instagram-posts-scraper 0.0.1__tar.gz

instagram_posts_scraper-0.0.1/LICENSE

@@ -0,0 +1,19 @@
+Copyright (c) <2025> <FaustRen>
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

instagram_posts_scraper-0.0.1/PKG-INFO

@@ -0,0 +1,104 @@
+Metadata-Version: 2.2
+Name: instagram-posts-scraper
+Version: 0.0.1
+Summary: Implement Instagram Posts Scraper for post data retrieval
+Home-page: https://github.com/FaustRen/instagram_posts_scraper
+Author: FaustRen
+Author-email: faustren1z@gmail.com
+License: MIT
+Classifier: Programming Language :: Python :: 3.11
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: requires-python
+Dynamic: summary
+
+# Instagram Posts Scraper
+
+InstagramPostsScraper is a Python library for collect instagram users' data.
+
+The data obtained by web crawlers is not real-time data, but rather data from a specific point in time on the same day.
+
+## Installation
+
+Use the package manager [pip](https://pip.pypa.io/en/stable/) to install instagram_posts_scraper.
+
+```bash
+beautifulsoup4==4.13.3
+cloudscraper==1.2.71
+pandas==2.2.3
+pytz==2025.1
+```
+
+
+## Usage - Sample
+
+```python
+from instagram_posts_scraper import InstaPeriodScraper
+
+
+target_info = {"username": "joemanweng", "days_limit":5}
+ig_posts_scraper = InstaPeriodScraper()
+res = ig_posts_scraper.get_posts(target_info=target_info)
+
+```
+
+## Result Sample
+
+```
+{
+    'profile': {
+        'introduction': ['台灣Youtuber\n⬇️專屬團購連結⬇️'],
+        'counts_of_posts': '1392',
+        'followers': '581198',
+        'followings': '859'
+    },
+    'account_status': 'public',
+    'updated_at': datetime.datetime(2025, 2, 9, 1, 28, 8, 793770, tzinfo=<DstTzInfo 'Asia/Taipei' CST+8:00:00 STD>),
+    'data': [
+        {
+            'type': 'igtv',
+            'sum': '《靈能的挑戰》參賽者後台花絮露出👀\n老師們比賽中較勁，但私下娛樂竟是互相算命！\n不知道有沒有先算出冠軍了（吃瓜）\n預祝大家新年快樂~~\n*節目中個人言論不代表本節目立場*\n﹏﹏﹏﹏﹏﹏﹏﹏﹏﹏﹏﹏\n#靈能的挑戰\xa0#Joeman\xa0#東森超視33頻道\n全台第一檔靈能競賽節目\n📺️ 全季觀看平台｜\n🎥 Joeman YT 頻道觀看全季\n🎥 東森超視 33 頻道已播出完畢\n﹋﹋﹋﹋﹋﹋﹋﹋﹋﹋﹋﹋\n#玄學 #易經 #塔羅 #通靈 #占星',
+            'sum_pure': '《靈能的挑戰》參賽者後台花絮露出 老師們比賽中較勁，但私下娛樂竟是互相算命！不知道有沒有先算出冠軍了（吃瓜）預祝大家新年快樂~~*節目中個人言論不代表本節目立場*﹏﹏﹏﹏﹏﹏﹏﹏﹏﹏﹏﹏#靈能的挑戰\xa0#Joeman\xa0#東森超視33頻道全台第一檔靈能競賽節目 ️ 全季觀看平台｜ Joeman YT 頻道觀看全季 東森超視 33 頻道已播出完畢﹋﹋﹋﹋﹋﹋﹋﹋﹋﹋﹋﹋#玄學 #易經 #塔羅 #通靈 #占星',
+            'shortcode': '6741582137415658464423',
+            'time': 1737885600,
+            'ftime': '13 days ago',
+            'count_like': 2442,
+            'count_comment': 6,
+            'count_like_pure': '2,442',
+            'count_comment_pure': '6',
