merge #4682: [naver] support videos & fix recent 'date' bug (#7395)

2025-04-22 09:25:22 +02:00
parent abf39b60ef 4c974debf5
commit 25c2c3a7da
4 changed files with 119 additions and 6 deletions
--- a/docs/configuration.rst
+++ b/docs/configuration.rst
@@ -3437,6 +3437,16 @@ Description
    Note: Not supported by all ``moebooru`` instances.


+extractor.naver.videos
+----------------------
+Type
+    ``bool``
+Default
+    ``true``
+Description
+    Download videos.
+
+
 extractor.newgrounds.flash
 --------------------------
 Type
--- a/docs/gallery-dl.conf
+++ b/docs/gallery-dl.conf
@@ -420,6 +420,10 @@
            "username": "",
            "password": ""
        },
+        "naver":
+        {
+            "videos": true
+        },
        "newgrounds":
        {
            "username": "",
--- a/gallery_dl/extractor/naver.py
+++ b/gallery_dl/extractor/naver.py
@@ -9,7 +9,9 @@
 """Extractors for https://blog.naver.com/"""

 from .common import GalleryExtractor, Extractor, Message
-from .. import text
+from .. import text, util
+import datetime
+import time


 class NaverBase():
@@ -59,19 +61,66 @@ class NaverPostExtractor(NaverBase, GalleryExtractor):
                "user"       : extr("var nickName = '", "'"),
            },
        }
-        data["post"]["date"] = text.parse_datetime(
+
+        data["post"]["date"] = self._parse_datetime(
            extr('se_publishDate pcol2">', '<') or
-            extr('_postAddDate">', '<'), "%Y. %m. %d. %H:%M")
+            extr('_postAddDate">', '<'))
+
        return data

+    def _parse_datetime(self, date_string):
+        if "전" in date_string:
+            ts = time.gmtime()
+            return datetime.datetime(ts.tm_year, ts.tm_mon, ts.tm_mday)
+        return text.parse_datetime(date_string, "%Y. %m. %d. %H:%M")
+
    def images(self, page):
-        results = []
+        files = []
+        self._extract_images(files, page)
+        if self.config("videos", True):
+            self._extract_videos(files, page)
+        return files
+
+    def _extract_images(self, files, page):
        for url in text.extract_iter(page, 'data-lazy-src="', '"'):
            url = url.replace("://post", "://blog", 1).partition("?")[0]
            if "\ufffd" in text.unquote(url):
                url = text.unquote(url, encoding="EUC-KR")
-            results.append((url, None))
-        return results
+            files.append((url, None))
+
+    def _extract_videos(self, files, page):
+        for module in text.extract_iter(page, " data-module='", "'></"):
+            if '"v2_video"' not in module:
+                continue
+            media = util.json_loads(module)["data"]
+            try:
+                self._extract_media(files, media)
+            except Exception as exc:
+                self.log.warning("%s: Failed to extract video '%s' (%s: %s)",
+                                 self.post_id, media.get("vid"),
+                                 exc.__class__.__name__, exc)
+
+    def _extract_media(self, files, media):
+        url = ("https://apis.naver.com/rmcnmv/rmcnmv/vod/play/v2.0/" +
+               media["vid"])
+        params = {
+            "key"  : media["inkey"],
+            "sid"  : "2",
+            #  "pid": "00000000-0000-0000-0000-000000000000",
+            "nonce": int(time.time()),
+            "devt" : "html5_pc",
+            "prv"  : "N",
+            "aup"  : "N",
+            "stpb" : "N",
+            "cpl"  : "ko_KR",
+            "providerEnv": "real",
+            "adt"  : "glad",
+            "lc"   : "ko_KR",
+        }
+        data = self.request(url, params=params).json()
+        video = max(data["videos"]["list"],
+                    key=lambda v: v.get("size") or 0)
+        files.append((video["source"], video))


 class NaverBlogExtractor(NaverBase, Extractor):
--- a/test/results/naver.py
+++ b/test/results/naver.py
@@ -51,6 +51,56 @@ __tests__ = (
    "extension": "png",
 },

