[naverpost] add 'post' and 'user' extractors

docs/supportedsites.md

@@ -559,6 +559,12 @@ Consider all sites to be NSFW unless otherwise known.
     <td>Blogs, Posts</td>
     <td></td>
 </tr>
+<tr>
+    <td>NaverPost</td>
+    <td>https://post.naver.com/</td>
+    <td>Posts, User Profiles</td>
+    <td></td>
+</tr>
 <tr>
     <td>NaverWebtoon</td>
     <td>https://comic.naver.com/</td>

gallery_dl/extractor/__init__.py

@@ -100,6 +100,7 @@ modules = [
     "myhentaigallery",
     "myportfolio",
     "naver",
+    "naverpost",
     "naverwebtoon",
     "newgrounds",
     "nhentai",

gallery_dl/extractor/naverpost.py

@@ -0,0 +1,143 @@
+# -*- 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://post.naver.com/"""
+
+from .common import Extractor, Message
+from .. import text, exception
+import json
+import re
+
+BASE_PATTERN = r"(?:https?://)?(?:m\.)?post\.naver\.com"
+
+
+class NaverpostExtractor(Extractor):
+    """Base class for naver post extractors"""
+    category = "naverpost"
+    root = "https://post.naver.com"
+    request_interval = (0.5, 1.5)
+
+    def _call(self, url, params=None):
+        if params is None:
+            params = {}
+        while True:
+            try:
+                return self.request(url, params=params)
+            except exception.HttpError as exc:
+                if exc.status == 401:
+                    raise exception.AuthenticationError()
+                if exc.status == 403:
+                    raise exception.AuthorizationError()
+                if exc.status == 404:
+                    raise exception.NotFoundError(self.subcategory)
+                self.log.debug(exc)
+                return
+
+    def _pagination(self, url, params=None):
+        if params is None:
+            params = {}
+        while True:
+            res = self._call(url, params).text
+            # the `html` string in the response contains escaped single quotes,
+            # which would throw a JSONDecodeError exception
+            res = json.loads(res.replace(r"\'", "'"))
+            urls = []
+            endpoints = text.extract_iter(
+                res["html"], '<div class="text_area">\n<a href="', '"')
+            for endpoint in endpoints:
+                urls.append(self.root + endpoint)
+            yield from urls
+            if "nextFromNo" not in res:
+                return
+            params["fromNo"] = res["nextFromNo"]
+
+
+class NaverpostPostExtractor(NaverpostExtractor):
+    """Extractor for posts on post.naver.com"""
+    subcategory = "post"
+    filename_fmt = "{image[id]}.{extension}"
+    directory_fmt = ("{category}", "{author}", "{volume_no}")
+    archive_fmt = "{image[id]}"
+    pattern = (BASE_PATTERN + r"/viewer/postView\.(naver|nhn)"
+               r"\?volumeNo=(\d+)(?:&.+)?")
+    example = "https://post.naver.com/viewer/postView.naver?volumeNo=12345"
+
+    def __init__(self, match):
+        NaverpostExtractor.__init__(self, match)
+        self.url = match.group(0)
+        self.page_ext = match.group(1)
+        self.volume_no = match.group(2)
+
+    def metadata(self, page):
+        data = {
+            "title": text.unescape(
+                text.extr(page, '"og:title" content="', '"')),
+            "description": text.unescape(
+                text.extr(page, '"og:description" content="', '"')),
+            "author": text.extr(page, '"og:author" content="', '"'),
+            "date": text.parse_datetime(
+                text.extr(page, '"og:createdate" content="', '"'),
+                format="%Y.%m.%d. %H:%M:%S", utcoffset=9),
+            "volume_no": self.volume_no,
+            "views": text.parse_int(
+                (text.extr(page, '<span class="post_view">', ' ') or
+                 text.extr(page, '<span class="se_view" style="">', ' ')
+                 ).replace(",", "")),
+            "url": self.url,
+        }
+        return data
+
+    def items(self):
+        page = self._call(self.url).text
+        data = self.metadata(page)
+
+        yield Message.Directory, data
+
+        image_classes = ("img_attachedfile", "se_mediaImage")
+        image_query = r"\?type=w\d+$"
+        for image in text.extract_iter(page, "<img", ">"):
+            img = {
+                "id": text.extr(image, ' id="', '"'),
+                "title": text.extr(image, ' title="', '"'),
+                "attachment-id": text.extr(
+                    image, ' data-attachment-id="', '"'),
+                "alt": None,
+            }
+            classes = text.extr(image, ' class="', '"').split()
+            if not any(item in classes for item in image_classes):
+                continue
+            url = text.extr(image, ' data-src="', '"')
+            if not re.search(image_query, url):
+                continue
+            url = re.sub(image_query, "", url)
+            img["url"] = url
+            alt = text.extr(image, ' alt="', '"')
+            if alt and alt.endswith(".jpg"):
+                img["alt"] = alt
+                data["filename"], _, data["extension"] = alt.rpartition(".")
+            else:
+                text.nameext_from_url(text.unquote(url), data)
+            data["image"] = img
+            yield Message.Url, url, data
+
+
+class NaverpostUserExtractor(NaverpostExtractor):
+    """Extractor for all posts from a user on post.naver.com"""
+    subcategory = "user"
+    pattern = BASE_PATTERN + r"/my\.naver\?memberNo=(\d+)"
+    example = "https://post.naver.com/my.naver?memberNo=12345"
+
+    def __init__(self, match):
+        NaverpostExtractor.__init__(self, match)
+        self.member_no = match.group(1)
+
+    def items(self):
+        data = {"_extractor": NaverpostPostExtractor}
+        endpoint = self.root + "/async/my.naver"
+        params = {"memberNo": self.member_no}
+        posts = self._pagination(endpoint, params)
+        for url in posts:
+            yield Message.Queue, url, data

