warp-beacon 2.7.16__tar.gz → 2.7.18__tar.gz

{warp_beacon-2.7.16/warp_beacon.egg-info → warp_beacon-2.7.18}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: warp_beacon
-Version: 2.7.16
+Version: 2.7.18
 Summary: Telegram bot for expanding external media links
 Home-page: https://github.com/sb0y/warp_beacon
 Author: Andrey Bagrintsev

warp_beacon-2.7.18/warp_beacon/__version__.py

@@ -0,0 +1,2 @@
+__version__ = "2.7.18"
+

{warp_beacon-2.7.16 → warp_beacon-2.7.18}/warp_beacon/scheduler/instagram_human.py

@@ -44,6 +44,7 @@ class InstagramHuman(object):
 							#self.scrapler.cl.media_like(media_id)
 							self.scrapler.cl.media_comments(media_id)
 							self.operations_count += 1
+
 							self.random_pause(short=True)
 						except Exception as e:
 							logging.warning("Failed to see comments to media '%s'", media_id, exc_info=e)
@@ -70,10 +71,14 @@ class InstagramHuman(object):
 			return
 
 		seen = []
+		explore_user = None
 		for m in stories[:random.randint(1, len(stories))]:
 			try:
 				logging.info("Wathing story with pk '%s'", str(m.id))
 				seen.append(str(m.id))
+				if random.random() > 0.5:
+					explore_user = m.user
+					break
 				self.random_pause()
 			except Exception as e:
 				logging.warning("Exception while watching content", exc_info=e)
@@ -86,17 +91,22 @@ class InstagramHuman(object):
 			except Exception as e:
 				logging.warning("Failed to mark seen watched watch stories!", exc_info=e)
 
+		if explore_user:
+			self.explore_profile(explore_user)
+
 	def watch_content(self, media: list) -> None:
 		if not media:
 			return
+		explore_user = None
 		seen = []
 		for m in media[:random.randint(1, len(media))]:
 			try:
 				logging.info("Watching content with pk '%s'", str(m.id))
-				#content = self.scrapler.cl.media_info_v1(m.pk)
 				seen.append(str(m.id))
 				logging.info("Watched content with id '%s'", str(m.id))
-				#self.operations_count += 1
+				if random.random() > 0.4:
+					explore_user = m.user
+					break
 				self.random_pause()
 			except Exception as e:
 				logging.warning("Exception while watching content")
@@ -107,12 +117,14 @@ class InstagramHuman(object):
 		except Exception as e:
 			logging.warning("Failed to mark seen watched videos!", exc_info=e)
 
+		if explore_user:
+			self.explore_profile(explore_user)
+
 	def scroll_content(self, last_pk: int) -> None:
 		timeline_initialized = False
 		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")
-			self.scrapler.timeline_cursor = self.browse_timeline()
+			self.browse_timeline()
 			logging.info("Starting to watch related reels with media_pk '%d'", last_pk)
 			media = self.scrapler.download_hndlr(self.scrapler.cl.reels, amount=random.randint(4, 10), last_media_pk=last_pk)
 			self.operations_count += 1
@@ -121,8 +133,7 @@ class InstagramHuman(object):
 		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")
-				self.scrapler.timeline_cursor = self.browse_timeline()
+				self.browse_timeline()
 			logging.info("Starting to explore reels with media_pk '%d'", last_pk)
 			media = self.scrapler.download_hndlr(self.scrapler.cl.explore_reels, amount=random.randint(4, 10), last_media_pk=last_pk)
 			self.operations_count += 1
@@ -146,14 +157,14 @@ class InstagramHuman(object):
 			logging.info("Starting morning activity simulation")
 			#self.scrapler.timeline_cursor = self.scrapler.download_hndlr(self.scrapler.cl.get_timeline_feed, "pull_to_refresh", self.scrapler.timeline_cursor.get("next_max_id"))
 			#self.operations_count += 1
-			self.scrapler.timeline_cursor = self.browse_timeline()
+			self.browse_timeline()
 			time.sleep(random.uniform(3, 7))
 			if random.random() > 0.5:
 				self.check_direct()
-			if random.random() > 0.6:
-				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() > 0.6:
+			#	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() > 0.2:
 				logging.info("Simulation updating reels tray feed ...")
 				self.scrapler.download_hndlr(self.scrapler.cl.get_reels_tray_feed, "pull_to_refresh")
@@ -200,11 +211,11 @@ class InstagramHuman(object):
 			time.sleep(random.uniform(2, 5))
 			if random.random() > 0.5:
 				self.check_direct()
-			if random.random() > 0.6:
-				logging.info("Checking notifications, tags ...")
-				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() > 0.6:
+			#	logging.info("Checking notifications, tags ...")
+			#	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() > 0.4:
 				self.watch_stories()
 				self.random_pause()
@@ -269,6 +280,20 @@ class InstagramHuman(object):
 				logging.warning("Failed to read thread %s", thread.id)
 				logging.exception(e)
 