+            'thum': 'https://scontent-fra3-1.cdninstagram.com/v/t51.2885-15/474907887_1129543381888335_8766424988966118915_n.jpg?stp=c0.248.640.640a_dst-jpg_e15_tt6&_nc_ht=scontent-fra3-1.cdninstagram.com&_nc_cat=103&_nc_ohc=YPiycXP_teMQ7kNvgF-DLaF&_nc_gid=3e3699c22b4246b98fb450d120d9527f&edm=APU89FABAAAA&ccb=7-5&oh=00_AYAb75YGceozAPWzbq4CQQGd_q_XyfKdjdwcKYak3J-pHA&oe=67AD07FF&_nc_sid=bc0c2c',
+            'pic': 'https://scontent-fra3-1.cdninstagram.com/v/t51.2885-15/474907887_1129543381888335_8766424988966118915_n.jpg?stp=dst-jpg_e15_tt6&_nc_ht=scontent-fra3-1.cdninstagram.com&_nc_cat=103&_nc_ohc=YPiycXP_teMQ7kNvgF-DLaF&_nc_gid=3e3699c22b4246b98fb450d120d9527f&edm=APU89FABAAAA&ccb=7-5&oh=00_AYA0qczIKFhJEbukWZRRSUvJJ28iqBuhIXZqRB3EEA450Q&oe=67AD07FF&_nc_sid=bc0c2c',
+            'pic_p': 'https://sp1.piokok.com/p/pt_6741582137415658464423_0_233bd378e8b9a4f088f6c850099951c7.jpg?u=https%3A%2F%2Fscontent-fra3-1.cdninstagram.com%2Fv%2Ft51.2885-15%2F474907887_1129543381888335_8766424988966118915_n.jpg%3Fstp%3Dc0.248.640.640a_dst-jpg_e15_tt6%26_nc_ht%3Dscontent-fra3-1.cdninstagram.com%26_nc_cat%3D103%26_nc_ohc%3DYPiycXP_teMQ7kNvgF-DLaF%26_nc_gid%3D3e3699c22b4246b98fb450d120d9527f%26edm%3DAPU89FABAAAA%26ccb%3D7-5%26oh%3D00_AYAb75YGceozAPWzbq4CQQGd_q_XyfKdjdwcKYak3J-pHA%26oe%3D67AD07FF%26_nc_sid%3Dbc0c2c',
+            'down_pic': 'https://scontent-fra3-1.cdninstagram.com/v/t51.2885-15/474907887_1129543381888335_8766424988966118915_n.jpg?stp=dst-jpg_e15_tt6&_nc_ht=scontent-fra3-1.cdninstagram.com&_nc_cat=103&_nc_ohc=YPiycXP_teMQ7kNvgF-DLaF&_nc_gid=3e3699c22b4246b98fb450d120d9527f&edm=APU89FABAAAA&ccb=7-5&oh=00_AYA0qczIKFhJEbukWZRRSUvJJ28iqBuhIXZqRB3EEA450Q&oe=67AD07FF&_nc_sid=bc0c2c&dl=1',
+            'is_video': True,
+            'video': 'https://scontent-fra3-1.cdninstagram.com/o1/v/t16/f2/m86/AQNbkAdWefxU8OJ015A7RX0oUxLJS-03KKFEbd2ueAbuWXS5jla4AsgRPhGeuuD9HsvVUz0mG5uKwOTWpYhvCVbbIPtxarY3vAIwG7A.mp4?stp=dst-mp4&efg=eyJxZV9ncm91cHMiOiJbXCJpZ193ZWJfZGVsaXZlcnlfdnRzX290ZlwiXSIsInZlbmNvZGVfdGFnIjoidnRzX3ZvZF91cmxnZW4uY2xpcHMuYzIuNzIwLmJhc2VsaW5lIn0&_nc_cat=103&vs=427033163733715_1223826287&_nc_vs=HBksFQIYUmlnX3hwdl9yZWVsc19wZXJtYW5lbnRfc3JfcHJvZC9ERDQ1NERCQUU1RkU4RDA5MzA5NzA2Q0IzODgxRUVBM192aWRlb19kYXNoaW5pdC5tcDQVAALIAQAVAhg6cGFzc3Rocm91Z2hfZXZlcnN0b3JlL0dPcGZUeHgyY1EtV3l3c0VBQjRRdldDeTRZdHFicV9FQUFBRhUCAsgBACgAGAAbABUAACamtPfZ0u%2BTQBUCKAJDMywXQF2QEGJN0vIYEmRhc2hfYmFzZWxpbmVfMV92MREAdf4HAA%3D%3D&_nc_rid=3e36937551&ccb=9-4&oh=00_AYANPnQ7Zlk5Z_6wS0OF1Hn3ttS8vsk-0K6OyM9y8xzM6A&oe=67A925DC&_nc_sid=bc0c2c',
+            'down_video': 'same_as_above'
+        }
+    ]
+}
+
+
+
+
+## Contributing - Sample
+
+comming soon..
+
+## License - Sample
+
+comming soon..
+
+## Tests - cd to tests folder
+coverage run test_crawler.py
+
+coverage html

