Merge branch 'config'

config

@@ -1,18 +0,0 @@
-[pixiv]
-username = XXXXX
-password = XXXXX
-
-[exhentai-cookies]
-ipb_member_id = XXXXX
-ipb_pass_hash = XXXXX
-
-[nijie-cookies]
-NIJIEIJIEID = XXXXX
-nijie_email_hash = XXXXX
-nijie_login_hash = XXXXX
-
-[danbooru]
-regex0 = d(?:anbooru)?[.:-_](\w.+)
-
-[gelbooru]
-regex0 = g(?:elbooru)?[.:-_](\w.+)

config.json

@@ -0,0 +1,39 @@
+{
+    "base-directory": "/tmp/",
+    "extractor":
+    {
+        "pixiv":
+        {
+            "directory": ["{category}", "{artist-id}"],
+            "username": "XXX",
+            "password": "XXX"
+        },
+        "nijie":
+        {
+            "cookies":
+            {
+                "NIJIEIJIEID": "XXX",
+                "nijie_email_hash": "XXX",
+                "nijie_login_hash": "XXX"
+            }
+        },
+        "4chan":
+        {
+            "directory": ["{category}", "{board}", "{thread} - {title}"]
+        },
+        "danbooru":
+        {
+            "pattern": ["d(?:anbooru)?[.:-_](\\w.+)"],
+            "filename": "{category}_{id:>07}_{md5}.{extension}"
+        },
+        "gelbooru":
+        {
+            "pattern": ["g(?:elbooru)?[.:-_](\\w.+)"],
+            "filename": "{category}_{id:>07}_{md5}.{extension}"
+        },
+        "e621":
+        {
+            "pattern": ["e(?:621)?[.:-_](\\w.+)"]
+        }
+    }
+}

gallery_dl/__init__.py

@@ -17,9 +17,7 @@ __email__      = "mike_faehrmann@web.de"
 import os
 import sys
 import argparse
-import configparser
-
-from .download import DownloadManager
+from . import config, download
 
 def parse_cmdline_options():
     parser = argparse.ArgumentParser(
@@ -41,18 +39,10 @@ def parse_cmdline_options():
     )
     return parser.parse_args()
 
-def parse_config_file(path):
-    config = configparser.ConfigParser(
-        interpolation=None,
-    )
-    config.optionxform = lambda opt: opt
-    config.read(os.path.expanduser(path))
-    return config
-
 def main():
+    config.load()
     opts = parse_cmdline_options()
-    conf = parse_config_file(opts.config)
-    dlmgr = DownloadManager(opts, conf)
+    dlmgr = download.DownloadManager(opts)
 
     try:
         for url in opts.urls:

gallery_dl/config.py

@@ -0,0 +1,88 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2015 Mike Fährmann
+#
+# 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.
+
+"""Global configuration module"""
+
+import sys
+import json
+import os.path
+import platform
+
+# --------------------------------------------------------------------
+# public interface
+
+def load(*files):
+    """Load JSON configuration files"""
+    configfiles = files or _default_configs
+    for conf in configfiles:
+        try:
+            path = os.path.expanduser(conf)
+            with open(path) as file:
+                confdict = json.load(file)
+            _config.update(confdict)
+        except FileNotFoundError:
+            continue
+        except json.decoder.JSONDecodeError as exception:
+            print("Error while loading '", path, "':", sep="", file=sys.stderr)
+            print(exception, file=sys.stderr)
+
+def clear():
+    """Reset configuration to en empty state"""
+    globals()["_config"] = {}
+
+def get(keys, default=None):
+    """Get the value of property 'key' or a default-value if it doenst exist"""
+    conf = _config
+    try:
+        for k in keys:
+            conf = conf[k]
+        return conf
+    except (KeyError, AttributeError):
+        return default
+
+def interpolate(keys, default=None):
+    """Interpolate the value of 'key'"""
+    conf = _config
+    try:
+        for k in keys:
+            default = conf.get(keys[-1], default)
+            conf = conf[k]
+        return conf
+    except (KeyError, AttributeError):
+        return default
+
+def set(keys, value):
+    """Set the value of property 'key' for this session"""
+    conf = _config
+    for k in keys[:-1]:
+        try:
+            conf = conf[k]
+        except KeyError:
+            temp = {}
+            conf[k] = temp
+            conf = temp
+    conf[keys[-1]] = value
+
+
+# --------------------------------------------------------------------
+# internals
+
+_config = {}
+
+if platform.system() == "Windows":
+    _default_configs = [
+        r"~\.config\gallery-dl.conf",
+        r"~\.gallery-dl.conf",
+    ]
+else:
+    _default_configs = [
+        "/etc/gallery-dl.conf",
+        "~/.config/gallery/config.json",
+        "~/.config/gallery-dl.conf",
+        "~/.gallery-dl.conf",
+    ]

