github/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[naver] adjust directory names and metadata structure

Browse Source
This commit is contained in:
Mike Fährmann
2019-10-31 16:42:26 +01:00
parent 702f2fbd1f
commit e877ca97c3
1 changed files with 20 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
gallery_dl/extractor/naver.py
View File

@@ -22,19 +22,20 @@ class NaverPostExtractor(NaverBase, GalleryExtractor):
"""Extractor for blog posts on blog.naver.com""" """Extractor for blog posts on blog.naver.com"""
subcategory = "post" subcategory = "post"
filename_fmt = "{num:>03}.{extension}" filename_fmt = "{num:>03}.{extension}"
directory_fmt = ("{category}", "{blog_id} {user}", "{post_num} {title}") directory_fmt = ("{category}", "{blog[user]} {blog[id]}",
archive_fmt = "{blog_id}_{post_num}_{num}" "{post[date]:%Y-%m-%d} {post[title]}")
archive_fmt = "{blog[id]}_{post[num]}_{num}"
pattern = (r"(?:https?://)?blog\.naver\.com/" pattern = (r"(?:https?://)?blog\.naver\.com/"
r"(?:PostView\.nhn\?blogId=(\w+)&logNo=(\d+)|(\w+)/(\d+)/?$)") r"(?:PostView\.nhn\?blogId=(\w+)&logNo=(\d+)|(\w+)/(\d+)/?$)")
test = ( test = (
("https://blog.naver.com/rlfqjxm0/221430673006", { ("https://blog.naver.com/rlfqjxm0/221430673006", {
"url": "6c694f3aced075ed5e9511f1e796d14cb26619cc", "url": "6c694f3aced075ed5e9511f1e796d14cb26619cc",
"keyword": "f0cc292cb29da5692217fae75aa6384763ebe72c", "keyword": "a6e23d19afbee86b37d6e7ad934650c379d2cb1e",
}), }),
(("https://blog.naver.com/PostView.nhn" (("https://blog.naver.com/PostView.nhn"
"?blogId=rlfqjxm0&logNo=221430673006"), { "?blogId=rlfqjxm0&logNo=221430673006"), {
"url": "6c694f3aced075ed5e9511f1e796d14cb26619cc", "url": "6c694f3aced075ed5e9511f1e796d14cb26619cc",
"keyword": "f0cc292cb29da5692217fae75aa6384763ebe72c", "keyword": "a6e23d19afbee86b37d6e7ad934650c379d2cb1e",
}), }),
) )
@@ -53,17 +54,22 @@ class NaverPostExtractor(NaverBase, GalleryExtractor):
def metadata(self, page): def metadata(self, page):
extr = text.extract_from(page) extr = text.extract_from(page)
return { data = {
"title" : extr('"og:title" content="', '"'), "post": {
"description": extr('"og:description" content="', '"'), "title" : extr('"og:title" content="', '"'),
"post_num" : text.parse_int(self.post_id), "description": extr('"og:description" content="', '"'),
"blog_num" : text.parse_int(extr("var blogNo = '", "'")), "num" : text.parse_int(self.post_id),
"blog_id" : self.blog_id, },
"user" : extr("var nickName = '", "'"), "blog": {
"date" : text.parse_datetime( "id" : self.blog_id,
extr('se_publishDate pcol2">', '<') or "num" : text.parse_int(extr("var blogNo = '", "'")),
extr('_postAddDate">', '<'), "%Y. %m. %d. %H:%M"), "user" : extr("var nickName = '", "'"),
},
} }
data["post"]["date"] = text.parse_datetime(
extr('se_publishDate pcol2">', '<') or
extr('_postAddDate">', '<'), "%Y. %m. %d. %H:%M")
return data
def images(self, page): def images(self, page):
return [ return [