From eb0859fbaf66782f18419a016cedcca905fbbccd Mon Sep 17 00:00:00 2001
From: msramalho <19508417+msramalho@users.noreply.github.com>
Date: Wed, 18 Jan 2023 21:34:40 +0000
Subject: [PATCH] vk archiver

---
 src/archivers/__init__.py      |  5 ++-
 src/archivers/vk_archiverv2.py | 67 ++++++++++++++++++++++++++++++++++
 src/utils/misc.py              | 11 ++++++
 3 files changed, 81 insertions(+), 2 deletions(-)
 create mode 100644 src/archivers/vk_archiverv2.py

diff --git a/src/archivers/__init__.py b/src/archivers/__init__.py
index 8fb0265..d2a2c49 100644
--- a/src/archivers/__init__.py
+++ b/src/archivers/__init__.py
@@ -7,7 +7,7 @@ from .archiver import Archiverv2
 from .wayback_archiver import WaybackArchiver
 from .youtubedl_archiver import YoutubeDLArchiver
 # from .twitter_archiver import TwitterArchiver
-from .vk_archiver import VkArchiver
+# from .vk_archiver import VkArchiver
 # from .twitter_api_archiver import TwitterApiArchiver
 # from .instagram_archiver import InstagramArchiver
 
@@ -16,4 +16,5 @@ from .twitter_archiverv2 import TwitterArchiver
 from .twitter_api_archiverv2 import TwitterApiArchiver
 from .instagram_archiverv2 import InstagramArchiver
 from .tiktok_archiverv2 import TiktokArchiver
-from .telegram_archiverv2 import TelegramArchiver
\ No newline at end of file
+from .telegram_archiverv2 import TelegramArchiver
+from .vk_archiverv2 import VkArchiver
\ No newline at end of file
diff --git a/src/archivers/vk_archiverv2.py b/src/archivers/vk_archiverv2.py
new file mode 100644
index 0000000..147424d
--- /dev/null
+++ b/src/archivers/vk_archiverv2.py
@@ -0,0 +1,67 @@
+import re, json, mimetypes, os
+
+from loguru import logger
+from vk_url_scraper import VkScraper, DateTimeEncoder
+
+from metadata import Metadata
+from media import Media
+from utils.misc import dump_payload
+from .archiver import Archiverv2
+
+
+class VkArchiver(Archiverv2):
+    """"
+    VK videos are handled by YTDownloader, this archiver gets posts text and images.
+    Currently only works for /wall posts
+    """
+    name = "vk_archiver"
+    wall_pattern = re.compile(r"(wall.{0,1}\d+_\d+)")
+    photo_pattern = re.compile(r"(photo.{0,1}\d+_\d+)")
+
+    def __init__(self, config: dict) -> None:
+        super().__init__(config)
+        self.assert_valid_string("username")
+        self.assert_valid_string("password")
+        self.vks = VkScraper(self.username, self.password, session_file=self.session_file)
+
+    @staticmethod
+    def configs() -> dict:
+        return {
+            "username": {"default": None, "help": "valid VKontakte username"},
+            "password": {"default": None, "help": "valid VKontakte password"},
+            "session_file": {"default": "secrets/vk_config.v2.json", "help": "valid VKontakte password"},
+        }
+
+    def download(self, item: Metadata) -> Metadata:
+        url = item.get_url()
+
+        if "vk.com" not in item.netloc: return False
+
+        # some urls can contain multiple wall/photo/... parts and all will be fetched
+        vk_scrapes = self.vks.scrape(url)
+        if not len(vk_scrapes): return False
+
+        result = Metadata()
+        for scrape in vk_scrapes:
+            if not result.get_title():
+                result.set_title(scrape["text"])
+            if not result.get_timestamp():
+                result.set_timestamp(scrape["datetime"])
+
+        result.set_content(dump_payload(vk_scrapes))
+
+        textual_output = ""
+        title, datetime = vk_scrapes[0]["text"], vk_scrapes[0]["datetime"]
+        urls_found = []
+        for scrape in vk_scrapes:
+            textual_output += f"id: {scrape['id']}<br>time utc: {scrape['datetime']}<br>text: {scrape['text']}<br>payload: {dump_payload(scrape['payload'])}<br><hr/><br>"
+            title = scrape["text"] if len(title) == 0 else title
+            datetime = scrape["datetime"] if not datetime else datetime
+            for attachments in scrape["attachments"].values():
+                urls_found.extend(attachments)
+
+        filenames = self.vks.download_media(vk_scrapes, item.get_tmp_dir())
+        for filename in filenames:
+            result.add_media(Media(filename))
+
+        return result.success("vk")
diff --git a/src/utils/misc.py b/src/utils/misc.py
index 644c713..e7c5427 100644
--- a/src/utils/misc.py
+++ b/src/utils/misc.py
@@ -29,3 +29,14 @@ def getattr_or(o: object, prop: str, default=None):
     except:
         return default
 
+
+class DateTimeEncoder(json.JSONEncoder):
+    # to allow json.dump with datetimes do json.dumps(obj, cls=DateTimeEncoder)
+    def default(self, o):
+        if isinstance(o, datetime):
+            return str(o)  # with timezone
+        return json.JSONEncoder.default(self, o)
+
+
+def dump_payload(p):
+    return json.dumps(p, ensure_ascii=False, indent=4, cls=DateTimeEncoder)