instagram_posts_scraper-0.0.1/instagram_posts_scraper/example.py

@@ -0,0 +1,10 @@
+# -*- coding: utf-8 -*-
+#%%
+from instagram_posts_scraper.instagram_posts_scraper import InstaPeriodScraper
+
+
+target_info = {"username": "joemanweng", "days_limit":5}
+ig_posts_scraper = InstaPeriodScraper()
+res = ig_posts_scraper.get_posts(target_info=target_info)
+res
+# %%

instagram_posts_scraper-0.0.1/instagram_posts_scraper/file_operation.py

@@ -0,0 +1,28 @@
+# -*- coding: utf-8 -*-.
+import os
+import json
+import pandas as pd
+
+class JsonOperation:
+    @staticmethod
+    def read_config_content():
+        current_directory = os.path.dirname(__file__) + "/resources/config"
+        with open(current_directory, 'r') as file:
+            result = json.load(file)
+        return result
+    
+    @staticmethod
+    def read_start_point():
+        current_directory = os.path.dirname(__file__) + "/resources/start_point_config"
+        with open(current_directory, 'r') as file:
+            result = json.load(file)
+        return result
+
+    
+
+class CsvOperation:
+    @staticmethod
+    def read_kol_csv():
+        current_directory = os.path.dirname(__file__) + "/resources/new_input_scraper.csv"
+        result = pd.read_csv(current_directory)
+        return result

instagram_posts_scraper-0.0.1/instagram_posts_scraper/instagram_posts_scraper.py

@@ -0,0 +1,160 @@
+# -*- coding: utf-8 -*-
+from instagram_posts_scraper.request import *
+from instagram_posts_scraper.parse import *
+from instagram_posts_scraper.utils import *
+from instagram_posts_scraper.scraper import *
+from instagram_posts_scraper.utils.utils import *
+from instagram_posts_scraper.file_operation import *
+
+
+class ScrapedDataManager(object):
+    def __init__(self):
+        pass
+
+
+class InstaPeriodScraper(object):
+    def __init__(self) -> None:
+        self.pixwox_request = PixwoxRequest()
+        self.parser=Parser()
+        self.api_parser=ApiParser()
+        self.scraper=Scraper( 
+            pixwox_request=self.pixwox_request, 
+            parser=self.parser, 
+            api_parser=self.api_parser
+        )
+
+    def check_account_is_public(self):
+        init_response = self.pixwox_request.send_requests(url=self.scraper.init_url)
+        self.profile_soup = self.parser.get_soup(response=init_response)
+        self.userid = self.parser.get_userid(profile_soup=self.profile_soup)
+        self.account_status = get_account_status(userid=self.userid, profile_soup=self.profile_soup)
+        return self.account_status == "public"
+    
+    def get_profile(self):
+        self.followings = self.parser.get_followings(self.profile_soup)
+        self.followers = self.parser.get_followers(self.profile_soup)
+        self.counts_of_posts = self.parser.get_counts_of_posts(self.profile_soup)
+        try:
+            self.introduction = self.parser.get_introduction(self.profile_soup)
+        except:
+            self.introduction = None
+        
+        self.profile_info = {
+            "introduction": self.introduction,
+            "counts_of_posts": self.counts_of_posts,
+            "followers": self.followers,
+            "followings": self.followings,
+        }
+
+    def get_init_api_data(self):
+        init_api_data = self.scraper.get_init_api_data(userid=self.userid)
+        return init_api_data
+    
+    def get_next_api_data(self, next_maxid:str, next_:str,username:str):
+        next_api_data = self.scraper.get_next_api_data(userid=self.userid, next_maxid=next_maxid, next_=next_, username=username)
+        return next_api_data
+
+    def get_private_account_res(self):
+        res = {
+            "profile":{
+                "userid":self.userid,
+                "username":self.target_info["username"],
+                "followers":self.followers,
+                "followings":self.followings,
+                "counts_of_posts":self.counts_of_posts,
+                "introduction":self.introduction
+                },
+            "account_status":self.account_status,
+            "updated_at": get_current_time(timezone="Asia/Taipei"),
+            "data":[]
+        }
+        return res
+
+    def get_missing_account_res(self):
+        res = {
+            "profile":{
+                "userid":None,
+                "username":self.target_info["username"],
+                "followers":None,
+                "followings":None,
+                "counts_of_posts":None,
+                "introduction":None
+                },
+            "account_status":self.account_status,
+            "updated_at": get_current_time(timezone="Asia/Taipei"),
+            "data":[]
+        }
+        return res
+
+    def get_public_account_res(self, scraped_posts, init_api_data):
+        res = {
+            "profile": self.profile_info,
+            "account_status":self.account_status,
+            "updated_at": get_current_time(timezone="Asia/Taipei"),
+            "data":scraped_posts}
+        return res
+
+    # @timeout(300)
+    def get_period_data(self, days_limit:int, init_maxid:str, init_api_data, username):
+        scraped_posts_res = init_api_data["posts"]["items"]
+        next_ = init_api_data["posts"]["next"]
+        next_maxid = init_maxid
+        for rounds in range(days_limit):
+            # Scraped next rounds data
+            next_api_data = self.get_next_api_data(next_maxid=next_maxid, next_=next_, username=username)
+            scraped_posts = next_api_data["posts"]
+            scraped_items = scraped_posts["items"]
+            scraped_posts_res += scraped_items
+            
+            # if get all posts or get target period posts
+            if has_all_data_been_collected(scraped_items=scraped_posts_res, counts_of_posts=self.counts_of_posts) or is_date_exceed_half_year(scraped_items=scraped_items,days_limit=days_limit):
+                return scraped_posts_res
+            
+            elif next_api_data["posts"]["has_next"]: # if there are posts can scrape
+                next_maxid = scraped_posts["maxid"]
+                next_ = scraped_posts["next"]
+                continue
+            else:
+                return scraped_posts_res
+        return scraped_posts_res
+    
+    def get_posts(self, target_info:dict):
+        self.target_info = target_info
+        self.username = self.target_info["username"]
+        username = self.target_info["username"]
+        self.scraper.set_username(username)
+        days_limit = target_info["days_limit"]
+        if not self.check_account_is_public():
+            print("This is private account")
+            if self.account_status == "private":
+                self.get_profile()
+                res = self.get_private_account_res()
+                return res
+            elif self.account_status == "missing":
+                res = self.get_missing_account_res()
+                return res
+        
+        if self.check_account_is_public():
+            init_api_data = self.get_init_api_data() # 帳號資訊 & 上方頁面內容
+            self.get_profile()
+            print(f"This is public account")
+            # can scrape next round's posts
+            if init_api_data["posts"]["has_next"] != False:
+                maxid = init_api_data["posts"]["maxid"]
+                period_posts = self.get_period_data(
+                    init_maxid=maxid,
+                    days_limit=days_limit,
+                    init_api_data=init_api_data,
+                    username=username
+                    )
+
+                # return period_posts
+                res = self.get_public_account_res(
+                    scraped_posts=period_posts, 
+                    init_api_data=init_api_data
+                    )
+                return res
+            # # no more posts
+            elif init_api_data["posts"]["has_next"] == False: # (表示該帳號貼文數<=12, 無法繼續往下找)
+                res = self.get_public_account_res(scraped_posts=init_api_data["posts"]["items"], init_api_data=init_api_data)
+                return res

