warp-beacon 2.7.2__tar.gz → 2.7.4__tar.gz

{warp_beacon-2.7.2/warp_beacon.egg-info → warp_beacon-2.7.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: warp_beacon
-Version: 2.7.2
+Version: 2.7.4
 Summary: Telegram bot for expanding external media links
 Home-page: https://github.com/sb0y/warp_beacon
 Author: Andrey Bagrintsev

warp_beacon-2.7.4/warp_beacon/__version__.py

@@ -0,0 +1,2 @@
+__version__ = "2.7.4"
+

{warp_beacon-2.7.2 → warp_beacon-2.7.4}/warp_beacon/scraper/__init__.py

@@ -392,6 +392,10 @@ class AsyncDownloader(object):
 											))
 									else:
 										logging.info("Scrolling in progress, ignoring request")
+								
+								# report media seen
+								if job.job_origin is Origin.INSTAGRAM:
+									actor.report_seen(items)
 						else:
 							logging.info("Job already in work in parallel worker. Redirecting job to upload worker.")
 							self.uploader.queue_task(job.to_upload_job())

{warp_beacon-2.7.2 → warp_beacon-2.7.4}/warp_beacon/scraper/instagram/instagram.py

@@ -256,6 +256,7 @@ class InstagramScraper(ScraperAbstract):
 			"canonical_name": self.extract_canonical_name(media_info),
 			"media_type": JobType.VIDEO,
 			"last_pk": media_info.pk,
+			"last_id": media_info.id,
 			"media_info": {"duration": round(media_info.video_duration)}
 		}
 
@@ -270,7 +271,8 @@ class InstagramScraper(ScraperAbstract):
 			"local_media_path": self.rename_local_file(path),
 			"canonical_name": self.extract_canonical_name(media_info),
 			"media_type": JobType.IMAGE,
-			"last_pk": media_info.pk
+			"last_pk": media_info.pk,
+			"last_id": media_info.id
 		}
 
 	def download_story(self, story_info: Story) -> dict:
@@ -296,7 +298,14 @@ class InstagramScraper(ScraperAbstract):
 			media_type = JobType.VIDEO
 			media_info["duration"] = story_info.video_duration
 
-		return {"local_media_path": self.rename_local_file(path), "media_type": media_type, "media_info": media_info, "effective_url": effective_url}
+		return {
+			"local_media_path": self.rename_local_file(path),
+			"media_type": media_type,
+			"media_info": media_info,
+			"effective_url": effective_url,
+			"last_pk": story_info.pk,
+			"last_id": story_info.id
+		}
 
 	def download_stories(self, stories: list[Story]) -> dict:
 		chunks = []
@@ -306,21 +315,30 @@ class InstagramScraper(ScraperAbstract):
 				chunk.append(self.download_story(story_info=story))
 			chunks.append(chunk)
 
-		return {"media_type": JobType.COLLECTION, "save_items": True, "items": chunks}
+		return {
+			"media_type": JobType.COLLECTION,
+			"save_items": True,
+			"items": chunks
+		}
 
 	def download_album(self, media_info: Media) -> dict:
 		chunks = []
 		for media_chunk in Utils.chunker(media_info.resources, 10):
 			chunk = []
 			for media in media_chunk:
-				_media_info = self.download_hndlr(self.cl.media_info_v1, media.pk)
+				_media_info = self.download_hndlr(self.cl.media_info, media.pk)
 				if media.media_type == 1: # photo
 					chunk.append(self.download_photo(url=_media_info.thumbnail_url, media_info=_media_info))
 				elif media.media_type == 2: # video
 					chunk.append(self.download_video(url=_media_info.video_url, media_info=_media_info))
 			chunks.append(chunk)
 
-		return {"media_type": JobType.COLLECTION, "items": chunks}
+		return {
+			"media_type": JobType.COLLECTION,
+			"items": chunks,
+			"last_pk": media_info.pk,
+			"last_id": media_info.id
+		}
 
