fb_scraper_request 0.2.3__tar.gz → 0.2.5__tar.gz

{fb_scraper_request-0.2.3 → fb_scraper_request-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fb_scraper_request
-Version: 0.2.3
+Version: 0.2.5
 Summary: Facebook GraphQL Scraper - No login required, simple API to scrape public Facebook posts
 Author-email: Nguyen Minh Quang <quangforwork1203@gmail.com>
 License: MIT
@@ -24,6 +24,7 @@ License-File: LICENSE
 Requires-Dist: requests>=2.28.0
 Requires-Dist: pytz
 Requires-Dist: pip>=26.0.1
+Requires-Dist: beautifulsoup4>=4.12.0
 Provides-Extra: dev
 Requires-Dist: build>=0.8.0; extra == "dev"
 Requires-Dist: twine>=4.0.0; extra == "dev"

fb_scraper_request-0.2.5/fb_scraper_request/base/base_page.py

@@ -0,0 +1,90 @@
+# -*- coding:utf-8 -*-
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from selenium.webdriver.chrome.service import Service
+
+
+class BasePage:
+    def __init__(self, driver_path: str, open_browser: bool = False):
+        chrome_options = self._build_options(open_browser)
+        normalized_driver_path = self._normalize_path(driver_path)
+
+        if self._looks_like_chrome_binary(normalized_driver_path):
+            chrome_options.binary_location = normalized_driver_path
+            service = Service()
+        elif normalized_driver_path:
+            service = Service(normalized_driver_path)
+        else:
+            service = Service()
+
+        self.driver = self._build_driver(service=service, chrome_options=chrome_options)
+        self.driver.maximize_window()
+
+    @staticmethod
+    def _build_options(open_browser: bool) -> ChromeOptions:
+        options = ChromeOptions()
+        options.add_argument("--disable-blink-features")
+        options.add_argument("--disable-notifications")
+        options.add_argument("--disable-blink-features=AutomationControlled")
+        if not open_browser:
+            options.add_argument("--headless=new")
+        options.add_argument("--blink-settings=imagesEnabled=false")
+        return options
+
+    @staticmethod
+    def _normalize_path(path: str | None) -> str | None:
+        if not path:
+            return None
+        # In notebook strings users often escape spaces (e.g. "Google\ Chrome").
+        return path.replace("\\ ", " ").strip()
+
+    @staticmethod
+    def _looks_like_chrome_binary(path: str | None) -> bool:
+        if not path:
+            return False
+        normalized = path.lower()
+        return normalized.endswith("/google chrome") or normalized.endswith("/chrome")
+
+    @staticmethod
+    def _build_driver(service: Service, chrome_options: ChromeOptions):
+        from seleniumwire import webdriver
+
+        try:
+            return webdriver.Chrome(service=service, options=chrome_options)
+        except AttributeError as exc:
+            if "VERSION_CHOICES" not in str(exc):
+                raise
+            # Some selenium-wire/pyOpenSSL combinations expose this at runtime.
+            BasePage._patch_seleniumwire_tls_version_choices()
+            return webdriver.Chrome(service=service, options=chrome_options)
+
+    @staticmethod
+    def _patch_seleniumwire_tls_version_choices() -> None:
+        from OpenSSL import SSL
+        from seleniumwire.thirdparty.mitmproxy.net import tls
+
+        if hasattr(tls, "VERSION_CHOICES"):
+            return
+
+        basic_options = SSL.OP_CIPHER_SERVER_PREFERENCE
+        if hasattr(SSL, "OP_NO_COMPRESSION"):
+            basic_options |= SSL.OP_NO_COMPRESSION
+
+        default_method = getattr(SSL, "SSLv23_METHOD", getattr(SSL, "TLS_METHOD", None))
+        default_options = basic_options
+        if hasattr(SSL, "OP_NO_SSLv2"):
+            default_options |= SSL.OP_NO_SSLv2
+        if hasattr(SSL, "OP_NO_SSLv3"):
+            default_options |= SSL.OP_NO_SSLv3
+
+        version_choices = {
+            "all": (default_method, basic_options),
+            "secure": (default_method, default_options),
+        }
+
+        for name in ("TLSv1", "TLSv1_1", "TLSv1_2"):
+            method_name = f"{name}_METHOD"
+            method = getattr(SSL, method_name, None)
+            if method is not None:
+                version_choices[name] = (method, basic_options)
+
+        tls.VERSION_CHOICES = version_choices

{fb_scraper_request-0.2.3 → fb_scraper_request-0.2.5}/fb_scraper_request/facebook_graphql_scraper.py

@@ -3,7 +3,6 @@ import re
 import requests
 from datetime import datetime
 from fb_scraper_request.utils.parser import RequestsParser
-from fb_scraper_request.utils.locator import *
 from fb_scraper_request.utils.utils import *
 