+	def explore_profile(self, user: UserShort) -> None:
+		try:
+			logging.info("Exploring user profile '%s'", user.username)
+			user_id = self.scrapler.download_hndlr(self.scrapler.cl.user_id_from_username, user.username)
+			self.operations_count += 1
+			if user_id:
+				user_medias = self.scrapler.download_hndlr(self.scrapler.cl.user_medias, user_id, amount=random.randint(5, 15), sleep=random.randint(3, 7))
+				self.operations_count += 1
+				if user_medias:
+					self.random_pause(short=True)
+					self.watch_content(user_medias)
+		except Exception as e:
+			logging.warning("Failed to explore user profile with username '%s'", user.username, exc_info=e)
+
 	def profile_view(self) -> None:
 		try:
 			logging.info("profile_view ...")
@@ -302,11 +327,11 @@ class InstagramHuman(object):
 			if random.random() > 0.5:
 				self.check_direct()
 
-			if random.random() > 0.3:
-				logging.info("Checking notifications, tags ...")
-				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() > 0.3:
+			#	logging.info("Checking notifications, tags ...")
+			#	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:
 				logging.info("user_medias with target_user_id = '%s' ...", target_user_id)

{warp_beacon-2.7.16 → warp_beacon-2.7.18}/warp_beacon/scraper/instagram/wb_instagrapi.py

@@ -1,16 +1,18 @@
 import logging
-from typing import Callable
+from typing import Callable, List
 from copy import deepcopy
 from urllib.parse import urlparse, parse_qs, urlencode, urlunparse
 from pathlib import Path
+import time
 import requests
 
 from instagrapi import Client
-from instagrapi.types import Media
+from instagrapi.types import Media, User
 from instagrapi.exceptions import (
-	ClientError,
-	ClientLoginRequired,
-	VideoNotDownload
+	#ClientError,
+	#ClientLoginRequired,
+	VideoNotDownload,
+	PrivateError
 )
 
 from warp_beacon.scraper.utils import ScraperUtils
@@ -190,4 +192,118 @@ class WBClient(Client):
 			self._medias_cache[media_pk] = media
 		return deepcopy(
 			self._medias_cache[media_pk]
-		)  # return copy of cache (dict changes protection)
+		)  # return copy of cache (dict changes protection)
+	
+	def user_info_by_username(self, username: str, use_cache: bool = True) -> User:
+		"""
+		Get user object from username
+
+		Parameters
+		----------
+		username: str
+			User name of an instagram account
+		use_cache: bool, optional
+			Whether or not to use information from cache, default value is True
+
+		Returns
+		-------
+		User
+			An object of User type
+		"""
+		username = str(username).lower()
+		if not use_cache or username not in self._usernames_cache:
+			user = self.user_info_by_username_v1(username)
+			self._users_cache[user.pk] = user
+			self._usernames_cache[user.username] = user.pk
+		return self.user_info(self._usernames_cache[username])
+	
+	def user_info(self, user_id: str, use_cache: bool = True) -> User:
+		"""
+		Get user object from user id
+
+		Parameters
+		----------
+		user_id: str
+			User id of an instagram account
+		use_cache: bool, optional
+			Whether or not to use information from cache, default value is True
+
+		Returns
+		-------
+		User
+			An object of User type
+		"""
+		user_id = str(user_id)
+		if not use_cache or user_id not in self._users_cache:
+			user = self.user_info_v1(user_id)
+			self._users_cache[user_id] = user
+			self._usernames_cache[user.username] = user.pk
+		return deepcopy(
+			self._users_cache[user_id]
+		)  # return copy of cache (dict changes protection)
+	
+	def user_medias(self, user_id: str, amount: int = 0, sleep: int = 0) -> List[Media]:
+		"""
+		Get a user's media
+
+		Parameters
+		----------
+		user_id: str
+		amount: int, optional
+			Maximum number of media to return, default is 0 (all medias)
+		sleep: int, optional
+			Timeout between page iterations
+
+		Returns
+		-------
+		List[Media]
+			A list of objects of Media
+		"""
+		amount = int(amount)
+		user_id = int(user_id)
+		sleep = int(sleep)
+		# User may been private, attempt via Private API
+		# (You can check is_private, but there may be other reasons,
+		#  it is better to try through a Private API)
+		medias = self.user_medias_v1(user_id, amount, sleep)
+		return medias
+	
+	def user_medias_v1(self, user_id: str, amount: int = 0, sleep: int = 0) -> List[Media]:
+		"""
+		Get a user's media by Private Mobile API
+
+		Parameters
+		----------
+		user_id: str
+		amount: int, optional
+			Maximum number of media to return, default is 0 (all medias)
+
+		Returns
+		-------
+		List[Media]
+			A list of objects of Media
+		"""
+		amount = int(amount)
+		user_id = int(user_id)
+		medias = []
+		next_max_id = ""
+		while True:
+			try:
+				medias_page, next_max_id = self.user_medias_paginated_v1(
+					user_id, amount, end_cursor=next_max_id
+				)
+			except PrivateError as e:
+				raise e
+			except Exception as e:
+				self.logger.exception(e)
+				break
+			medias.extend(medias_page)
+			if not next_max_id:
+				break
+			if amount and len(medias) >= amount:
+				break
+			if sleep:
+				time.sleep(sleep)
+		if amount:
+			medias = medias[:amount]
+		return medias

{warp_beacon-2.7.16 → warp_beacon-2.7.18/warp_beacon.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: warp_beacon
-Version: 2.7.16
+Version: 2.7.18
 Summary: Telegram bot for expanding external media links
 Home-page: https://github.com/sb0y/warp_beacon
 Author: Andrey Bagrintsev

warp_beacon-2.7.16/warp_beacon/__version__.py

@@ -1,2 +0,0 @@
-__version__ = "2.7.16"
-