instagram_posts_scraper-0.0.1/instagram_posts_scraper/parse.py

@@ -0,0 +1,75 @@
+# -*- coding: utf-8 -*-
+from bs4 import BeautifulSoup
+import json
+
+
+class Parser(object):
+    def __init__(self):
+        self.__DEFAULT_SOUP_PARSER = "lxml"
+        self.__DEFAULT_USER_ELEMENT = (
+            "input", {"name": "userid", "type": "hidden"})
+
+    @staticmethod
+    def extract_info_value(item_in):
+        return item_in.find('div', class_='num')[
+            "title"].replace(',', '')
+
+    @staticmethod
+    def get_followers(profile_soup):
+        item_followers = profile_soup.find("div", class_="item_followers")
+        return Parser.extract_info_value(item_in=item_followers)
+
+    @staticmethod
+    def get_followings(profile_soup):
+        item_followings = profile_soup.find("div", class_="item_following")
+        return Parser.extract_info_value(item_in=item_followings)
+
+    @staticmethod
+    def get_counts_of_posts(profile_soup):
+        item_posts = profile_soup.find("div", class_="item_posts")
+        return Parser.extract_info_value(item_in=item_posts)
+
+    @staticmethod
+    def get_introduction(profile_soup):
+        user_info_list = []
+        user_info = profile_soup.find("div", class_="info")
+        user_info = user_info.find("div", class_="sum")
+        for each_info in user_info:
+            if each_info.text != ' ':
+                user_info_list.append(str(each_info.text))
+        return user_info_list
+
+    def get_soup(self, response):
+        soup = BeautifulSoup(response.text, self.__DEFAULT_SOUP_PARSER)
+        return soup
+    
+    def get_userid(self, profile_soup):
+        userid_input_element = profile_soup.find(
+            "input", {"name": "userid",
+                      "type": "hidden"})
+        if userid_input_element:
+            return userid_input_element["value"]
+        return ""
+
+    def get_maxid(self, response):
+        maxid = json.loads(response.text)["posts"]["maxid"]
+        return maxid
+
+    def get_userid_and_soup(self, response):
+        soup = BeautifulSoup(response.text, self.__DEFAULT_SOUP_PARSER)
+        userid_input_element = soup.find("input", {"name": "userid",
+                                                   "type": "hidden"}
+                                         )
+
+        if userid_input_element:
+            return userid_input_element["value"], soup
+
+        return "", ""
+    
+
+class ApiParser(object):
+    def __init__(self) -> None:
+        pass
+
+    def get_maxid(self, scraped_api_data:dict) -> str:
+        return scraped_api_data["posts"]["maxid"]