gallery_dl/download.py

@@ -12,14 +12,14 @@ import re
 import importlib
 
 from .extractor.common import Message
+from . import config
 
 class DownloadManager():
 
-    def __init__(self, opts, config):
+    def __init__(self, opts):
         self.opts = opts
-        self.config = config
         self.modules = {}
-        self.extractors = ExtractorFinder(config)
+        self.extractors = ExtractorFinder()
 
     def add(self, url):
         job = DownloadJob(self, url)
@@ -38,7 +38,7 @@ class DownloadManager():
         if self.opts.dest:
             return self.opts.dest
         else:
-            return self.config.get("general", "destination", fallback="/tmp/")
+            return config.get(("base-directory",), default="/tmp/")
 
 
 class DownloadJob():
@@ -50,16 +50,14 @@ class DownloadJob():
             return
         self.directory = mngr.get_base_directory()
         self.downloaders = {}
-        self.filename_fmt = mngr.config.get(
-            self.info["category"], "filename",
-            fallback=self.info["filename"]
+        self.filename_fmt = config.get(
+            ("extractor", self.info["category"], "filename"),
+            default=self.info["filename"]
+        )
+        segments = config.get(
+            ("extractor", self.info["category"], "directory"),
+            default=self.info["directory"]
         )
-        try:
-            segments = mngr.config.get(
-                self.info["category"], "directory"
-            ).split("/")
-        except Exception:
-            segments = self.info["directory"]
         self.directory_fmt = os.path.join(*segments)
 
     def run(self):
@@ -114,13 +112,11 @@ class DownloadJob():
         scheme = url[:pos] if pos != -1 else "http"
         if scheme == "https":
             scheme = "http"
-
         downloader = self.downloaders.get(scheme)
         if downloader is None:
             module = self.mngr.get_downloader_module(scheme)
             downloader = module.Downloader()
             self.downloaders[scheme] = downloader
-
         return downloader
 
     @staticmethod
@@ -144,26 +140,23 @@ class DownloadJob():
 
 class ExtractorFinder():
 
-    def __init__(self, config):
-        self.config = config
-
     def get_for_url(self, url):
         """Get an extractor-instance suitable for 'url'"""
         name, match = self.find_pattern_match(url)
         if match:
             module = importlib.import_module(".extractor." + name, __package__)
             klass = getattr(module, module.info["extractor"])
-            return klass(match, self.config), module.info
+            return klass(match), module.info
         else:
             print("no suitable extractor found")
             return None, None
 
     def find_pattern_match(self, url):
-        """Find a pattern, that matches 'url', and return the (category,match) tuple"""
-        for category in self.config:
-            for key, value in self.config[category].items():
-                if key.startswith("regex"):
-                    match = re.match(value, url)
+        """Find a pattern that matches 'url' and return the (category,match) tuple"""
+        for category in config.get(("extractor",)):
+            patterns = config.get(("extractor", category, "pattern"), default=[])
+            for pattern in patterns:
+                match = re.match(pattern, url)
                 if match:
                     return category, match
         for category, info in self.extractor_metadata():

gallery_dl/extractor/3dbooru.py

@@ -22,8 +22,8 @@ info = {
 
 class ThreeDeeBooruExtractor(JSONBooruExtractor):
 
