warp-beacon 2.6.86__tar.gz → 2.6.88__tar.gz

{warp_beacon-2.6.86/warp_beacon.egg-info → warp_beacon-2.6.88}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: warp_beacon
-Version: 2.6.86
+Version: 2.6.88
 Summary: Telegram bot for expanding external media links
 Home-page: https://github.com/sb0y/warp_beacon
 Author: Andrey Bagrintsev
@@ -241,6 +241,7 @@ Requires-Dist: yt_dlp
 Requires-Dist: pydub
 Requires-Dist: SpeechRecognition
 Requires-Dist: playwright
+Requires-Dist: fake-useragent
 Dynamic: author
 Dynamic: home-page
 Dynamic: license-file

{warp_beacon-2.6.86 → warp_beacon-2.6.88}/pyproject.toml

@@ -29,7 +29,8 @@ dependencies = [
 	"yt_dlp",
 	"pydub",
 	"SpeechRecognition",
-	"playwright"
+	"playwright",
+	"fake-useragent"
 ]
 keywords = ["bot", "telegram", "instagram", "export"]
 classifiers = [

warp_beacon-2.6.88/warp_beacon/__version__.py

@@ -0,0 +1,2 @@
+__version__ = "2.6.88"
+

{warp_beacon-2.6.86 → warp_beacon-2.6.88}/warp_beacon/scheduler/instagram_human.py

@@ -17,7 +17,9 @@ class InstagramHuman(object):
 		self.operations_count = 0
 
 	def watch_content(self, media: list) -> None:
-		for m in media[:random.randint(1, 15)]:
+		if not media:
+			return
+		for m in media[:random.randint(1, len(media))]:
 			try:
 				logging.info("Wathing content with pk '%s'", str(m.pk))
 				content = self.scrapler.cl.media_info_v1(m.pk)
@@ -30,7 +32,7 @@ class InstagramHuman(object):
 
 	def scroll_content(self, last_pk: int) -> None:
 		timeline_initialized = False
-		if random.random() > 0.7:
+		if random.random() > 0.5:
 			timeline_initialized = True
 			self.scrapler.timeline_cursor = self.scrapler.download_hndlr(self.scrapler.cl.get_timeline_feed, reason="cold_start_fetch")
 			logging.info("Starting to watch related reels with media_pk '%d'", last_pk)
@@ -38,7 +40,7 @@ class InstagramHuman(object):
 			self.operations_count += 1
 			self.watch_content(media)
 		
-		if random.random() > 0.9:
+		if random.random() > 0.7:
 			time.sleep(random.uniform(2, 20))
 			if not timeline_initialized:
 				self.scrapler.timeline_cursor = self.scrapler.download_hndlr(self.scrapler.cl.get_timeline_feed, reason="cold_start_fetch")
@@ -75,7 +77,7 @@ class InstagramHuman(object):
 				self.scrapler.download_hndlr(self.scrapler.cl.notification_like_and_comment_on_photo_user_tagged, "everyone")
 				self.operations_count += 1
 				self.random_pause()
-			if random.random() > 0.5:
+			if random.random() > 0.2:
 				logging.info("Simulation updating reels tray feed ...")
 				self.scrapler.download_hndlr(self.scrapler.cl.get_reels_tray_feed, "pull_to_refresh")
 				self.operations_count += 1
@@ -98,7 +100,7 @@ class InstagramHuman(object):
 				self.random_pause()
 			if random.random() > 0.4:
 				logging.info("Watching reels ...")
-				reels = self.scrapler.download_hndlr(self.scrapler.cl.reels)
+				reels = self.scrapler.download_hndlr(self.scrapler.cl.reels, amount=random.randint(4, 15))
 				self.operations_count += 1
 				self.watch_content(reels)
 				self.random_pause()
@@ -126,11 +128,11 @@ class InstagramHuman(object):
 				self.random_pause()
 			if random.random() > 0.4:
 				logging.info("Watching reels ...")
-				reels = self.scrapler.download_hndlr(self.scrapler.cl.reels)
+				reels = self.scrapler.download_hndlr(self.scrapler.cl.reels, amount=random.randint(4, 15))
 				self.operations_count += 1
 				self.watch_content(reels)
 				self.random_pause()
-			if random.random() > 0.6:
+			if random.random() > 0.4:
 				logging.info("Simulation profile view ...")
 				self.profile_view()
 				self.random_pause()
@@ -145,9 +147,9 @@ class InstagramHuman(object):
 				self.scrapler.download_hndlr(self.scrapler.cl.direct_active_presence)
 				self.operations_count += 1
 				self.random_pause(short=True)
-			if random.random() > 0.8:
+			if random.random() > 0.5:
 				logging.info("Watching reels ...")
-				reels = self.scrapler.download_hndlr(self.scrapler.cl.reels)
+				reels = self.scrapler.download_hndlr(self.scrapler.cl.reels, amount=random.randint(4, 15))
 				self.operations_count += 1
 				self.watch_content(reels)
 				self.random_pause()
@@ -179,14 +181,14 @@ class InstagramHuman(object):
 				#self.scrapler.download_hndlr(self.scrapler.cl.user_info, target_user_id)
 				self.scrapler.download_hndlr(self.scrapler.cl.user_info_v1, target_user_id)
 				self.operations_count += 1
-				time.sleep(random.uniform(2, 5))
+				self.random_pause()
 			elif isinstance(random_friend, str):
 				target_user_id = self.scrapler.download_hndlr(self.scrapler.cl.user_id_from_username, random_friend)
 				logging.info("user_info with target_user_id = '%s' ...", target_user_id)
 				#self.scrapler.download_hndlr(self.scrapler.cl.user_info, target_user_id)
 				self.scrapler.download_hndlr(self.scrapler.cl.user_info_v1, target_user_id)
 				self.operations_count += 1
-				time.sleep(random.uniform(2, 5))
+				self.random_pause()
 			