 

fb_scraper_request-0.2.5/fb_scraper_request/pages/page_optional.py

@@ -0,0 +1,131 @@
+# -*- coding: utf-8 -*-
+from fb_scraper_request.utils.locator import *
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.common.action_chains import ActionChains
+from selenium.webdriver.common.keys import Keys
+import time
+
+
+class PageOptional(object):
+    def __init__(self, driver=None, fb_account: str = None, fb_pwd: str = None):
+        self.locator = PageLocators
+        self.xpath_elements = PageXpath
+        self.class_elements = PageClass
+        self.page_text = PageText
+        self.driver = driver
+        self.fb_account = fb_account
+        self.fb_pwd = fb_pwd
+
+        # Loggin account
+        if self.fb_account and self.fb_pwd:
+            login_page_url = "https://www.facebook.com/login"
+            self.driver.get(url=login_page_url)
+            self.login_page()
+
+    def login_page(self):
+        try:
+            self.login_account(
+                user=self.fb_account,
+                password=self.fb_pwd,
+            )
+            time.sleep(5)
+        except Exception as e:
+            print(f"Login faield, message: {e}")
+
+    def clean_requests(self):
+        print(
+            f"Before cleaning driver requests, the number of requests are: {len(self.driver.requests)}"
+        )
+        try:
+            print("Try to clear driver requests..")
+            del self.driver.requests
+            print(f"Clear, the number of requests are: {len(self.driver.requests)}")
+        except Exception as e:
+            print(f"Clear unsuccessfully, message: {e}")
+
+    def get_in_url(self):
+        self.driver.get(url=self.url)
+
+    def login_account(self, user: str, password: str):
+        user_element = self.driver.find_element(By.NAME, "email")
+        user_element.send_keys(user)
+        password_element = self.driver.find_element(By.NAME, "pass")
+        password_element.send_keys(password)
+        password_element.send_keys(Keys.ENTER)
+
+    def scroll_window(self):
+        self.driver.execute_script("window.scrollTo(0,document.body.scrollHeight)")
+
+    def scroll_window_with_parameter(self, parameter_in: str):
+        self.driver.execute_script(f"window.scrollBy(0, {parameter_in});")
+
+    def set_browser_zoom_percent(self, zoom_percent: int):
+        zoom_percent = str(zoom_percent)
+        self.driver.execute_script(f"document.body.style.zoom='{zoom_percent}%'")
+
+    def move_to_element(self, element_in):
+        ActionChains(self.driver).move_to_element(element_in).perform()
+
+    def load_next_page(self, url: str, clear_limit: int = 20):
+        """>> Move on to target facebook user page,
+        before moving, clean driver's requests first,
+        or driver would store previous account's data.
+        Args: url (str): user(kol) links"""
+        i = 0
+        while i <= clear_limit:
+            self.clean_requests()
+            if len(self.driver.requests) == 0:
+                print("Clear all driver requests already!")
+                break
+            i += 1
+        self.driver.get(url=url)
+
+    def click_display_button(self):
+        elements = self.driver.find_elements(self.locator.DISPLAY_MORE)
+        for _ in range(10):
+            for each_element in elements:
+                if (
+                    each_element.text == self.page_text.DISPLAY_MORE
+                    or each_element.text == self.page_text.DISPLAY_MORE2
+                ):
+                    self.move_to_element(element_in=each_element)
+                    self.scroll_window_with_parameter(parameter_in="500")
+                    try:
+                        each_element.click()
+                        elements = self.driver.find_elements(self.locator.DISPLAY_MORE)
+                    except Exception as e:
+                        print(f"Click display more unsucessfully, error message:\n{e}")
+
+    def click_display_button2(self):
+        display_more_xpath = f"//div[@class='{PageClass.DISPLAY_MORE}' and @role='{PageRoleValue.DISPLAY_MORE}' and text()='{PageText.DISPLAY_MORE}']"
+        elements = self.driver.find_elements(By.XPATH, display_more_xpath)
+        for _ in range(10):
+            for each_element in elements:
+                if (
+                    each_element.text == self.page_text.DISPLAY_MORE
+                    or each_element.text == self.page_text.DISPLAY_MORE2
+                ):
+                    self.move_to_element(element_in=each_element)
+                    self.scroll_window_with_parameter(parameter_in="500")
+                    try:
+                        each_element.click()
+                        elements = self.driver.find_elements(self.locator.DISPLAY_MORE)
+                    except Exception as e:
+                        print(f"Click display more unsucessfully, error message:\n{e}")
+
+    def click_reject_login_button(self):
+        try:
+            reject_login_button = WebDriverWait(self.driver, 10).until(
+                EC.visibility_of_element_located((self.locator.CLOSELOGIN))
+            )
+            reject_login_button.click()
+        except Exception as e:
+            print(f"Click reject button failed, message:{e}")
+
+    def quit_driver(self):
+        self.driver.quit()
+
+    def close_driver(self):
+        self.driver.close()