-    def __init__(self, match, config):
-        JSONBooruExtractor.__init__(self, match, config, info)
+    def __init__(self, match):
+        JSONBooruExtractor.__init__(self, match, info)
         self.api_url = "http://behoimi.org/post/index.json"
         self.headers = {
             "Referer": "http://behoimi.org/post/show/",

gallery_dl/extractor/4chan.py

@@ -25,8 +25,8 @@ class FourChanExtractor(ChanExtractor):
     api_url = "https://a.4cdn.org/{board}/thread/{thread}.json"
     file_url = "https://i.4cdn.org/{board}/{tim}{ext}"
 
-    def __init__(self, match, config):
+    def __init__(self, match):
         ChanExtractor.__init__(
-            self, config, info["category"],
+            self, info["category"],
             match.group(1), match.group(2)
         )

gallery_dl/extractor/8chan.py

@@ -25,8 +25,8 @@ class InfinityChanExtractor(ChanExtractor):
     api_url = "https://8ch.net/{board}/res/{thread}.json"
     file_url = "https://media.8ch.net/{board}/src/{tim}{ext}"
 
-    def __init__(self, match, config):
+    def __init__(self, match):
         ChanExtractor.__init__(
-            self, config, info["category"],
+            self, info["category"],
             match.group(1), match.group(2)
         )

gallery_dl/extractor/batoto.py

@@ -27,8 +27,8 @@ class BatotoExtractor(AsynchronousExtractor):
 
     url_base = "http://bato.to/read/_/"
 
-    def __init__(self, match, config):
-        AsynchronousExtractor.__init__(self, config)
+    def __init__(self, match):
+        AsynchronousExtractor.__init__(self)
         self.chapter_id = match.group(1)
 
     def items(self):

gallery_dl/extractor/booru.py

@@ -19,8 +19,8 @@ class BooruExtractor(SequentialExtractor):
 
     api_url = ""
 
-    def __init__(self, match, config, info):
-        SequentialExtractor.__init__(self, config)
+    def __init__(self, match, info):
+        SequentialExtractor.__init__(self)
         self.info = info
         self.tags = text.unquote(match.group(1))
         self.page = "page"

gallery_dl/extractor/chan.py

@@ -10,15 +10,14 @@
 
 from .common import SequentialExtractor, Message
 from .. import text
-import re
 
 class ChanExtractor(SequentialExtractor):
 
     api_url = ""
     file_url = ""
 
-    def __init__(self, config, category, board, thread):
-        SequentialExtractor.__init__(self, config)
+    def __init__(self, category, board, thread):
+        SequentialExtractor.__init__(self)
         self.metadata = {
             "category": category,
             "board": board,

gallery_dl/extractor/common.py

@@ -12,7 +12,7 @@ import time
 import queue
 import requests
 import threading
-import html.parser
+from .. import config
 
 
 class Message():
@@ -47,15 +47,15 @@ class Extractor():
 
 class SequentialExtractor(Extractor):
 
-    def __init__(self, _):
+    def __init__(self):
         Extractor.__init__(self)
 
 
 class AsynchronousExtractor(Extractor):
 
-    def __init__(self, config):
+    def __init__(self):
         Extractor.__init__(self)
-        queue_size = int(config.get("general", "queue-size", fallback=5))
+        queue_size = int(config.get(("queue-size",), default=5))
         self.__queue = queue.Queue(maxsize=queue_size)
         self.__thread = threading.Thread(target=self.async_items, daemon=True)
 

gallery_dl/extractor/danbooru.py

@@ -22,6 +22,6 @@ info = {
 
 class DanbooruExtractor(JSONBooruExtractor):
 
-    def __init__(self, match, config):
-        JSONBooruExtractor.__init__(self, match, config, info)
+    def __init__(self, match):
+        JSONBooruExtractor.__init__(self, match, info)
         self.api_url = "https://danbooru.donmai.us/posts.json"

gallery_dl/extractor/e621.py

@@ -23,6 +23,6 @@ info = {
 
 class E621Extractor(JSONBooruExtractor):
 
