[imagebam] update to new extractor interface

gallery_dl/extractor/imagebam.py

@@ -1,20 +1,48 @@
-from .common import AsyncExtractor
+# -*- coding: utf-8 -*-
 
-class Extractor(AsyncExtractor):
+# Copyright 2014, 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.
+
+"""Extract images from galleries at http://www.imagebam.com/"""
+
+from .common import AsynchronousExtractor
+from .common import Message
+from .common import filename_from_url
+
+info = {
+    "category": "imagebam",
+    "extractor": "ImagebamExtractor",
+    "directory": ["{category}", "{title} - {key}"],
+    "filename": "{num:>03}-{name}",
+    "pattern": [
+        r"(?:https?://)?(?:www\.)?imagebam\.com/(gallery)/([^/]+).*",
+    ],
+}
+
+class ImagebamExtractor(AsynchronousExtractor):
+
+    url_base = "http://www.imagebam.com"
 
     def __init__(self, match, config):
-        AsyncExtractor.__init__(self, config)
+        AsynchronousExtractor.__init__(self, config)
-        title, key = self.get_title(match)
+        self.match = match
-        self.category  = "imagebam"
+        self.num = 0
-        self.directory = title + " - " + key
+        self.metadata = {}
 
-    def images(self):
+    def items(self):
-        next_url = self.url
+        self.num = 0
-        num  = 1
+        self.metadata = self.get_job_metadata()
+        yield Message.Version, 1
+        yield Message.Directory, self.metadata
+
+        next_url = self.metadata["first-url"]
         done = False
         while not done:
             # get current page
-            text = self.request("http://www.imagebam.com" + next_url).text
+            text = self.request(self.url_base + next_url).text
 
             # get url for next page
             next_url, pos = self.extract(text, "<a class='buttonblue' href='", "'")
@@ -24,24 +52,30 @@ class Extractor(AsyncExtractor):
                 done = True
 
             # get image url
-            img_url , pos = self.extract(text, 'onclick="scale(this);" src="', '"', pos)
+            img_url, pos = self.extract(text, 'onclick="scale(this);" src="', '"', pos)
 
-            # extract filename from image url
+            yield Message.Url, img_url, self.get_file_metadata(img_url)
-            name = img_url[img_url.rindex("/")+1:]
 
-            yield img_url, "{:>03}-{}".format(num, name)
+    def get_job_metadata(self):
-            num += 1
+        """Collect metadata for extractor-job"""
+        gallery_key = self.match.group(2)
+        text = self.request(self.url_base + "/gallery/" + gallery_key).text
+        _    , pos = self.extract(text, "<img src='/img/icons/photos.png'", "")
+        title, pos = self.extract(text, "'> ", " <", pos)
+        count, pos = self.extract(text, "'>", " images", pos)
+        url  , pos = self.extract(text, "<a href='http://www.imagebam.com", "'", pos)
+        return {
+            "category": info["category"],
+            "key": gallery_key,
+            "title": title,
+            "count": count,
+            "first-url": url,
+        }
 
-    def get_title(self, match):
+    def get_file_metadata(self, url):
-        if match.group(1) == "image":
+        """Collect metadata for a downloadable file"""
-            text = self.request(match.group(0)).text
+        self.num += 1
-            gallery_url, _ = self.extract(text, "class='gallery_title'><a href='", "'")
+        data = self.metadata.copy()
-            gallery_key = gallery_url.split("/")[-2]
+        data["num"] = self.num
-        else:
+        data["name"] = filename_from_url(url)
-            gallery_key = match.group(2)
+        return data
-
-        text = self.request("http://www.imagebam.com/gallery/" + gallery_key).text
-        _       , pos = self.extract(text, "<img src='/img/icons/photos.png'", "")
-        title   , pos = self.extract(text, "'> ", " <", pos)
-        self.url, pos = self.extract(text, "<a href='http://www.imagebam.com", "'", pos)
-        return title, gallery_key