[wikimedia] update

- rewrite using BaseExtractor
- support most Wiki* domains
- update docs/supportedsites
- add tests
This commit is contained in:
Mike Fährmann
2024-01-16 22:08:03 +01:00
parent 221f54309c
commit c3c1635ef3
12 changed files with 426 additions and 156 deletions

23
test/results/wikibooks.py Normal file
View File

@@ -0,0 +1,23 @@
# -*- 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 wikimedia
__tests__ = (
{
"#url" : "https://www.wikibooks.org/wiki/Title",
"#category": ("wikimedia", "wikibooks", "article"),
"#class" : wikimedia.WikimediaArticleExtractor,
},
{
"#url" : "https://en.wikibooks.org/wiki/Category:Title",
"#category": ("wikimedia", "wikibooks", "category"),
"#class" : wikimedia.WikimediaCategoryExtractor,
},
)

View File

@@ -0,0 +1,23 @@
# -*- 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 wikimedia
__tests__ = (
{
"#url" : "https://commons.wikimedia.org/wiki/File:Starr-050516-1367-Pimenta_dioica-flowers-Maunaloa-Molokai_(24762757525).jpg",
"#category": ("wikimedia", "wikimediacommons", "article"),
"#class" : wikimedia.WikimediaArticleExtractor,
},
{
"#url" : "https://commons.wikimedia.org/wiki/Category:Network_maps_of_the_Paris_Metro",
"#category": ("wikimedia", "wikimediacommons", "category"),
"#class" : wikimedia.WikimediaCategoryExtractor,
},
)

23
test/results/wikinews.py Normal file
View File

@@ -0,0 +1,23 @@
# -*- 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 wikimedia
__tests__ = (
{
"#url" : "https://www.wikinews.org/wiki/Title",
"#category": ("wikimedia", "wikinews", "article"),
"#class" : wikimedia.WikimediaArticleExtractor,
},
{
"#url" : "https://en.wikinews.org/wiki/Category:Title",
"#category": ("wikimedia", "wikinews", "category"),
"#class" : wikimedia.WikimediaCategoryExtractor,
},
)

53
test/results/wikipedia.py Normal file
View File

@@ -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 wikimedia
__tests__ = (
{
"#url" : "https://www.wikipedia.org/wiki/Title",
"#category": ("wikimedia", "wikipedia", "article"),
"#class" : wikimedia.WikimediaArticleExtractor,
},
{
"#url" : "https://en.wikipedia.org/wiki/Athena",
"#category": ("wikimedia", "wikipedia", "article"),
"#class" : wikimedia.WikimediaArticleExtractor,
"#pattern" : r"https://upload.wikimedia.org/wikipedia/.+",
"#count" : range(50, 100),
"bitdepth" : int,
"canonicaltitle": str,
"comment" : str,
"commonmetadata": dict,
"date" : "type:datetime",
"descriptionshorturl": str,
"descriptionurl": str,
"extension" : str,
"extmetadata" : dict,
"filename" : str,
"height" : int,
"metadata" : dict,
"mime" : r"re:image/\w+",
"page" : "Athena",
"sha1" : r"re:^[0-9a-f]{40}$",
"size" : int,
"timestamp" : str,
"url" : str,
"user" : str,
"userid" : int,
"width" : int,
},
{
"#url" : "https://en.wikipedia.org/wiki/Category:Physics",
"#category": ("wikimedia", "wikipedia", "category"),
"#class" : wikimedia.WikimediaCategoryExtractor,
},
)

23
test/results/wikiquote.py Normal file
View File

@@ -0,0 +1,23 @@
# -*- 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 wikimedia
__tests__ = (
{
"#url" : "https://www.wikiquote.org/wiki/Title",
"#category": ("wikimedia", "wikiquote", "article"),
"#class" : wikimedia.WikimediaArticleExtractor,
},
{
"#url" : "https://en.wikiquote.org/wiki/Category:Title",
"#category": ("wikimedia", "wikiquote", "category"),
"#class" : wikimedia.WikimediaCategoryExtractor,
},
)

View File

@@ -0,0 +1,23 @@
# -*- 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 wikimedia
__tests__ = (
{
"#url" : "https://www.wikisource.org/wiki/Title",
"#category": ("wikimedia", "wikisource", "article"),
"#class" : wikimedia.WikimediaArticleExtractor,
},
{
"#url" : "https://en.wikisource.org/wiki/Category:Title",
"#category": ("wikimedia", "wikisource", "category"),
"#class" : wikimedia.WikimediaCategoryExtractor,
},
)

View File

@@ -0,0 +1,25 @@
# -*- 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 wikimedia
__tests__ = (
{
"#url" : "https://species.wikimedia.org/wiki/Geranospiza",
"#category": ("wikimedia", "wikispecies", "article"),
"#class" : wikimedia.WikimediaArticleExtractor,
"#urls" : "https://upload.wikimedia.org/wikipedia/commons/0/01/Geranospiza_caerulescens.jpg",
"#sha1_content": "3a17c14b15489928e4154f826af1c42afb5a523e",
},
{
"#url" : "https://species.wikimedia.org/wiki/Category:Names",
"#category": ("wikimedia", "wikispecies", "category"),
"#class" : wikimedia.WikimediaCategoryExtractor,
},
)

View File

@@ -0,0 +1,23 @@
# -*- 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 wikimedia
__tests__ = (
{
"#url" : "https://www.wikiversity.org/wiki/Title",
"#category": ("wikimedia", "wikiversity", "article"),
"#class" : wikimedia.WikimediaArticleExtractor,
},
{
"#url" : "https://en.wikiversity.org/wiki/Category:Title",
"#category": ("wikimedia", "wikiversity", "category"),
"#class" : wikimedia.WikimediaCategoryExtractor,
},
)

View File

@@ -0,0 +1,23 @@
# -*- 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 wikimedia
__tests__ = (
{
"#url" : "https://www.wiktionary.org/wiki/Word",
"#category": ("wikimedia", "wiktionary", "article"),
"#class" : wikimedia.WikimediaArticleExtractor,
},
{
"#url" : "https://en.wiktionary.org/wiki/Category:Words",
"#category": ("wikimedia", "wiktionary", "category"),
"#class" : wikimedia.WikimediaCategoryExtractor,
},
)