New upstream version 1.14.4.upstream/1.14.4

1 files changed, 24 insertions, 19 deletions

diff --git a/gallery_dl/extractor/subscribestar.py b/gallery_dl/extractor/subscribestar.py
index 08d8850..076d0c0 100644
--- a/gallery_dl/extractor/subscribestar.py
+++ b/gallery_dl/extractor/subscribestar.py
@@ -11,7 +11,6 @@
 from .common import Extractor, Message
 from .. import text, exception
 from ..cache import cache
-import datetime
 import json
 
 
@@ -35,8 +34,6 @@ class SubscribestarExtractor(Extractor):
             self.cookiedomain = "subscribestar.adult"
             self.subcategory += "-adult"
         Extractor.__init__(self, match)
-        self.metadata = self.config("metadata", False)
-        self._year = " " + str(datetime.date.today().year)
 
     def items(self):
         self.login()
@@ -92,38 +89,46 @@ class SubscribestarExtractor(Extractor):
 
     @staticmethod
     def _media_from_post(html):
+        media = []
+
         gallery = text.extract(html, 'data-gallery="', '"')[0]
         if gallery:
-            return [
+            media.extend(
                 item for item in json.loads(text.unescape(gallery))
                 if "/previews/" not in item["url"]
-            ]
-        return ()
+            )
+
+        attachments = text.extract(
+            html, 'class="uploads-docs"', 'data-role="post-edit_form"')[0]
+        if attachments:
+            for att in attachments.split('class="doc_preview"')[1:]:
+                media.append({
+                    "id"  : text.parse_int(text.extract(
+                        att, 'data-upload-id="', '"')[0]),
+                    "url" : text.extract(att, 'href="', '"')[0],
+                    "type": "attachment",
+                })
+
+        return media
 
     def _data_from_post(self, html):
         extr = text.extract_from(html)
-        data = {
+        return {
             "post_id"    : text.parse_int(extr('data-id="', '"')),
             "author_id"  : text.parse_int(extr('data-user-id="', '"')),
             "author_name": text.unescape(extr('href="/', '"')),
             "author_nick": text.unescape(extr('>', '<')),
+            "date"       : self._parse_datetime(text.remove_html(extr(
+                'class="post-date">', '</'))),
             "content"    : (extr(
                 '<div class="post-content', '<div class="post-uploads')
                 .partition(">")[2]),
         }
 
-        if self.metadata:
-            url = "{}/posts/{}".format(self.root, data["post_id"])
-            page = self.request(url).text
-            data["date"] = self._parse_datetime(text.extract(
-                page, 'class="section-subtitle">', '<')[0])
-
-        return data
-
     def _parse_datetime(self, dt):
-        date = text.parse_datetime(dt, "%B %d, %Y %H:%M")
+        date = text.parse_datetime(dt, "%b %d, %Y %I:%M %p")
         if date is dt:
-            date = text.parse_datetime(dt + self._year, "%d %b %H:%M %Y")
+            date = text.parse_datetime(dt, "%B %d, %Y %I:%M %p")
         return date
 
 
@@ -141,6 +146,7 @@ class SubscribestarUserExtractor(SubscribestarExtractor):
                 "author_name": "subscribestar",
                 "author_nick": "SubscribeStar",
                 "content": str,
+                "date"   : "type:datetime",
                 "height" : int,
                 "id"     : int,
                 "pinned" : bool,
@@ -209,8 +215,7 @@ class SubscribestarPostExtractor(SubscribestarExtractor):
 
     def posts(self):
         url = "{}/posts/{}".format(self.root, self.item)
-        self._page = self.request(url).text
-        return (self._page,)
+        return (self.request(url).text,)
 
     def _data_from_post(self, html):
         extr = text.extract_from(html)