instagram_posts_scraper-0.0.1/instagram_posts_scraper/request.py

@@ -0,0 +1,42 @@
+# -*- coding: utf-8 -*-
+import json
+import cloudscraper
+from bs4 import BeautifulSoup
+
+
+class PixwoxRequest(object):
+    def __init__(self):
+        self.__DEFAULT_SOUP_PARSER = "lxml"
+        self.__scraper = cloudscraper.create_scraper(
+            delay=10,
+            browser={"custom": "ScraperBot/1.0",
+                     "platform": "windows",
+                     "mobile": "False"})
+
+    def send_requests(self, url):
+        response = self.__scraper.get(url)
+        return response
+
+    def get_init_content(self, username: str) -> str:
+        get_url = f"https://www.picnob.com/zh-hant/profile/{username}"
+        res = self.send_requests(get_url)
+        soup = BeautifulSoup(res.text, self.__DEFAULT_SOUP_PARSER)
+        userid_input_element = soup.find(
+            "input", {"name": "userid", "type": "hidden"})
+
+        if userid_input_element:
+            return userid_input_element["value"], soup
+
+        return "", ""
+    
+    def get_init_soup(self, profile_response):
+        soup = BeautifulSoup(profile_response.text, self.__DEFAULT_SOUP_PARSER)
+        return soup
+
+    def get_maxid(self, response):
+        maxid = json.loads(response.text)["posts"]["maxid"]
+        return maxid
+
+    def get_data(self, response):
+        scraped_data = json.loads(response.text)
+        return scraped_data

instagram_posts_scraper-0.0.1/instagram_posts_scraper/scraper.py

@@ -0,0 +1,53 @@
+# -*- coding: utf-8 -*-
+import json
+
+
+class Scraper(object):
+    def __init__(self, pixwox_request=None, parser=None,api_parser=None):
+        self.pixwox_request = pixwox_request
+        self.parser = parser
+        self.api_parser = api_parser
+        # self.target_info = target_info
+
+    def set_username(self, username:str):
+        self.__username = username
+    
+    @property
+    def username(self):
+        return self.__username
+
+    @property
+    def init_url(self) -> str:
+        self._init_url = f"https://www.picnob.com/zh-hant/profile/{self.username}"
+        return self._init_url
+    
+    def get_init_api(self, userid:str) -> str:
+        self._init_api = f"https://www.piokok.com/api/posts?userid={userid}"
+        return self._init_api
+    
+    def get_next_api(self, userid:str, next_maxid:str, next_:str, username:str) -> str:
+        next_api = f"https://www.piokok.com/api/posts?username={username}&userid={userid}&next={next_}&maxid={next_maxid}"
+        return next_api
+    
+    def send_api(self,api_url:str):
+        api_response = self.pixwox_request.send_requests(url=api_url)
+        return api_response
+
+    def get_api_data(self, api_response):
+        if api_response.status_code != 200:
+            print("status code from init api request is not equal 200")
+            return None
+        else:
+            json_data = json.loads(api_response.content)
+            return json_data
+
+    def get_init_api_data(self,userid:str) -> dict:
+        init_api = self.get_init_api(userid=userid)
+        init_api_response = self.send_api(api_url=init_api)
+        return self.get_api_data(api_response=init_api_response)
+    
+    def get_next_api_data(self, userid:str, next_maxid:str,next_:str, username:str):
+        next_api = self.get_next_api(userid=userid, next_maxid=next_maxid,next_=next_, username=username)
+        api_response = self.send_api(api_url=next_api)
+        next_api_data = self.get_api_data(api_response)
+        return next_api_data

