[warosu] fix and update

gallery_dl/extractor/warosu.py

@@ -1,21 +1,22 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2017-2019 Mike Fährmann
+# Copyright 2017-2022 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 https://warosu.org/"""
+"""Extractors for https://warosu.org/"""
 
 from .common import Extractor, Message
 from .. import text
 
 
 class WarosuThreadExtractor(Extractor):
-    """Extractor for images from threads on warosu.org"""
+    """Extractor for threads on warosu.org"""
     category = "warosu"
     subcategory = "thread"
+    root = "https://warosu.org"
     directory_fmt = ("{category}", "{board}", "{thread} - {title}")
     filename_fmt = "{tim}-{filename}.{extension}"
     archive_fmt = "{board}_{thread}_{tim}"
@@ -31,7 +32,6 @@ class WarosuThreadExtractor(Extractor):
             "content": "d48df0a701e6599312bfff8674f4aa5d4fb8db1c",
         }),
     )
-    root = "https://warosu.org"
 
     def __init__(self, match):
         Extractor.__init__(self, match)
@@ -40,12 +40,12 @@ class WarosuThreadExtractor(Extractor):
     def items(self):
         url = "{}/{}/thread/{}".format(self.root, self.board, self.thread)
         page = self.request(url).text
-        data = self.get_metadata(page)
+        data = self.metadata(page)
         posts = self.posts(page)
 
         if not data["title"]:
-            title = text.remove_html(posts[0]["com"])
-            data["title"] = text.unescape(title)[:50]
+            data["title"] = text.unescape(text.remove_html(
+                posts[0]["com"]))[:50]
 
         yield Message.Directory, data
         for post in posts:
@@ -55,25 +55,24 @@ class WarosuThreadExtractor(Extractor):
                 post.update(data)
                 yield Message.Url, post["image"], post
 
-    def get_metadata(self, page):
-        """Collect metadata for extractor-job"""
+    def metadata(self, page):
         boardname = text.extr(page, "<title>", "</title>")
         title = text.extr(page, 'filetitle" itemprop="name">', '<')
         return {
-            "board": self.board,
+            "board"     : self.board,
             "board_name": boardname.rpartition(" - ")[2],
-            "thread": self.thread,
-            "title": title,
+            "thread"    : self.thread,
+            "title"     : title,
         }
 
     def posts(self, page):
-        """Build a list of all post-objects"""
+        """Build a list of all post objects"""
         page = text.extr(page, '<div class="content">', '<table>')
         needle = '<table itemscope itemtype="http://schema.org/Comment">'
         return [self.parse(post) for post in page.split(needle)]
 
     def parse(self, post):
-        """Build post-object by extracting data from an HTML post"""
+        """Build post object by extracting data from an HTML post"""
         data = self._extract_post(post)
         if "<span>File:" in post:
             self._extract_image(post, data)
@@ -84,24 +83,23 @@ class WarosuThreadExtractor(Extractor):
 
     @staticmethod
     def _extract_post(post):
-        data = text.extract_all(post, (
-            ("no"  , 'id="p', '"'),
-            ("name", '<span itemprop="name">', '</span>'),
-            ("time", '<span class="posttime" title="', '000">'),
-            ("now" , '', '<'),
-            ("com" , '<blockquote><p itemprop="text">', '</p></blockquote>'),
-        ))[0]
-        data["com"] = text.unescape(text.remove_html(data["com"].strip()))
-        return data
+        extr = text.extract_from(post)
+        return {
+            "no"  : extr('id="p', '"'),
+            "name": extr('<span itemprop="name">', "</span>"),
+            "time": extr('<span class="posttime" title="', '000">'),
+            "now" : extr("", "<"),
+            "com" : text.unescape(text.remove_html(extr(
+                '<blockquote><p itemprop="text">', '</p></blockquote>'
+            ).strip())),
+        }
 
     @staticmethod
     def _extract_image(post, data):
-        text.extract_all(post, (
-            ("fsize"   , '<span>File: ', ', '),
-            ("w"       , '', 'x'),
-            ("h"       , '', ', '),
-            ("filename", '', '<'),
-            ("image"   , '<br />\n<a href="', '"'),
-        ), 0, data)
-        data["filename"] = text.unquote(data["filename"].rpartition(".")[0])
-        data["image"] = "https:" + data["image"]
+        extr = text.extract_from(post)
+        data["fsize"] = extr("<span>File: ", ", ")
+        data["w"] = extr("", "x")
+        data["h"] = extr("", ", ")
+        data["filename"] = text.unquote(extr("", "<").rpartition(".")[0])
+        extr("<br />", "")
+        data["image"] = "https:" + extr('<a href="', '"')