-    def __init__(self, match, config):
-        JSONBooruExtractor.__init__(self, match, config, info)
+    def __init__(self, match):
+        JSONBooruExtractor.__init__(self, match, info)
         self.api_url = "https://e621.net/post/index.json"

gallery_dl/extractor/gelbooru.py

@@ -22,8 +22,8 @@ info = {
 
 class GelbooruExtractor(XMLBooruExtractor):
 
-    def __init__(self, match, config):
-        XMLBooruExtractor.__init__(self, match, config, info)
+    def __init__(self, match):
+        XMLBooruExtractor.__init__(self, match, info)
         self.api_url = "http://gelbooru.com/"
         self.params = {"page":"dapi", "s":"post", "q":"index", "tags":self.tags}
 

gallery_dl/extractor/imagebam.py

@@ -25,8 +25,8 @@ class ImagebamExtractor(AsynchronousExtractor):
 
     url_base = "http://www.imagebam.com"
 
-    def __init__(self, match, config):
-        AsynchronousExtractor.__init__(self, config)
+    def __init__(self, match):
+        AsynchronousExtractor.__init__(self)
         self.match = match
         self.num = 0
         self.metadata = {}

gallery_dl/extractor/imgbox.py

@@ -26,8 +26,8 @@ class ImgboxExtractor(AsynchronousExtractor):
 
     url_base = "http://imgbox.com"
 
-    def __init__(self, match, config):
-        AsynchronousExtractor.__init__(self, config)
+    def __init__(self, match):
+        AsynchronousExtractor.__init__(self)
         self.key = match.group(1)
         self.metadata = {}
 

gallery_dl/extractor/imgchili.py

@@ -24,8 +24,8 @@ info = {
 
 class ImgchiliExtractor(SequentialExtractor):
 
-    def __init__(self, match, config):
-        SequentialExtractor.__init__(self, config)
+    def __init__(self, match):
+        SequentialExtractor.__init__(self)
         self.match = match
         self.num = 0
 

gallery_dl/extractor/mangareader.py

@@ -28,8 +28,8 @@ class MangaReaderExtractor(AsynchronousExtractor):
 
     url_base = "http://www.mangareader.net"
 
-    def __init__(self, match, config):
-        AsynchronousExtractor.__init__(self, config)
+    def __init__(self, match):
+        AsynchronousExtractor.__init__(self)
         self.part = match.group(1)
 
     def items(self):

gallery_dl/extractor/nijie.py

@@ -9,7 +9,7 @@
 """Extract images from https://nijie.info/"""
 
 from .common import AsynchronousExtractor, Message
-from ..text  import filename_from_url
+from .. import config, text
 import re
 
 info = {
@@ -26,8 +26,8 @@ class NijieExtractor(AsynchronousExtractor):
 
     popup_url = "https://nijie.info/view_popup.php?id="
 
-    def __init__(self, match, config):
-        AsynchronousExtractor.__init__(self, config)
+    def __init__(self, match):
+        AsynchronousExtractor.__init__(self)
         self.artist_id = match.group(1)
         self.artist_url = (
             "https://nijie.info/members_illust.php?id="
@@ -36,7 +36,9 @@ class NijieExtractor(AsynchronousExtractor):
         self.session.headers["Referer"] = self.artist_url
         self.session.cookies["R18"] = "1"
         self.session.cookies["nijie_referer"] = "nijie.info"
-        self.session.cookies.update(config["nijie-cookies"])
+        self.session.cookies.update(
+            config.get(("extractor", info["category"], "cookies"))
+        )
 
     def items(self):
         data = self.get_job_metadata()
@@ -56,19 +58,19 @@ class NijieExtractor(AsynchronousExtractor):
 
     def get_image_ids(self):
         """Collect all image-ids for a specific artist"""
-        text = self.request(self.artist_url).text
+        page = self.request(self.artist_url).text
         regex = r'<a href="/view\.php\?id=(\d+)"'
-        return [m.group(1) for m in re.finditer(regex, text)]
+        return [m.group(1) for m in re.finditer(regex, page)]
 