scripts/supportedsites.py

@@ -89,6 +89,7 @@ CATEGORY_MAP = {
     "mastodon.social": "mastodon.social",
     "myhentaigallery": "My Hentai Gallery",
     "myportfolio"    : "Adobe Portfolio",
+    "naverpost"      : "NaverPost",
     "naverwebtoon"   : "NaverWebtoon",
     "nhentai"        : "nhentai",
     "nijie"          : "nijie",

test/results/naverpost.py

@@ -0,0 +1,53 @@
+# -*- 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.
+
+from gallery_dl.extractor import naverpost
+
+IMAGE_URL_PATTERN = r"(?i)https://post-phinf\.pstatic\.net/.*\.(?:gif|jpe?g|png|webp)"
+
+
+__tests__ = (
+{
+    "#url": "https://m.post.naver.com/viewer/postView.nhn?volumeNo=15861102&memberNo=16220685",
+    "#comment": ".nhn page extension",
+    "#category": ("", "naverpost", "post"),
+    "#class": naverpost.NaverpostPostExtractor,
+    "#pattern": IMAGE_URL_PATTERN,
+    "#count": 34,
+
+    "title": "[쇼! 음악중심] 180526 방탄소년단 FAKE LOVE 현장 포토",
+    "description": "[BY MBC예능연구소] [쇼! 음악중심] 589회, 20180526 ※본 콘텐츠는 상업적 용도의 사용을 금합니다.",
+    "author": "MBC예능연구소",
+    "date": "dt:2018-05-29 12:09:34",
+    "views": int,
+},
+
+{
+    "#url": "https://post.naver.com/viewer/postView.naver?volumeNo=31389956&memberNo=29156514",
+    "#comment": ".naver page extension",
+    "#category": ("", "naverpost", "post"),
+    "#class": naverpost.NaverpostPostExtractor,
+    "#pattern": IMAGE_URL_PATTERN,
+    "#count": 48,
+
+    "title": "매일 밤 꿈꿔 왔던 드림캐쳐 '바람아' 활동 비하인드 현장",
+    "description": "[BY 드림캐쳐컴퍼니] 안녕하세요.드림캐쳐 포스트 지기입니다!(*･▽･*)'Odd Eye' 활동이 끝나고 아쉬웠을...",
+    "author": "드림캐쳐컴퍼니",
+    "date": "dt:2021-05-03 06:00:09",
+    "views": int,
+},
+
+{
+    "#url": "https://post.naver.com/my.naver?memberNo=29156514",
+    "#comment": "up to 20 posts are returned per request",
+    "#category": ("", "naverpost", "user"),
+    "#class": naverpost.NaverpostUserExtractor,
+    "#pattern": naverpost.NaverpostPostExtractor.pattern,
+    "#range": "1-21",
+    "#count": 21,
+},
+
+)