[mangapark] add manga extractor

gallery_dl/extractor/mangapark.py

@@ -10,7 +10,33 @@
 
 from .common import Extractor, Message
 from .. import text
-import re
+
+class MangaparkMangaExtractor(Extractor):
+    """Extract all chapters of a manga from mangapark"""
+    category = "mangapark"
+    subcategory = "manga"
+    pattern = [r"(?:https?://)?(?:www\.)?mangapark\.me/manga/([^/]+)"]
+    url_base = "http://mangapark.me"
+
+    def __init__(self, match):
+        Extractor.__init__(self)
+        self.url_title = match.group(1)
+
+    def items(self):
+        yield Message.Version, 1
+        for chapter in self.get_chapters():
+            print(self.url_base + chapter)
+            yield Message.Queue, self.url_base + chapter
+
+    def get_chapters(self):
+        """Return a list of all chapter urls"""
+        page = self.request(self.url_base + "/manga/" + self.url_title).text
+        needle = '<a class="ch sts sts_1" target="_blank" href="'
+        pos = page.index('<div id="list" class="book-list">')
+        return reversed(list(
+            text.extract_iter(page, needle, '"', pos)
+        ))
+
 
 class MangaparkChapterExtractor(Extractor):
     """Extract a single manga-chapter from mangapark"""
@@ -18,7 +44,8 @@ class MangaparkChapterExtractor(Extractor):
     subcategory = "chapter"
     directory_fmt = ["{category}", "{manga}", "c{chapter:>03}{chapter-minor}"]
     filename_fmt = "{manga}_c{chapter:>03}{chapter-minor}_{page:>03}.{extension}"
-    pattern = [r"(?:https?://)?(?:www\.)?mangapark\.me/manga/([^/]+/s(\d+)(?:/v(\d+))?/c(\d+)(\.\d+)?)"]
+    pattern = [(r"(?:https?://)?(?:www\.)?mangapark\.me/manga/"
+                r"([^/]+/s(\d+)(?:/v(\d+))?/c(\d+)(\.\d+)?)")]
 
     def __init__(self, match):
         Extractor.__init__(self)
@@ -35,6 +62,7 @@ class MangaparkChapterExtractor(Extractor):
             yield Message.Url, data["url"], text.nameext_from_url(data["url"], data)
 
     def get_job_metadata(self, page):
+        """Collect metadata for extractor-job"""
         data = {
             "category": self.category,
             "version": self.version,
@@ -55,7 +83,9 @@ class MangaparkChapterExtractor(Extractor):
         data["manga"] = data["manga"][:pos]
         return data
 
-    def get_images(self, page):
+    @staticmethod
+    def get_images(page):
+        """Collect image-urls, -widths and -heights"""
         pos = 0
         while True:
             url   , pos = text.extract(page, ' target="_blank" href="', '"', pos)