     def get_image_data(self, image_id):
         """Get URL and metadata for images specified by 'image_id'"""
-        text = self.request(self.popup_url + image_id).text
-        matches = re.findall('<img src="([^"]+)"', text)
+        page = self.request(self.popup_url + image_id).text
+        matches = re.findall('<img src="([^"]+)"', page)
         for index, url in enumerate(matches):
             yield "https:" + url, {
                 "count": len(matches),
                 "index": index,
                 "image-id": image_id,
-                "name" : filename_from_url(url),
+                "name" : text.filename_from_url(url),
                 "extension": url[url.rfind(".")+1:],
             }

gallery_dl/extractor/pixiv.py

@@ -9,7 +9,7 @@
 """Extract images and ugoira from http://www.pixiv.net/"""
 
 from .common import SequentialExtractor, Message
-from .. import text
+from .. import config, text
 import re
 import json
 
@@ -29,16 +29,15 @@ class PixivExtractor(SequentialExtractor):
     member_url = "http://www.pixiv.net/member_illust.php"
     illust_url = "http://www.pixiv.net/member_illust.php?mode=medium"
 
-    def __init__(self, match, config):
-        SequentialExtractor.__init__(self, config)
-        self.config = config
+    def __init__(self, match):
+        SequentialExtractor.__init__(self)
         self.artist_id = match.group(1)
         self.api = PixivAPI(self.session)
 
     def items(self):
         self.api.login(
-            self.config.get("pixiv", "username"),
-            self.config.get("pixiv", "password"),
+            config.get(("extractor", "pixiv", "username")),
+            config.get(("extractor", "pixiv", "password")),
         )
         metadata = self.get_job_metadata()
 

gallery_dl/extractor/redhawkscans.py

@@ -28,8 +28,8 @@ class RedHawkScansExtractor(SequentialExtractor):
 
     url_base = "https://manga.redhawkscans.com/reader/read/"
 
-    def __init__(self, match, config):
-        SequentialExtractor.__init__(self, config)
+    def __init__(self, match):
+        SequentialExtractor.__init__(self)
         self.part = match.group(1)
 
     def items(self):

gallery_dl/extractor/yandere.py

@@ -22,6 +22,6 @@ info = {
 
 class YandereExtractor(JSONBooruExtractor):
 
-    def __init__(self, match, config):
-        JSONBooruExtractor.__init__(self, match, config, info)
+    def __init__(self, match):
+        JSONBooruExtractor.__init__(self, match, info)
         self.api_url = "https://yande.re/post.json"

test/test_config.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+# Copyright 2015 Mike Fährmann
+#
+# 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.
+
+import unittest
+import gallery_dl.config as config
+import os
+import tempfile
+
+class TestConfig(unittest.TestCase):
+
+    def setUp(self):
+        fd, self._configfile = tempfile.mkstemp()
+        with os.fdopen(fd, "w") as file:
+            file.write('{"a": "1", "b": {"c": "text"}}')
+        config.load(self._configfile)
+
+    def tearDown(self):
+        config.clear()
+        os.remove(self._configfile)
+
+    def test_get(self):
+        self.assertEqual(config.get(["a"]), "1")
+        self.assertEqual(config.get(["b", "c"]), "text")
+        self.assertEqual(config.get(["d"]), None)
+        self.assertEqual(config.get(["e", "f", "g"], 123), 123)
+
+    def test_set(self):
+        config.set(["b", "c"], [1, 2, 3])
+        config.set(["e", "f", "g"], value=234)
+        self.assertEqual(config.get(["b", "c"]), [1, 2, 3])
+        self.assertEqual(config.get(["e", "f", "g"]), 234)
+
+    def test_interpolate(self):
+        self.assertEqual(config.interpolate(["a"]), "1")
+        self.assertEqual(config.interpolate(["b", "a"]), "1")
+        self.assertEqual(config.interpolate(["b", "c"], "2"), "text")
+        self.assertEqual(config.interpolate(["b", "d"], "2"), "2")
+        config.set(["d"], 123)
+        self.assertEqual(config.interpolate(["b", "d"], "2"), 123)
+        self.assertEqual(config.interpolate(["d", "d"], "2"), 123)
+
+if __name__ == '__main__':
+    unittest.main()