+{
+    "#url"     : "https://blog.naver.com/jws790103/223239681955",
+    "#comment" : "videos",
+    "#category": ("", "naver", "post"),
+    "#class"   : naver.NaverPostExtractor,
+    "#pattern" : (
+        r"https://blogfiles.pstatic.net/MjAyMzA5MjVfMTMy/MDAxNjk1NjQ0MzI4OTE3.UxgvxTesk7Y88OWGvPMwQhbmCPp6mPA_C-5l5lJggyEg.B0DbxNEzz3DxRJtShiiBHDLzLQSCFDo_Bp6c-bcMDiog.JPEG.jws790103/20230925%EF%BC%BF080218.jpg",
+        r"https://blogfiles.pstatic.net/MjAyMzA5MjVfMjAz/MDAxNjk1NjQ0MzI4OTA5.Kd4VzqHhhrgby7rCA1iPdBX6f_k2DPEBnlRdOWD-kPgg.U0C1lmlKVMZMA4hhhs69nolZwCZ4Plme4KVbNfhezhkg.JPEG.jws790103/20230925%EF%BC%BF081103.jpg",
+        r"https://blogfiles.pstatic.net/MjAyMzA5MjVfMTg3/MDAxNjk1NjQ0MzI4OTk2.faiqny7Fl82Nnc3cJj85xa_MSBjYR3BStKeHw2bjYTwg.7Z8w0lDO9Uhjr8QTGwA0az_UZhN9haHocbYWgEyBO9gg.JPEG.jws790103/20230925%EF%BC%BF081141.jpg",
+        r"https://blogfiles.pstatic.net/MjAyMzA5MjVfMTIz/MDAxNjk1NjQ0MzI4OTIz.xkrCwJuYVtQID9td3XdEz8JHHrdN5UZzfOJ6nb1rW4Mg.d1FfbB8GONEej23X9Uc9uAP_oBwWnTbb9aFaBCrkfQEg.JPEG.jws790103/20230925%EF%BC%BF100506.jpg",
+        r"https://blogfiles.pstatic.net/MjAyMzA5MjVfMjI4/MDAxNjk1NjQ0MzI5Njg4.BHqs4eTTqOFfvYx7oZBCdeYXkQOkTFiTb8kWdC4JLeYg.8ytEDpmgyn79au0g1vGJhVxRPRVlKLF0gwQe4L0egFIg.JPEG.jws790103/20230925%EF%BC%BF100548.jpg",
+        r"https://a01-g-naver-vod.akamaized.net/blog/a/read/v2/VOD_ALPHA/blog_2023_10_18_2486/base_pathfinder_pf3448100_81cd756f-6cff-11ee-b67f-80615f0c46d6.mp4\?__gda__=\d+_\w+&in_out_flag=1",
+        r"https://a01-g-naver-vod.akamaized.net/blog/a/read/v2/VOD_ALPHA/blog_2023_10_18_162/base_pathfinder_pf3448100_810b0fc9-6cff-11ee-8895-a0369ffde1ec.mp4\?__gda__=\d+_\w+&in_out_flag=1",
+    ),
+
+    "blog": {
+        "id"  : "jws790103",
+        "num" : 25591202,
+        "user": "fm컴퍼니 짱",
+    },
+    "post": {
+        "date"       : "dt:2023-10-18 06:50:00",
+        "description": "체육행사 기획행사는 fm컴퍼니에서 함께 하겠습니다. 어린이집 연합회 마라톤 대회에 무대렌탈 장비를 대여...",
+        "num"        : 223239681955,
+        "title"      : "마라톤대회 무대설치 기획행사 무대설치 체육행사 무대설치완료 fm컴퍼니에서 함께 하였습니다.",
+    },
+    "extension": {"jpg", "mp4"},
+    "count"    : 7,
+    "num"      : range(1, 7),
+},
+
+{
+    "#url"     : "https://blog.naver.com/jws790103/223239681955",
+    "#comment" : "'videos' option",
+    "#category": ("", "naver", "post"),
+    "#class"   : naver.NaverPostExtractor,
+    "#options" : {"videos": False},
+    "#urls": (
+        "https://blogfiles.pstatic.net/MjAyMzA5MjVfMTMy/MDAxNjk1NjQ0MzI4OTE3.UxgvxTesk7Y88OWGvPMwQhbmCPp6mPA_C-5l5lJggyEg.B0DbxNEzz3DxRJtShiiBHDLzLQSCFDo_Bp6c-bcMDiog.JPEG.jws790103/20230925%EF%BC%BF080218.jpg",
+        "https://blogfiles.pstatic.net/MjAyMzA5MjVfMjAz/MDAxNjk1NjQ0MzI4OTA5.Kd4VzqHhhrgby7rCA1iPdBX6f_k2DPEBnlRdOWD-kPgg.U0C1lmlKVMZMA4hhhs69nolZwCZ4Plme4KVbNfhezhkg.JPEG.jws790103/20230925%EF%BC%BF081103.jpg",
+        "https://blogfiles.pstatic.net/MjAyMzA5MjVfMTg3/MDAxNjk1NjQ0MzI4OTk2.faiqny7Fl82Nnc3cJj85xa_MSBjYR3BStKeHw2bjYTwg.7Z8w0lDO9Uhjr8QTGwA0az_UZhN9haHocbYWgEyBO9gg.JPEG.jws790103/20230925%EF%BC%BF081141.jpg",
+        "https://blogfiles.pstatic.net/MjAyMzA5MjVfMTIz/MDAxNjk1NjQ0MzI4OTIz.xkrCwJuYVtQID9td3XdEz8JHHrdN5UZzfOJ6nb1rW4Mg.d1FfbB8GONEej23X9Uc9uAP_oBwWnTbb9aFaBCrkfQEg.JPEG.jws790103/20230925%EF%BC%BF100506.jpg",
+        "https://blogfiles.pstatic.net/MjAyMzA5MjVfMjI4/MDAxNjk1NjQ0MzI5Njg4.BHqs4eTTqOFfvYx7oZBCdeYXkQOkTFiTb8kWdC4JLeYg.8ytEDpmgyn79au0g1vGJhVxRPRVlKLF0gwQe4L0egFIg.JPEG.jws790103/20230925%EF%BC%BF100548.jpg",
+    ),
+
+    "extension": "jpg",
+    "count"    : 5,
+    "num"      : range(1, 5),
+},
+
 {
    "#url"     : "https://blog.naver.com/PostView.naver?blogId=rlfqjxm0&logNo=221430673006",
    "#category": ("", "naver", "post"),