[mangashare] add manga-extractor

gallery_dl/extractor/mangashare.py

@@ -6,13 +6,37 @@
 # it under the terms of the GNU General Public License version 2 as
 # published by the Free Software Foundation.
 
-"""Extract manga pages from http://www.mangashare.com/"""
+"""Extract manga-chapters and entire manga from http://www.mangashare.com/"""
 
-from .common import AsynchronousExtractor, Message
+from .common import Extractor, AsynchronousExtractor, Message
 from .. import text
 
-class MangaShareExtractor(AsynchronousExtractor):
+class MangaShareMangaExtractor(Extractor):
+    """Extract all manga-chapters from mangashare"""
+    category = "mangashare"
+    directory_fmt = ["{category}", "{manga}", "c{chapter:>03} - {title}"]
+    filename_fmt = "{manga}_c{chapter:>03}_{page:>03}.{extension}"
+    pattern = [r"(?:https?://)?read\.mangashare\.com/[^/]+$"]
+
+    def __init__(self, match):
+        Extractor.__init__(self)
+        self.url = match.group(0)
+
+    def items(self):
+        yield Message.Version, 1
+        for chapter in self.get_chapters():
+            yield Message.Queue, chapter
+
+    def get_chapters(self):
+        """Return a list of all chapter urls"""
+        page = self.request(self.url).text
+        return reversed(list(
+            text.extract_iter(page, '<td class="datarow-0"><a href="', '"')
+        ))
+
 
+class MangaShareChapterExtractor(AsynchronousExtractor):
+    """Extract a single manga-chapter from mangashare"""
     category = "mangashare"
     directory_fmt = ["{category}", "{manga}", "c{chapter:>03} - {title}"]
     filename_fmt = "{manga}_c{chapter:>03}_{page:>03}.{extension}"