instagram_posts_scraper-0.0.1/instagram_posts_scraper/utils/utils.py

@@ -0,0 +1,71 @@
+# -*- coding: utf-8 -*-
+import concurrent.futures as futures
+from datetime import datetime
+import pytz
+import pandas as pd
+from functools import wraps
+import time
+
+
+def timeit(func):
+    @wraps(func)
+    def timeit_wrapper(*args, **kwargs):
+        start_time = time.perf_counter()
+        result = func(*args, **kwargs)
+        end_time = time.perf_counter()
+        total_time = end_time - start_time
+        print(f'Function {func.__name__}{args} {kwargs} Took {total_time:.4f} seconds')
+        return result
+    return timeit_wrapper
+
+def timeout(timelimit):
+    def decorator(func):
+        def decorated(*args, **kwargs):
+            with futures.ThreadPoolExecutor(max_workers=1) as executor:
+                future = executor.submit(func, *args, **kwargs)
+                try:
+                    result = future.result(timelimit)
+                except futures.TimeoutError:
+                    print('Time out!')
+                    raise TimeoutError from None
+                else:
+                    print(result)
+                executor._threads.clear()
+                futures.thread._threads_queues.clear()
+                return result
+        return decorated
+    return decorator
+
+def get_current_time(timezone="Asia/Taipei"):
+    current_time_utc = datetime.utcnow()
+    target_timezone = pytz.timezone(timezone)
+    target_current_time = current_time_utc.replace(
+        tzinfo=pytz.utc).astimezone(target_timezone)
+    return target_current_time
+
+def get_account_status(userid, profile_soup=None):
+    if userid == "":
+        return "missing"
+    else:
+        private_span = profile_soup.find(
+            "span", class_="ident private icon icon_lock")
+        if private_span:
+            return "private"
+        return "public"
+
+def has_all_data_been_collected(scraped_items:pd.DataFrame,counts_of_posts):
+    """Whether program get all posts already."""
+    if len(set([each["shortcode"] for each in scraped_items])) >= int(counts_of_posts):
+        return True
+    return False
+
+def is_date_exceed_half_year(scraped_items:pd.DataFrame, days_limit:int):
+    """Check if scraped posts' published date exceed half year"""
+    current_time = datetime.now()
+    days_ago_list = [int(
+        (current_time - pd.to_datetime(each["time"], unit="s")).days) for each in scraped_items]
+    
+    max_days_ago = max(days_ago_list) # 爬到的貼文裡, 發文時間距離當前時間最遠的日期
+    if max_days_ago > days_limit:  # 半年內
+        return True
+    return False

instagram_posts_scraper-0.0.1/instagram_posts_scraper/utils.py

@@ -0,0 +1,40 @@
+# -*- coding: utf-8 -*-
+import concurrent.futures as futures
+from datetime import datetime
+import pytz
+
+
+def timeout(timelimit):
+    def decorator(func):
+        def decorated(*args, **kwargs):
+            with futures.ThreadPoolExecutor(max_workers=1) as executor:
+                future = executor.submit(func, *args, **kwargs)
+                try:
+                    result = future.result(timelimit)
+                except futures.TimeoutError:
+                    print('Time out!')
+                    raise TimeoutError from None
+                else:
+                    print(result)
+                executor._threads.clear()
+                futures.thread._threads_queues.clear()
+                return result
+        return decorated
+    return decorator
+
+def get_current_time(timezone="Asia/Taipei"):
+    current_time_utc = datetime.utcnow()
+    target_timezone = pytz.timezone(timezone)
+    target_current_time = current_time_utc.replace(
+        tzinfo=pytz.utc).astimezone(target_timezone)
+    return target_current_time
+
+def get_account_status(userid, profile_soup=None):
+    if userid == "":
+        return "missing"
+    else:
+        private_span = profile_soup.find(
+            "span", class_="ident private icon icon_lock")
+        if private_span:
+            return "private"
+        return "public"

