Mirrors/gallery-dl
1
0
Fork 0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-22 18:53:21 +01:00
Code Issues Releases Wiki Activity

[nijie] fix dojin extraction

Browse Source 
- correctly extract artist_id
- set extension to "jpg" if it was empty and let filetype checks do
  the rest
This commit is contained in:
Mike Fährmann 2018-02-09 21:51:35 +01:00
parent 7f7c16ae37
commit f5f2d29f56
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88
3 changed files with 21 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
gallery_dl/extractor/nijie.py
View File

@ -1,6 +1,6 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
# Copyright 2015-2017 Mike Fährmann # Copyright 2015-2018 Mike Fährmann
# #
# This program is free software; you can redistribute it and/or modify # 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 # it under the terms of the GNU General Public License version 2 as
@ -35,6 +35,8 @@ class NijieExtractor(AsynchronousExtractor):
for image_id in images: for image_id in images:
for image_url, image_data in self.get_image_data(image_id): for image_url, image_data in self.get_image_data(image_id):
image_data.update(data) image_data.update(data)
if not image_data["extension"]:
image_data["extension"] = "jpg"
yield Message.Url, image_url, image_data yield Message.Url, image_url, image_data
def get_job_metadata(self): def get_job_metadata(self):
@ -138,7 +140,9 @@ class NijieImageExtractor(NijieExtractor):
if 300 <= response.status_code < 400: if 300 <= response.status_code < 400:
raise exception.NotFoundError("image") raise exception.NotFoundError("image")
self.page = response.text self.page = response.text
self.artist_id = text.extract(self.page, "/nijie_picture/sp/", "_")[0] self.artist_id = text.extract(
self.page, "/nijie_picture/sp/", "_")[0] or text.extract(
self.page, "/dojin_main/", "_")[0]
return NijieExtractor.get_job_metadata(self) return NijieExtractor.get_job_metadata(self)
def get_image_ids(self): def get_image_ids(self):

16
gallery_dl/extractor/powermanga.py
View File

@ -1,6 +1,6 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
# Copyright 2015-2017 Mike Fährmann # Copyright 2015-2018 Mike Fährmann
# #
# This program is free software; you can redistribute it and/or modify # 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 # it under the terms of the GNU General Public License version 2 as
@ -26,6 +26,16 @@ class PowermangaMangaExtractor(foolslide.FoolslideMangaExtractor):
category = "powermanga" category = "powermanga"
pattern = foolslide.manga_pattern(r"read\.powermanga\.org") pattern = foolslide.manga_pattern(r"read\.powermanga\.org")
test = [("https://read.powermanga.org/series/one_piece/", { test = [("https://read.powermanga.org/series/one_piece/", {
"url": "e5e9a64c14ca51a170e14c4b711aaa88fdf7a7aa", "count": ">= 1",
"keyword": "1245ab2a730f9129001a4589b1d8615a17dc4a7b", "keyword": {
"chapter": int,
"chapter_minor": str,
"chapter_string": str,
"group": "PowerManga",
"lang": "en",
"language": "English",
"manga": "One Piece",
"title": str,
"volume": int,
},
})] })]

3
test/test_extractors.py
View File

@ -1,7 +1,7 @@
#!/usr/bin/env python3 #!/usr/bin/env python3
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
# Copyright 2015-2017 Mike Fährmann # Copyright 2015-2018 Mike Fährmann
# #
# This program is free software; you can redistribute it and/or modify # 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 # it under the terms of the GNU General Public License version 2 as
@ -20,6 +20,7 @@ SKIP = {
# temporary issues # temporary issues
"chronos", "chronos",
"coreimg", "coreimg",
"hosturimage",
"yeet", "yeet",
} }