 	def extract_canonical_name(self, media: Media) -> str:
 		ret = ""
@@ -349,7 +367,7 @@ class InstagramScraper(ScraperAbstract):
 					#	"chat_id": self.job.chat_id,
 					#	"message_id": self.job.placeholder_message_id
 					#})
-					media_info = self.download_hndlr(self.cl.media_info_v1, media_id)
+					media_info = self.download_hndlr(self.cl.media_info, media_id)
 					logging.info("media_type is '%d', product_type is '%s'", media_info.media_type, media_info.product_type)
 					if media_info.media_type == 2 and media_info.product_type in ("clips", "ad"): # Reels
 						res.append(self.download_video(url=media_info.video_url, media_info=media_info))
@@ -357,10 +375,6 @@ class InstagramScraper(ScraperAbstract):
 						res.append(self.download_photo(url=media_info.thumbnail_url, media_info=media_info))
 					elif media_info.media_type == 8: # Album
 						res.append(self.download_album(media_info=media_info))
-					try:
-						self.cl.media_seen([media_info.id])
-					except Exception as e:
-						logging.warning("Failed to mark seen with id = '%s'", media_info.id, exc_info=e)
 				elif scrap_type == "story":
 					story_info = self.cl.story_info(media_id)
 					logging.info("media_type for story is '%d'", story_info.media_type)
@@ -460,4 +474,26 @@ class InstagramScraper(ScraperAbstract):
 				"report_type": ReportType.PROGRESS
 			}
 			self.status_pipe.send(msg)
-			self._download_progress_threshold += 5
+			self._download_progress_threshold += 5
+
+	def report_seen(self, items: dict) -> None:
+		try:
+			seen = []
+			for item in items:
+				if item["media_type"] == JobType.COLLECTION:
+					if item.get("last_id", None):
+						seen.append(item["last_id"])
+					if item.get("items", None):
+						for col_item in item["items"]:
+							last_id = col_item.get("last_id", None)
+							if last_id:
+								seen.append(last_id)
+				else:
+					last_id = item.get("last_id", None)
+					if last_id:
+						seen.append(last_id)
+
+			if seen:
+				self.download_hndlr(self.cl.media_seen, seen)
+		except Exception as e:
+			logging.error("Failed to report seen media!", exc_info=e)

{warp_beacon-2.7.2 → warp_beacon-2.7.4}/warp_beacon/telegram/progress_bar.py

@@ -15,6 +15,7 @@ class ProgressBar(object):
 		self._next_threshold = 5
 		self.client = client
 		self.complete = False
+		self.rendered_text = ""
 
 	def is_complete(self) -> bool:
 		return self.complete
@@ -104,13 +105,18 @@ class ProgressBar(object):
 			pbar = self.make_emoji_progress_bar(percent, 10)
 			logging.info("[Progress bar]: Operation: %s %d%%", operation, percent)
 			try:
-				# we don't need to wait completion, waste of time and resources
 				text = f"{pbar}\n{operation}"
 				if label:
 					text += f"\n<code>{label}</code>"
 				if total:
 					text += f" <b>{self.format_size_si(total)}</b>"
+
+				# avoid duplicate render
+				if text == f"{chat_id}:{message_id}:{text}":
+					return
+
 				await self.client.edit_message_caption(chat_id, message_id, text, ParseMode.HTML)
+				self.rendered_text = f"{chat_id}:{message_id}:{text}"
 				#task = self.client.loop.create_task(
 				#	self.client.edit_message_caption(chat_id, message_id, text, ParseMode.HTML)
 				#)
@@ -120,7 +126,7 @@ class ProgressBar(object):
 			except Exception as e:
 				logging.warning("An error occurred while setup task to update progress bar")
 				logging.exception(e)
-			if total > 0:
+			if total > 0 and percent != 0:
 				self._next_threshold += 5
 
 	@staticmethod

{warp_beacon-2.7.2 → warp_beacon-2.7.4}/warp_beacon/uploader/__init__.py

@@ -4,6 +4,7 @@ from typing import Callable
 import asyncio
 import threading
 import multiprocessing
+from queue import Empty
 
 from warp_beacon.jobs.types import JobType
 from warp_beacon.jobs.upload_job import UploadJob
@@ -179,7 +180,7 @@ class AsyncUploader(object):
 							logging.info("No callback no call!!")
 					except Exception as e:
 						logging.exception(e)
-				except multiprocessing.Queue.empty:
+				except Empty:
 					pass
 			except Exception as e:
 				logging.error("Exception occurred inside upload worker!")

{warp_beacon-2.7.2 → warp_beacon-2.7.4/warp_beacon.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: warp_beacon
-Version: 2.7.2
+Version: 2.7.4
 Summary: Telegram bot for expanding external media links
 Home-page: https://github.com/sb0y/warp_beacon
 Author: Andrey Bagrintsev

warp_beacon-2.7.2/warp_beacon/__version__.py

@@ -1,2 +0,0 @@
-__version__ = "2.7.2"
-