 			if random.random() > 0.5:
 				logging.info("Checking direct ...")
@@ -202,7 +204,7 @@ class InstagramHuman(object):
 			
 			if random.random() > 0.5:
 				logging.info("user_medias with target_user_id = '%s' ...", target_user_id)
-				self.scrapler.download_hndlr(self.scrapler.cl.user_medias_v1, target_user_id, amount=random.randint(1, 5))
+				self.scrapler.download_hndlr(self.scrapler.cl.user_medias_v1, target_user_id, amount=random.randint(1, 10))
 				self.operations_count += 1
 				self.random_pause()
 		except Exception as e:

{warp_beacon-2.6.86 → warp_beacon-2.6.88}/warp_beacon/scheduler/scheduler.py

@@ -126,7 +126,7 @@ class IGScheduler(object):
 
 	def handle_time_planning(self) -> None:
 		if int(self.state.get("remaining", 0)) <= 0:
-			self.state["remaining"] = randrange(9292, 26200)
+			self.state["remaining"] = randrange(5292, 12253)
 
 	def do_work(self) -> None:
 		logging.info("Scheduler thread started ...")

{warp_beacon-2.6.86 → warp_beacon-2.6.88}/warp_beacon/scraper/__init__.py

@@ -130,7 +130,7 @@ class AsyncDownloader(object):
 								proxy = selector.get_current_proxy()
 							if job.job_origin is Origin.INSTAGRAM:
 								from warp_beacon.scraper.instagram.instagram import InstagramScraper
-								if not job.scroll_content and selector.get_ig_request_count() >= int(os.environ.get("IG_REQUESTS_PER_ACCOUNT", default="10")):
+								if not job.scroll_content and selector.get_ig_request_count() >= int(os.environ.get("IG_REQUESTS_PER_ACCOUNT", default="20")):
 									logging.info("The account request limit has been reached. Selecting the next account.")
 									selector.reset_ig_request_count()
 									selector.next()
@@ -164,7 +164,7 @@ class AsyncDownloader(object):
 										break
 									if job.session_validation and job.job_origin in (Origin.INSTAGRAM, Origin.YOUTUBE):
 										if job.job_origin is Origin.INSTAGRAM:
-											if selector.get_ig_request_count() >= int(os.environ.get("IG_REQUESTS_PER_ACCOUNT", default="10")):
+											if selector.get_ig_request_count() >= int(os.environ.get("IG_REQUESTS_PER_ACCOUNT", default="20")):
 												logging.info("The account request limit has been reached. Selecting the next account.")
 												selector.reset_ig_request_count()
 												selector.next()

{warp_beacon-2.6.86 → warp_beacon-2.6.88}/warp_beacon/scraper/instagram/instagram.py

@@ -31,6 +31,7 @@ from warp_beacon.jobs.download_job import DownloadJob
 from warp_beacon.telegram.utils import Utils
 from warp_beacon.scraper.instagram.wb_instagrapi import WBClient
 from warp_beacon.telegram.types import ReportType
+from warp_beacon.scraper.utils import ScraperUtils
 
 INST_SESSION_FILE_TPL = "/var/warp_beacon/inst_session_account_%d.json"
 
@@ -61,10 +62,7 @@ class InstagramScraper(ScraperAbstract):
 			"Accept": "*/*",
 			"Accept-Encoding": "gzip, deflate, br",
 			"Accept-Language": "en-US,en;q=0.9",
-			"User-Agent": (
-				"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
-				"(KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36"
-			)
+			"User-Agent": ScraperUtils.get_ua()
 		})
 		self.cl.set_progress_callback(self.download_progress)
 
