[speakerdeck] Add a new extractor for speakerdeck.com (#726)

gallery_dl/extractor/__init__.py

@@ -105,6 +105,7 @@ modules = [
     "slickpic",
     "slideshare",
     "smugmug",
+    "speakerdeck",
     "tsumino",
     "tumblr",
     "twitter",

gallery_dl/extractor/speakerdeck.py

@@ -0,0 +1,70 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2020 Leonardo Taccari
+#
+# 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://speakerdeck.com/"""
+
+from .common import Extractor, Message
+from .. import text
+
+
+class SpeakerdeckPresentationExtractor(Extractor):
+    """Extractor for images from a presentation on speakerdeck.com"""
+    category = "speakerdeck"
+    subcategory = "presentation"
+    directory_fmt = ("{category}", "{user}")
+    filename_fmt = "{presentation}-{num:>02}.{extension}"
+    archive_fmt = "{presentation}_{num}"
+    pattern = (r"(?:https?://)?(?:www\.)?speakerdeck\.com"
+               r"/([^/?&#]+)/([^/?&#]+)")
+    test = (
+        (("https://speakerdeck.com/speakerdeck/introduction-to-speakerdeck"), {
+            "url": "e97d4a7d5c64267e921c13eb7946d7074794a0d2",
+            "content": "75c7abf0969b0bcab23e0da9712c95ee5113db3a",
+        }),
+    )
+
+    def __init__(self, match):
+        Extractor.__init__(self, match)
+        self.user, self.presentation = match.groups()
+        self.presentation_id = None
+
+    def items(self):
+        data = self.get_job_metadata()
+        imgs = self.get_image_urls()
+        data["count"] = len(imgs)
+        yield Message.Version, 1
+        yield Message.Directory, data
+        for data["num"], url in enumerate(imgs, 1):
+            yield Message.Url, url, text.nameext_from_url(url, data)
+
+    def get_job_metadata(self):
+        """Collect metadata for extractor-job"""
+        url = "https://speakerdeck.com/oembed.json"
+        params = {
+            "url": "https://speakerdeck.com/" + self.user +
+                   "/" + self.presentation,
+        }
+
+        data = self.request(url, params=params).json()
+
+        self.presentation_id, pos = \
+            text.extract(data["html"], 'src="//speakerdeck.com/player/', '"')
+
+        return {
+            "user": self.user,
+            "presentation": self.presentation,
+            "presentation_id": self.presentation_id,
+            "title": data["title"],
+            "author": data["author_name"],
+        }
+
+    def get_image_urls(self):
+        """Extract and return a list of all image-urls"""
+        page = self.request("https://speakerdeck.com/player/" +
+                            self.presentation_id).text
+        return list(text.extract_iter(page, 'js-sd-slide" data-url="', '"'))

scripts/supportedsites.py

@@ -80,6 +80,7 @@ CATEGORY_MAP = {
     "slickpic"       : "SlickPic",
     "slideshare"     : "SlideShare",
     "smugmug"        : "SmugMug",
+    "speakerdeck"    : "Speaker Deck",
     "thebarchive"    : "The /b/ Archive",
     "vanillarock"    : "もえぴりあ",
     "vsco"           : "VSCO",