instagram_posts_scraper-0.0.1/instagram_posts_scraper.egg-info/PKG-INFO

@@ -0,0 +1,104 @@
+Metadata-Version: 2.2
+Name: instagram-posts-scraper
+Version: 0.0.1
+Summary: Implement Instagram Posts Scraper for post data retrieval
+Home-page: https://github.com/FaustRen/instagram_posts_scraper
+Author: FaustRen
+Author-email: faustren1z@gmail.com
+License: MIT
+Classifier: Programming Language :: Python :: 3.11
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: requires-python
+Dynamic: summary
+
+# Instagram Posts Scraper
+
+InstagramPostsScraper is a Python library for collect instagram users' data.
+
+The data obtained by web crawlers is not real-time data, but rather data from a specific point in time on the same day.
+
+## Installation
+
+Use the package manager [pip](https://pip.pypa.io/en/stable/) to install instagram_posts_scraper.
+
+```bash
+beautifulsoup4==4.13.3
+cloudscraper==1.2.71
+pandas==2.2.3
+pytz==2025.1
+```
+
+
+## Usage - Sample
+
+```python
+from instagram_posts_scraper import InstaPeriodScraper
+
+
+target_info = {"username": "joemanweng", "days_limit":5}
+ig_posts_scraper = InstaPeriodScraper()
+res = ig_posts_scraper.get_posts(target_info=target_info)
+
+```
+
+## Result Sample
+
+```
+{
+    'profile': {
+        'introduction': ['台灣Youtuber\n⬇️專屬團購連結⬇️'],
+        'counts_of_posts': '1392',
+        'followers': '581198',
+        'followings': '859'
+    },
+    'account_status': 'public',
+    'updated_at': datetime.datetime(2025, 2, 9, 1, 28, 8, 793770, tzinfo=<DstTzInfo 'Asia/Taipei' CST+8:00:00 STD>),
+    'data': [
+        {
+            'type': 'igtv',
+            'sum': '《靈能的挑戰》參賽者後台花絮露出👀\n老師們比賽中較勁，但私下娛樂竟是互相算命！\n不知道有沒有先算出冠軍了（吃瓜）\n預祝大家新年快樂~~\n*節目中個人言論不代表本節目立場*\n﹏﹏﹏﹏﹏﹏﹏﹏﹏﹏﹏﹏\n#靈能的挑戰\xa0#Joeman\xa0#東森超視33頻道\n全台第一檔靈能競賽節目\n📺️ 全季觀看平台｜\n🎥 Joeman YT 頻道觀看全季\n🎥 東森超視 33 頻道已播出完畢\n﹋﹋﹋﹋﹋﹋﹋﹋﹋﹋﹋﹋\n#玄學 #易經 #塔羅 #通靈 #占星',
+            'sum_pure': '《靈能的挑戰》參賽者後台花絮露出 老師們比賽中較勁，但私下娛樂竟是互相算命！不知道有沒有先算出冠軍了（吃瓜）預祝大家新年快樂~~*節目中個人言論不代表本節目立場*﹏﹏﹏﹏﹏﹏﹏﹏﹏﹏﹏﹏#靈能的挑戰\xa0#Joeman\xa0#東森超視33頻道全台第一檔靈能競賽節目 ️ 全季觀看平台｜ Joeman YT 頻道觀看全季 東森超視 33 頻道已播出完畢﹋﹋﹋﹋﹋﹋﹋﹋﹋﹋﹋﹋#玄學 #易經 #塔羅 #通靈 #占星',
+            'shortcode': '6741582137415658464423',
+            'time': 1737885600,
+            'ftime': '13 days ago',
+            'count_like': 2442,
+            'count_comment': 6,
+            'count_like_pure': '2,442',
+            'count_comment_pure': '6',
+            'thum': 'https://scontent-fra3-1.cdninstagram.com/v/t51.2885-15/474907887_1129543381888335_8766424988966118915_n.jpg?stp=c0.248.640.640a_dst-jpg_e15_tt6&_nc_ht=scontent-fra3-1.cdninstagram.com&_nc_cat=103&_nc_ohc=YPiycXP_teMQ7kNvgF-DLaF&_nc_gid=3e3699c22b4246b98fb450d120d9527f&edm=APU89FABAAAA&ccb=7-5&oh=00_AYAb75YGceozAPWzbq4CQQGd_q_XyfKdjdwcKYak3J-pHA&oe=67AD07FF&_nc_sid=bc0c2c',
+            'pic': 'https://scontent-fra3-1.cdninstagram.com/v/t51.2885-15/474907887_1129543381888335_8766424988966118915_n.jpg?stp=dst-jpg_e15_tt6&_nc_ht=scontent-fra3-1.cdninstagram.com&_nc_cat=103&_nc_ohc=YPiycXP_teMQ7kNvgF-DLaF&_nc_gid=3e3699c22b4246b98fb450d120d9527f&edm=APU89FABAAAA&ccb=7-5&oh=00_AYA0qczIKFhJEbukWZRRSUvJJ28iqBuhIXZqRB3EEA450Q&oe=67AD07FF&_nc_sid=bc0c2c',
+            'pic_p': 'https://sp1.piokok.com/p/pt_6741582137415658464423_0_233bd378e8b9a4f088f6c850099951c7.jpg?u=https%3A%2F%2Fscontent-fra3-1.cdninstagram.com%2Fv%2Ft51.2885-15%2F474907887_1129543381888335_8766424988966118915_n.jpg%3Fstp%3Dc0.248.640.640a_dst-jpg_e15_tt6%26_nc_ht%3Dscontent-fra3-1.cdninstagram.com%26_nc_cat%3D103%26_nc_ohc%3DYPiycXP_teMQ7kNvgF-DLaF%26_nc_gid%3D3e3699c22b4246b98fb450d120d9527f%26edm%3DAPU89FABAAAA%26ccb%3D7-5%26oh%3D00_AYAb75YGceozAPWzbq4CQQGd_q_XyfKdjdwcKYak3J-pHA%26oe%3D67AD07FF%26_nc_sid%3Dbc0c2c',
+            'down_pic': 'https://scontent-fra3-1.cdninstagram.com/v/t51.2885-15/474907887_1129543381888335_8766424988966118915_n.jpg?stp=dst-jpg_e15_tt6&_nc_ht=scontent-fra3-1.cdninstagram.com&_nc_cat=103&_nc_ohc=YPiycXP_teMQ7kNvgF-DLaF&_nc_gid=3e3699c22b4246b98fb450d120d9527f&edm=APU89FABAAAA&ccb=7-5&oh=00_AYA0qczIKFhJEbukWZRRSUvJJ28iqBuhIXZqRB3EEA450Q&oe=67AD07FF&_nc_sid=bc0c2c&dl=1',
+            'is_video': True,
+            'video': 'https://scontent-fra3-1.cdninstagram.com/o1/v/t16/f2/m86/AQNbkAdWefxU8OJ015A7RX0oUxLJS-03KKFEbd2ueAbuWXS5jla4AsgRPhGeuuD9HsvVUz0mG5uKwOTWpYhvCVbbIPtxarY3vAIwG7A.mp4?stp=dst-mp4&efg=eyJxZV9ncm91cHMiOiJbXCJpZ193ZWJfZGVsaXZlcnlfdnRzX290ZlwiXSIsInZlbmNvZGVfdGFnIjoidnRzX3ZvZF91cmxnZW4uY2xpcHMuYzIuNzIwLmJhc2VsaW5lIn0&_nc_cat=103&vs=427033163733715_1223826287&_nc_vs=HBksFQIYUmlnX3hwdl9yZWVsc19wZXJtYW5lbnRfc3JfcHJvZC9ERDQ1NERCQUU1RkU4RDA5MzA5NzA2Q0IzODgxRUVBM192aWRlb19kYXNoaW5pdC5tcDQVAALIAQAVAhg6cGFzc3Rocm91Z2hfZXZlcnN0b3JlL0dPcGZUeHgyY1EtV3l3c0VBQjRRdldDeTRZdHFicV9FQUFBRhUCAsgBACgAGAAbABUAACamtPfZ0u%2BTQBUCKAJDMywXQF2QEGJN0vIYEmRhc2hfYmFzZWxpbmVfMV92MREAdf4HAA%3D%3D&_nc_rid=3e36937551&ccb=9-4&oh=00_AYANPnQ7Zlk5Z_6wS0OF1Hn3ttS8vsk-0K6OyM9y8xzM6A&oe=67A925DC&_nc_sid=bc0c2c',
+            'down_video': 'same_as_above'
+        }
+    ]
+}
+
+
+
+
+## Contributing - Sample
+
+comming soon..
+
+## License - Sample
+
+comming soon..
+
+## Tests - cd to tests folder
+coverage run test_crawler.py
+
+coverage html

