From bcb23e44cee25be618dc52b3bb6b020455784931 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Sat, 21 Nov 2015 04:19:23 +0100
Subject: [PATCH] [powermanga] transfer code from redhawkscans

---
 gallery_dl/extractor/powermanga.py | 46 +++++++++++++++++++++++++++---
 1 file changed, 42 insertions(+), 4 deletions(-)

diff --git a/gallery_dl/extractor/powermanga.py b/gallery_dl/extractor/powermanga.py
index 40ebc909..ce66fa09 100644
--- a/gallery_dl/extractor/powermanga.py
+++ b/gallery_dl/extractor/powermanga.py
@@ -8,7 +8,11 @@
 
 """Extract manga pages from http://powermanga.org/"""
 
-from .redhawkscans import RedHawkScansExtractor
+from .common import Extractor, Message
+from .. import text, iso639_1
+import os.path
+import json
+import re
 
 info = {
     "category": "powermanga",
@@ -21,10 +25,44 @@ info = {
     ],
 }
 
-class PowerMangaExtractor(RedHawkScansExtractor):
+class PowerMangaExtractor(Extractor):
 
     def __init__(self, match):
-        RedHawkScansExtractor.__init__(self, match)
-        extra = "er" if "://reader" in match.string else ""
+        Extractor.__init__(self)
         self.category = info["category"]
+        self.part = match.group(1)
+        self.lang = match.group(2)
+        extra = "er" if "://reader" in match.string else ""
         self.url_base = "https://read" + extra + ".powermanga.org/read/"
+
+    def items(self):
+        yield Message.Version, 1
+        data, pages = self.get_job_metadata()
+        yield Message.Directory, data
+        for page_index, page_data in enumerate(pages, 1):
+            name, ext = os.path.splitext(page_data["filename"])
+            page_data.update(data)
+            page_data["page"] = page_index
+            page_data["name"] = name
+            page_data["extension"] = ext[1:]
+            yield Message.Url, "https" + page_data["url"][4:], page_data
+
+    def get_job_metadata(self):
+        """Collect metadata for extractor-job"""
+        response = self.request(self.url_base + self.part)
+        response.encoding = "utf-8"
+        page = response.text
+        _        , pos = text.extract(page, '<h1 class="tbtitle dnone">', '')
+        manga    , pos = text.extract(page, 'title="', '"', pos)
+        chapter  , pos = text.extract(page, '">', '</a>', pos)
+        json_data, pos = text.extract(page, 'var pages = ', ';', pos)
+        match = re.match(r"(\w+ (\d+)([^:+]*)(?:: (.*))?|[^:]+)", chapter)
+        return {
+            "category": self.category,
+            "manga": text.unescape(manga),
+            "chapter": match.group(2) or match.group(1),
+            "chapter-minor": match.group(3) or "",
+            "lang": self.lang,
+            "language": iso639_1.code_to_language(self.lang),
+            "title": text.unescape(match.group(4) or ""),
+        }, json.loads(json_data)