24 22:22:49 +02:00
|
|
|
config.interpolate(("extractor", self.category, "username")),
|
2016-03-06 21:07:00 +01:00
|
|
|
config.interpolate(("extractor", self.category, "password"))
|
|
|
|
)
|
2015-05-04 20:40:53 +02:00
|
|
|
data = self.get_job_metadata()
|
2016-09-04 11:01:16 +02:00
|
|
|
images = self.get_image_ids()
|
2015-05-04 20:40:53 +02:00
|
|
|
yield Message.Version, 1
|
|
|
|
yield Message.Directory, data
|
2016-09-04 11:01:16 +02:00
|
|
|
for image_id in images:
|
2015-05-04 20:40:53 +02:00
|
|
|
for image_url, image_data in self.get_image_data(image_id):
|
|
|
|
image_data.update(data)
|
|
|
|
yield Message.Url, image_url, image_data
|
|
|
|
|
|
|
|
def get_job_metadata(self):
|
|
|
|
"""Collect metadata for extractor-job"""
|
2016-09-25 14:22:07 +02:00
|
|
|
return {"artist-id": self.artist_id}
|
2015-05-04 20:40:53 +02:00
|
|
|
|
|
|
|
def get_image_ids(self):
|
2015-10-03 15:43:02 +02:00
|
|
|
"""Collect all image-ids for a specific artist"""
|
2016-09-19 08:51:49 +02:00
|
|
|
return []
|
2015-05-04 20:40:53 +02:00
|
|
|
|
|
|
|
def get_image_data(self, image_id):
|
|
|
|
"""Get URL and metadata for images specified by 'image_id'"""
|
2015-10-05 15:35:48 +02:00
|
|
|
page = self.request(self.popup_url + image_id).text
|
2016-09-19 08:51:49 +02:00
|
|
|
return self.extract_image_data(page, image_id)
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
def extract_image_data(page, image_id):
|
|
|
|
"""Get URL and metadata for images from 'page'"""
|
2015-12-11 00:07:21 +01:00
|
|
|
images = list(text.extract_iter(page, '<img src="//pic', '"'))
|
|
|
|
for index, url in enumerate(images):
|
|
|
|
yield "https://pic" + url, text.nameext_from_url(url, {
|
|
|
|
"count": len(images),
|
2015-05-04 20:40:53 +02:00
|
|
|
"index": index,
|
|
|
|
"image-id": image_id,
|
2015-11-16 17:32:26 +01:00
|
|
|
})
|
2015-12-11 00:07:21 +01:00
|
|
|
|
2016-03-06 21:07:00 +01:00
|
|
|
@cache(maxage=30*24*60*60, keyarg=1)
|
2016-07-24 22:22:49 +02:00
|
|
|
def login(self, username, password):
|
2015-12-11 00:07:21 +01:00
|
|
|
"""Login and obtain session cookie"""
|
2016-07-24 22:22:49 +02:00
|
|
|
params = {"email": username, "password": password}
|
2016-09-19 08:51:49 +02:00
|
|
|
page = self.session.post("https://nijie.info/login_int.php",
|
|
|
|
data=params).text
|
2015-12-11 00:07:21 +01:00
|
|
|
if "//nijie.info/login.php" in page:
|
2016-07-20 14:21:13 +02:00
|
|
|
raise exception.AuthenticationError()
|
2016-03-06 21:07:00 +01:00
|
|
|
return self.session.cookies
|
2016-09-19 08:51:49 +02:00
|
|
|
|
|
|
|
|
|
|
|
class NijieUserExtractor(NijieExtractor):
|
|
|
|
"""Extractor for works of a nijie-user"""
|
|
|
|
subcategory = "user"
|
|
|
|
pattern = [(r"(?:https?://)?(?:www\.)?nijie\.info/"
|
|
|
|
r"members(?:_illust)?\.php\?id=(\d+)")]
|
2016-12-30 01:46:42 +01:00
|
|
|
test = [
|
|
|
|
("https://nijie.info/members_illust.php?id=44", {
|
|
|
|
"url": "585d821df4716b1098660a0be426d01db4b65f2a",
|
|
|
|
"keyword": "7a2dbf8fc0dfdb2af208ecdb8ec7f3186bdc31ab",
|
|
|
|
}),
|
|
|
|
("https://nijie.info/members_illust.php?id=43", {
|
|
|
|
"exception": exception.NotFoundError,
|
|
|
|
}),
|
|
|
|
]
|
2016-09-19 08:51:49 +02:00
|
|
|
|
|
|
|
def __init__(self, match):
|
|
|
|
NijieExtractor.__init__(self)
|
|
|
|
self.artist_id = match.group(1)
|
|
|
|
self.artist_url = ("https://nijie.info/members_illust.php?id="
|
|
|
|
+ self.artist_id)
|
|
|
|
|
|
|
|
def get_image_ids(self):
|
2016-12-30 01:46:42 +01:00
|
|
|
response = self.session.get(self.artist_url)
|
2016-09-19 08:51:49 +02:00
|
|
|
if response.status_code == 404:
|
|
|
|
raise exception.NotFoundError("artist")
|
|
|
|
return list(text.extract_iter(response.text, ' illust_id="', '"'))
|
|
|
|
|
|
|
|
|
|
|
|
class NijieImageExtractor(NijieExtractor):
|
|
|
|
"""Extractor for a work/image from nijie.info"""
|
|
|
|
subcategory = "image"
|
|
|
|
pattern = [r"(?:https?://)?(?:www\.)?nijie\.info/view\.php\?id=(\d+)"]
|
2016-12-30 01:46:42 +01:00
|
|
|
test = [
|
|
|
|
("https://nijie.info/view.php?id=70720", {
|
|
|
|
"url": "a10d4995645b5f260821e32c60a35f73546c2699",
|
|
|
|
"keyword": "e454c2bad9b636b90d569881bf4fe8438506e0d2",
|
|
|
|
"content": "d85e3ea896ed5e4da0bca2390ad310a4df716ca6",
|
|
|
|
}),
|
|
|
|
("https://nijie.info/view.php?id=70724", {
|
|
|
|
"exception": exception.NotFoundError,
|
|
|
|
}),
|
|
|
|
]
|
2016-09-19 08:51:49 +02:00
|
|
|
|
|
|
|
def __init__(self, match):
|
|
|
|
NijieExtractor.__init__(self)
|
|
|
|
self.image_id = match.group(1)
|
|
|
|
self.page = ""
|
|
|
|
|
|
|
|
def get_job_metadata(self):
|
|
|
|
response = self.session.get(self.popup_url + self.image_id,
|
|
|
|
allow_redirects=False)
|
|
|
|
if 300 <= response.status_code < 400:
|
|
|
|
raise exception.NotFoundError("image")
|
|
|
|
self.page = response.text
|
|
|
|
self.artist_id = text.extract(self.page, "/nijie_picture/sp/", "_")[0]
|
|
|
|
return NijieExtractor.get_job_metadata(self)
|
|
|
|
|
|
|
|
def get_image_ids(self):
|
|
|
|
return (self.image_id,)
|
|
|
|
|
|
|
|
def get_image_data(self, _):
|
|
|
|
return self.extract_image_data(self.page, self.image_id)
|