instagram_posts_scraper-0.0.1/instagram_posts_scraper.egg-info/SOURCES.txt

@@ -0,0 +1,16 @@
+LICENSE
+setup.py
+instagram_posts_scraper/__init__.py
+instagram_posts_scraper/example.py
+instagram_posts_scraper/file_operation.py
+instagram_posts_scraper/instagram_posts_scraper.py
+instagram_posts_scraper/parse.py
+instagram_posts_scraper/request.py
+instagram_posts_scraper/scraper.py
+instagram_posts_scraper/utils.py
+instagram_posts_scraper.egg-info/PKG-INFO
+instagram_posts_scraper.egg-info/SOURCES.txt
+instagram_posts_scraper.egg-info/dependency_links.txt
+instagram_posts_scraper.egg-info/top_level.txt
+instagram_posts_scraper/utils/__init__.py
+instagram_posts_scraper/utils/utils.py

instagram_posts_scraper-0.0.1/instagram_posts_scraper.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

instagram_posts_scraper-0.0.1/instagram_posts_scraper.egg-info/top_level.txt

@@ -0,0 +1 @@
+instagram_posts_scraper

instagram_posts_scraper-0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

instagram_posts_scraper-0.0.1/setup.py

@@ -0,0 +1,25 @@
+# -*- coding: utf-8 -*-
+import setuptools
+from setuptools import setup, find_packages
+
+setup(
+    name='instagram-posts-scraper',
+    version='0.0.1',
+    packages=[
+        "instagram_posts_scraper",
+        "instagram_posts_scraper.utils"
+    ],
+    license='MIT',
+    description='Implement Instagram Posts Scraper for post data retrieval',
+    long_description=open('README.md').read(),
+    long_description_content_type='text/markdown',
+    author='FaustRen',
+    author_email='faustren1z@gmail.com',
+    url='https://github.com/FaustRen/instagram_posts_scraper',
+    classifiers=[
+        "Programming Language :: Python :: 3.11",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+    python_requires='>=3.11',
+)