@@ -96,7 +94,7 @@ class InstagramScraper(ScraperAbstract):
 			"uuid": uuids.get("uuid", self.cl.generate_uuid()),
 			"client_session_id": self.client_session_id,
 			"advertising_id": uuids.get("advertising_id", self.cl.generate_uuid()),
-			"device_id": uuids.get("device_id", self.cl.generate_uuid())
+			"device_id": uuids.get("device_id", self.cl.generate_android_device_id())
 		})
 
 	def safe_write_session(self) -> None:

{warp_beacon-2.6.86 → warp_beacon-2.6.88}/warp_beacon/scraper/instagram/wb_instagrapi.py

@@ -7,6 +7,8 @@ import requests
 from instagrapi import Client
 from instagrapi.exceptions import VideoNotDownload
 
+from warp_beacon.scraper.utils import ScraperUtils
+
 class WBClient(Client):
 	"""
 	patched instagrapi
@@ -17,10 +19,7 @@ class WBClient(Client):
 		self.session = requests.Session()
 		# may be I should remove '"Sec-Fetch-*", "Upgrade-Insecure-Requests", "DNT"' ?
 		self.session.headers.update({
-			"User-Agent": (
-				"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
-				"(KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36"
-			),
+			"User-Agent": ScraperUtils.get_ua(),
 			"Accept": (
 				"text/html,application/xhtml+xml,application/xml;"
 				"q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8"
@@ -29,12 +28,12 @@ class WBClient(Client):
 			"Accept-Encoding": "gzip, deflate, br",
 			"Referer": "https://www.instagram.com/",
 			"Connection": "keep-alive",
-			"Sec-Fetch-Site": "same-origin",
-			"Sec-Fetch-Mode": "navigate",
-			"Sec-Fetch-User": "?1",
-			"Sec-Fetch-Dest": "document",
-			"Upgrade-Insecure-Requests": "1",
-			"DNT": "1",
+			#"Sec-Fetch-Site": "same-origin",
+			#"Sec-Fetch-Mode": "navigate",
+			#"Sec-Fetch-User": "?1",
+			#"Sec-Fetch-Dest": "document",
+			#"Upgrade-Insecure-Requests": "1",
+			#"DNT": "1",
 		})
 		self.essential_params = {"oe", "oh", "_nc_ht", "_nc_cat", "_nc_oc", "_nc_ohc", "_nc_gid"}
 

warp_beacon-2.6.88/warp_beacon/scraper/utils.py

@@ -0,0 +1,20 @@
+import logging
+
+from fake_useragent import UserAgent
+
+class ScraperUtils(object):
+	@staticmethod
+	def get_ua_dict(browsers: list = ['Facebook', 'Android'], platforms: list = ['mobile', 'tablet'], os: list =['Android', 'iOS']) -> dict:
+		random_client = None
+		try:
+			ua = UserAgent(browsers=browsers, platforms=platforms, os=os)
+			random_client = ua.getRandom
+			logging.info("Select random UA: %s", random_client)
+		except Exception as e:
+			logging.warning("Exception occurrd while generating random client UA!", exc_info=e)
+			random_client = {'useragent': 'Mozilla/5.0 (Linux; Android 14; SM-S911B Build/UP1A.231005.007; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/133.0.6943.117 Mobile Safari/537.36 [FB_IAB/FB4A;FBAV/502.0.0.66.79;IABMV/1;]', 'percent': 0.017937771404345798, 'type': 'mobile', 'device_brand': 'Samsung', 'browser': 'Facebook', 'browser_version': '502.0.0', 'browser_version_major_minor': 502.0, 'os': 'Android', 'os_version': '14', 'platform': 'Linux aarch64'}
+		return random_client
+
+	@staticmethod
+	def get_ua(browsers: list = ['Facebook', 'Android'], platforms: list = ['mobile', 'tablet'], os: list =['Android', 'iOS']) -> str:
+		return ScraperUtils.get_ua_dict(browsers=browsers, platforms=platforms, os=os)["useragent"]

{warp_beacon-2.6.86 → warp_beacon-2.6.88}/warp_beacon/scraper/youtube/abstract.py

