warp-beacon 2.3.13__tar.gz → 2.3.15__tar.gz

{warp_beacon-2.3.13/warp_beacon.egg-info → warp_beacon-2.3.15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: warp_beacon
-Version: 2.3.13
+Version: 2.3.15
 Summary: Telegram bot for expanding external media links
 Home-page: https://github.com/sb0y/warp_beacon
 Author: Andrey Bagrintsev

warp_beacon-2.3.15/warp_beacon/__version__.py

@@ -0,0 +1,2 @@
+__version__ = "2.3.15"
+

{warp_beacon-2.3.13 → warp_beacon-2.3.15}/warp_beacon/scraper/instagram/instagram.py

@@ -14,7 +14,7 @@ import urllib3
 from urllib.parse import urljoin, urlparse
 
 from instagrapi.mixins.story import Story
-#from instagrapi.types import Media
+from instagrapi.types import Media
 from instagrapi import Client
 from instagrapi.mixins.challenge import ChallengeChoice
 from instagrapi.exceptions import LoginRequired, PleaseWaitFewMinutes, MediaNotFound, ClientNotFoundError, UserNotFound, ChallengeRequired, \
@@ -187,19 +187,20 @@ class InstagramScraper(ScraperAbstract):
 
 		return ret_val
 
-	def download_video(self, url: str, media_info: dict) -> dict:
+	def download_video(self, url: str, media_info: Media) -> dict:
 		self.cl.request_timeout = int(os.environ.get("IG_REQUEST_TIMEOUT", default=60))
 		path = self._download_hndlr(self.cl.video_download_by_url, url, folder='/tmp')
-		return {"local_media_path": str(path), "media_type": JobType.VIDEO, "media_info": {"duration": round(media_info.video_duration)}}
+		return {"local_media_path": str(path), "canonical_name": self.extract_canonical_name(media_info), \
+			"media_type": JobType.VIDEO, "media_info": {"duration": round(media_info.video_duration)}}
 
-	def download_photo(self, url: str) -> dict:
+	def download_photo(self, url: str, media_info: Media) -> dict:
 		path = str(self._download_hndlr(self.cl.photo_download_by_url, url, folder='/tmp'))
 		path_lowered = path.lower()
 		if ".webp" in path_lowered:
 			path = InstagramScraper.convert_webp_to_png(path)
 		if ".heic" in path_lowered:
 			path = InstagramScraper.convert_heic_to_png(path)
-		return {"local_media_path": path, "media_type": JobType.IMAGE}
+		return {"local_media_path": path, "canonical_name": self.extract_canonical_name(media_info), "media_type": JobType.IMAGE}
 	
 	def download_story(self, story_info: Story) -> dict:
 		path, media_type, media_info = "", JobType.UNKNOWN, {}
@@ -236,20 +237,33 @@ class InstagramScraper(ScraperAbstract):
 
 		return {"media_type": JobType.COLLECTION, "save_items": True, "items": chunks}
 
-	def download_album(self, media_info: dict) -> dict:
+	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, media.pk)
 				if media.media_type == 1: # photo
-					chunk.append(self.download_photo(url=_media_info.thumbnail_url))
+					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}
 
+	def extract_canonical_name(self, media: Media) -> str:
+		ret = ""
+		try:
+			if media.title:
+				ret = media.title
+			if media.caption_text:
+				ret += "\n" + media.caption_text
+		except Exception as e:
+			logging.warning("Failed to extract canonical media name!")
+			logging.exception(e)
+
+		return ret
+
 	def download(self, job: DownloadJob) -> Optional[list[dict]]:
 		res = []
 		while True:
@@ -261,7 +275,7 @@ class InstagramScraper(ScraperAbstract):
 					if media_info.media_type == 2 and media_info.product_type == "clips": # Reels
 						res.append(self.download_video(url=media_info.video_url, media_info=media_info))
 					elif media_info.media_type == 1: # Photo
-						res.append(self.download_photo(url=media_info.thumbnail_url))
+						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))
 				elif scrap_type == "story":

{warp_beacon-2.3.13 → warp_beacon-2.3.15}/warp_beacon/telegram/bot.py

@@ -257,7 +257,6 @@ class Bot(object):
 					args["duration"] = round(job.media_info["duration"])
 					args["title"] = job.canonical_name
 					args["caption"] = self.build_signature_caption(job)
-				#args["file_name"] = "%s%s" % (job.canonical_name, os.path.splitext(job.local_media_path)[-1]),
 		elif job.media_type == JobType.ANIMATION:
 			if job.tg_file_id:
 				if job.placeholder_message_id:

{warp_beacon-2.3.13 → warp_beacon-2.3.15}/warp_beacon/telegram/utils.py

@@ -71,19 +71,19 @@ class Utils(object):
 
 	@staticmethod
 	def extract_message_author(message: Message) -> str:
-		if message.from_user:
-			if message.from_user.username:
-				return message.from_user.username
-			if message.from_user.first_name:
-				return message.from_user.first_name
-			if message.from_user.id:
-				return str(message.from_user.mention(style=enums.ParseMode.HTML))
-		if message.sender_chat:
-			if message.sender_chat.username:
-				return message.sender_chat.username
-			if message.sender_chat.title:
-				return message.sender_chat.title
-		return ''
+		#if message.from_user:
+		#	if message.from_user.username:
+		#		return message.from_user.username
+		#	if message.from_user.first_name:
+		#		return message.from_user.first_name
+		#	if message.from_user.id:
+		return str(message.from_user.mention(style=enums.ParseMode.HTML))
+		#if message.sender_chat:
+		#	if message.sender_chat.username:
+		#		return message.sender_chat.username
+		#	if message.sender_chat.title:
+		#		return message.sender_chat.title
+		#return ''
 
 	@staticmethod
 	def compute_leftover(urls: list, message: str) -> str:
@@ -107,6 +107,10 @@ class Utils(object):
 	@staticmethod
 	async def handle_mentions(chat_id: int, client: Client, message: str) -> str:
 		try:
+			mentions = Utils.mention_re.findall(message)
+			if not mentions:
+				return message
+
 			logging.info("Processing chat_id: '%s'", str(chat_id))
 			chat = await client.get_chat(chat_id)
 			chat_id = chat.id
@@ -118,7 +122,6 @@ class Utils(object):
 
 			username = ''
 			members = [member async for member in client.get_chat_members(chat_id)]
-			mentions = Utils.mention_re.findall(message)
 			for mention in mentions:
 				username = mention[1:].strip()
 				if username:

{warp_beacon-2.3.13 → warp_beacon-2.3.15/warp_beacon.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: warp_beacon
-Version: 2.3.13
+Version: 2.3.15
 Summary: Telegram bot for expanding external media links
 Home-page: https://github.com/sb0y/warp_beacon
 Author: Andrey Bagrintsev

warp_beacon-2.3.13/warp_beacon/__version__.py

@@ -1,2 +0,0 @@
-__version__ = "2.3.13"
-