[imagebam] fix extraction

docs/supportedsites.md

@@ -261,7 +261,7 @@ Consider all sites to be NSFW unless otherwise known.
 </tr>
 <tr>
     <td>ImageBam</td>
-    <td>http://www.imagebam.com/</td>
+    <td>https://www.imagebam.com/</td>
     <td>Galleries, individual Images</td>
     <td></td>
 </tr>

gallery_dl/extractor/imagebam.py

@@ -1,12 +1,12 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2014-2019 Mike Fährmann
+# Copyright 2014-2021 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 http://www.imagebam.com/"""
+"""Extractors for https://www.imagebam.com/"""
 
 from .common import Extractor, Message
 from .. import text, exception
@@ -15,34 +15,29 @@ from .. import text, exception
 class ImagebamExtractor(Extractor):
     """Base class for imagebam extractors"""
     category = "imagebam"
-    root = "http://www.imagebam.com"
+    root = "https://www.imagebam.com"
 
-    def get_image_data(self, page_url, data):
-        """Fill 'data' and return image URL"""
+    def get_image_data(self, data):
+        page_url = "{}/image/{}".format(self.root, data["image_key"])
         page = self.request(page_url).text
-        image_url = text.extract(page, 'property="og:image" content="', '"')[0]
-        data["extension"] = image_url.rpartition(".")[2]
-        data["image_key"] = page_url.rpartition("/")[2]
-        data["image_id"] = data["image_key"][6:]
-        return image_url
+        image_url, pos = text.extract(page, '<img src="https://images', '"')
+        filename = text.unescape(text.extract(page, 'alt="', '"', pos)[0])
 
-    def request_page(self, url):
-        """Retrive the main part of a gallery page"""
-        page = self.request(text.urljoin(self.root, url)).text
-        return text.extract(page, "<fieldset>", "</fieldset>")[0]
+        data["url"] = "https://images" + image_url
+        data["filename"], _, data["extension"] = filename.rpartition(".")
 
 
 class ImagebamGalleryExtractor(ImagebamExtractor):
     """Extractor for image galleries from imagebam.com"""
     subcategory = "gallery"
-    directory_fmt = ("{category}", "{title} - {gallery_key}")
-    filename_fmt = "{num:>03}-{image_key}.{extension}"
+    directory_fmt = ("{category}", "{title} {gallery_key}")
+    filename_fmt = "{num:>03} {filename}.{extension}"
     archive_fmt = "{gallery_key}_{image_key}"
     pattern = r"(?:https?://)?(?:www\.)?imagebam\.com/gallery/([0-9a-z]+)"
     test = (
-        ("http://www.imagebam.com/gallery/adz2y0f9574bjpmonaismyrhtjgvey4o", {
+        ("https://www.imagebam.com/gallery/adz2y0f9574bjpmonaismyrhtjgvey4o", {
             "url": "76d976788ae2757ac81694736b07b72356f5c4c8",
-            "keyword": "9e25b8827474ac93c54855e798d60aa3cbecbd7a",
+            "keyword": "b048478b1bbba3072a7fa9fcc40630b3efad1f6c",
             "content": "596e6bfa157f2c7169805d50075c2986549973a8",
         }),
         ("http://www.imagebam.com/gallery/op9dwcklwdrrguibnkoe7jxgvig30o5p", {
@@ -51,7 +46,7 @@ class ImagebamGalleryExtractor(ImagebamExtractor):
             "url": "32ae6fe5dc3e4ca73ff6252e522d16473595d1d1",
         }),
         ("http://www.imagebam.com/gallery/gsl8teckymt4vbvx1stjkyk37j70va2c", {
-            "exception": exception.NotFoundError,
+            "exception": exception.HttpError,
         }),
     )
 
@@ -61,55 +56,50 @@ class ImagebamGalleryExtractor(ImagebamExtractor):
 
     def items(self):
         url = "{}/gallery/{}".format(self.root, self.gallery_key)
-        page = self.request_page(url)
-        if not page or ">Error<" in page:
-            raise exception.NotFoundError("gallery")
+        page = self.request(url).text
 
         data = self.get_metadata(page)
-        imgs = self.get_image_pages(page)
-        data["count"] = len(imgs)
+        keys = self.get_image_keys(page)
+        keys.reverse()
+        data["count"] = len(keys)
         data["gallery_key"] = self.gallery_key
 
-        yield Message.Version, 1
         yield Message.Directory, data
-        for data["num"], page_url in enumerate(imgs, 1):
-            image_url = self.get_image_data(page_url, data)
-            yield Message.Url, image_url, data
+        for data["num"], data["image_key"] in enumerate(keys, 1):
+            self.get_image_data(data)
+            yield Message.Url, data["url"], data
 
     @staticmethod
     def get_metadata(page):
         """Return gallery metadata"""
-        return text.extract_all(page, (
-            ("title"      , "'> ", " <span "),
-            (None         , "'>", "</span>"),
-            ("description", ":#FCFCFC;'>", "</div>"),
-        ))[0]
+        title = text.extract(page, 'id="gallery-name">', '<')[0]
+        return {"title": text.unescape(title.strip())}
 
-    def get_image_pages(self, page):
-        """Return a list of all image pages"""
-        pages = []
+    def get_image_keys(self, page):
+        """Return a list of all image keys"""
+        keys = []
         while True:
-            pages.extend(text.extract_iter(page, "\n<a href='", "'"))
-            pos = page.find('"pagination_current"')
+            keys.extend(text.extract_iter(
+                page, '<a href="https://www.imagebam.com/image/', '"'))
+            pos = page.find('rel="next" aria-label="Next')
             if pos > 0:
-                url = text.extract(page, "<a href='", "'", pos)[0]
+                url = text.rextract(page, 'href="', '"', pos)[0]
                 if url:
-                    page = self.request_page(url)
+                    page = self.request(url).text
                     continue
-            return pages
+            return keys
 
 
 class ImagebamImageExtractor(ImagebamExtractor):
     """Extractor for single images from imagebam.com"""
     subcategory = "image"
-    filename_fmt = "{image_key}.{extension}"
     archive_fmt = "{image_key}"
     pattern = (r"(?:https?://)?(?:\w+\.)?imagebam\.com"
                r"/(?:image/|(?:[0-9a-f]{2}/){3})([0-9a-f]+)")
     test = (
-        ("http://www.imagebam.com/image/94d56c502511890", {
+        ("https://www.imagebam.com/image/94d56c502511890", {
             "url": "5e9ba3b1451f8ded0ae3a1b84402888893915d4a",
-            "keyword": "4263d4840007524129792b8587a562b5d20c2687",
+            "keyword": "2a4380d4b57554ff793898c2d6ec60987c86d1a1",
             "content": "0c8768055e4e20e7c7259608b67799171b691140",
         }),
         ("http://images3.imagebam.com/1d/8c/44/94d56c502511890.png"),
@@ -120,9 +110,7 @@ class ImagebamImageExtractor(ImagebamExtractor):
         self.image_key = match.group(1)
 
     def items(self):
-        page_url = "{}/image/{}".format(self.root, self.image_key)
-        data = {}
-        image_url = self.get_image_data(page_url, data)
-        yield Message.Version, 1
+        data = {"image_key": self.image_key}
+        self.get_image_data(data)
         yield Message.Directory, data
-        yield Message.Url, image_url, data
+        yield Message.Url, data["url"], data