@@ -29,6 +29,7 @@ from warp_beacon.scraper.abstract import ScraperAbstract
 from warp_beacon.scraper.exceptions import (BadProxy, TimeOut, Unavailable,
 											extract_exception_message)
 from warp_beacon.yt_auth import YtAuth
+from warp_beacon.scraper.utils import ScraperUtils
 
 class YoutubeAbstract(ScraperAbstract):
 	DOWNLOAD_DIR = "/tmp"
@@ -226,7 +227,10 @@ class YoutubeAbstract(ScraperAbstract):
 		return ret_val
 
 	def yt_on_progress(self, stream: Stream, chunk: bytes, bytes_remaining: int) -> None:
-		total_size = stream.filesize or stream.filesize_approx
+		total_size = int(stream.filesize or stream.filesize_approx or 0)
+		if not total_size:
+			logging.warning("[Download worker]: total_size is '%d'", total_size)
+			return
 		bytes_downloaded = total_size - bytes_remaining
 		percentage_of_completion = bytes_downloaded / (total_size or 1) * 100
 		if total_size == 0 or percentage_of_completion >= self._download_progress_threshold:
@@ -286,6 +290,28 @@ class YoutubeAbstract(ScraperAbstract):
 				yt_opts["proxies"] = self.build_proxies(proxy_dsn)
 		return YouTube(**yt_opts)
 	
+	def yt_dlp_on_progress(self, params: dict) -> None:
+		if params.get("status", "") == "downloading":
+			total_size = int(params.get("total_bytes") or params.get("total_bytes_estimate") or 0)
+			if not total_size or total_size < 0:
+				logging.warning("[Download worker][yt_dlp]: total_size is '%d'", total_size)
+				return
+			bytes_downloaded = int(params.get("downloaded_bytes", 0))
+			percentage_of_completion = bytes_downloaded / (total_size or 1) * 100
+			if total_size == 0 or percentage_of_completion >= self._download_progress_threshold:
+				msg = {
+					"action": "report_download_status",
+					"current": bytes_downloaded,
+					"total": total_size,
+					"message_id": self.job.placeholder_message_id,
+					"chat_id": self.job.chat_id,
+					"completed": percentage_of_completion >= 100
+				}
+				self.status_pipe.send(msg)
+				logging.debug("[Download worker][yt_dlp] Downloaded %d%%", percentage_of_completion)
+				if total_size > 0:
+					self._download_progress_threshold += 20
+
 	def build_yt_dlp(self, timeout: int = 60) -> yt_dlp.YoutubeDL:
 		auth_data = {}
 		with open(self.YT_SESSION_FILE % self.account_index, 'r', encoding="utf-8") as f:
@@ -297,9 +323,24 @@ class YoutubeAbstract(ScraperAbstract):
 			'format': 'bestvideo+bestaudio/best',
 			'merge_output_format': 'mp4',
 			'noplaylist': True,
-			'tv_auth': auth_data
+			'progress_hooks': [self.yt_dlp_on_progress],
+			'http_headers': {
+				"Accept-Language": "en-US,en;q=0.9",
+				'User-Agent': ScraperUtils.get_ua(
+					browsers=["Google", "Chrome", "Firefox"],
+					os=["Windows", "Linux", "Ubuntu", "Chrome OS", "Mac OS X"],
+					platforms=["desktop"]
+				)
+			}
 		}
 
+		if auth_data and auth_data.get("access_token", None):
+			ydl_opts["http_headers"]["Authorization"] = f'Bearer {auth_data["access_token"]}'
+
+		yt_dlp_cookies_file = os.environ.get("YT_DLP_COOKIES_FILE", default="/var/warp_beacon/yt_dlp_cookies.txt")
+		if yt_dlp_cookies_file and os.path.exists(yt_dlp_cookies_file):
+			ydl_opts['cookiefile'] = yt_dlp_cookies_file
+
 		if self.proxy:
 			proxy_dsn = self.proxy.get("dsn", "")
 			logging.info("Using proxy DSN '%s'", proxy_dsn)

{warp_beacon-2.6.86 → warp_beacon-2.6.88/warp_beacon.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: warp_beacon
-Version: 2.6.86
+Version: 2.6.88
 Summary: Telegram bot for expanding external media links
 Home-page: https://github.com/sb0y/warp_beacon
 Author: Andrey Bagrintsev
@@ -241,6 +241,7 @@ Requires-Dist: yt_dlp
 Requires-Dist: pydub
 Requires-Dist: SpeechRecognition
 Requires-Dist: playwright
+Requires-Dist: fake-useragent
 Dynamic: author
 Dynamic: home-page
 Dynamic: license-file

{warp_beacon-2.6.86 → warp_beacon-2.6.88}/warp_beacon.egg-info/requires.txt

@@ -15,3 +15,4 @@ yt_dlp
 pydub
 SpeechRecognition
 playwright
+fake-useragent

warp_beacon-2.6.86/warp_beacon/__version__.py

@@ -1,2 +0,0 @@
-__version__ = "2.6.86"
-

warp_beacon-2.6.86/warp_beacon/scraper/utils.py

@@ -1,4 +0,0 @@
-#import logging
-
-class Utils(object):
-	pass