fb_scraper_request-0.2.5/fb_scraper_request/utils/parser.py

@@ -0,0 +1,131 @@
+# -*- coding: utf-8 -*-
+import json
+from urllib.parse import parse_qs, unquote
+from fb_scraper_request.utils.utils import *
+
+
+class RequestsParser(object):
+    def __init__(self) -> None:
+        # self.driver = driver
+        self.reaction_names = ["讚", "哈", "怒", "大心", "加油", "哇", "嗚"]
+        self.en_reaction_names = [
+            "like",
+            "haha",
+            "angry",
+            "love",
+            "care",
+            "sorry",
+            "wow",
+        ]
+
+    def get_graphql_body_content(self, req_response, req_url):
+        target_url = "https://www.facebook.com/api/graphql/"
+        if req_response and req_url == target_url:
+            response = req_response
+            body = decode(
+                response.body, response.headers.get("Content-Encoding", "identity")
+            )
+            body_content = body.decode("utf-8").split("\n")
+            return body_content
+        return None
+
+    def _clean_res(self):
+        self.res_new = []
+        self.feedback_list = []
+        self.context_list = []
+        self.creation_list = []
+        self.author_id_list = []
+        self.author_id_list2 = []
+        self.owning_profile = []
+
+    def parse_body(self, body_content):
+        for each_body in body_content:
+            json_data = json.loads(each_body)
+            self.res_new.append(json_data)
+            try:
+                each_res = json_data["data"]["node"].copy()
+                each_feedback = find_feedback_with_subscription_target_id(each_res)
+                if each_feedback:
+                    self.feedback_list.append(each_feedback)
+                    message_text = find_message_text(json_data)
+                    creation_time = find_creation(json_data)
+                    owing_profile = find_owning_profile(json_data)
+                    if message_text:
+                        self.context_list.append(message_text)
+                    elif not message_text:
+                        self.context_list.append(None)
+                    if creation_time:
+                        self.creation_list.append(creation_time)
+                    self.owning_profile.append(owing_profile)
+
+            # Did not display or record error message at here
+            except Exception as e:
+                pass
+
+    def collect_posts(self):
+        res_out = []
+        for each in self.feedback_list:
+            res_out.append(
+                {
+                    "post_id": each["subscription_target_id"],
+                    "reaction_count": each["reaction_count"],
+                    "top_reactions": each["top_reactions"],
+                    "share_count": each["share_count"],
+                    "comment_rendering_instance": each["comment_rendering_instance"],
+                    "video_view_count": each["video_view_count"],
+                }
+            )
+        return res_out
+
+    def convert_res_to_df(self, res_in):
+        # Pure Python version without pandas
+        selected_fields = [
+            "post_id",
+            "reaction_count",
+            "comment_rendering_instance",
+            "share_count",
+            "top_reactions",
+            "video_view_count",
+        ]
+        result = []
+        for item in res_in:
+            row = {field: item.get(field) for field in selected_fields}
+            result.append(row)
+        return result
+
+    def process_reactions(self, reactions_in) -> dict:
+        """Extract sub reaction value:
+        Args:
+            reactions_in (_type_): _description_
+        Returns:
+            _dict_: {
+                "like": value,
+                "haha": value,
+                "angry": value,
+                "love": value,
+                "care": value,
+                "sorry": value,
+                "wow": value
+        }
+        Note:
+        """
+        reaction_hash = {}
+        for each_react in reactions_in:
+            reaction_hash[each_react["node"]["localized_name"]] = each_react[
+                "reaction_count"
+            ]  # get reaction value
+        return reaction_hash
+
+    def extract_first_payload(self, payload: str):
+        parsed_data = parse_qs(payload)
+        print("Parsed data:", parsed_data)  # Debug: Show the parsed data
+        decoded_data = {
+            unquote(k): [unquote(v) for v in vals] for k, vals in parsed_data.items()
+        }  # 解碼 keys 和 values
+        first_payload = {
+            k: v[0] for k, v in decoded_data.items()
+        }  # 如果只需要第一個值作為字典中的單一值
+        payload_variables = json.loads(first_payload["variables"])
+        first_payload["variables"] = payload_variables
+        print(first_payload)
+        return first_payload

fb_scraper_request-0.2.5/fb_scraper_request/utils/utils.py

@@ -0,0 +1,318 @@
+# -*- coding: utf-8 -*-
+import concurrent.futures as futures
+import requests
+import re
+from bs4 import BeautifulSoup
+from datetime import datetime, timedelta
+import pytz
+import time
+import json
+
+
+# if key: 'subscription_target_id' in feedback, store this feedback
+def find_feedback_with_subscription_target_id(data):
+    if isinstance(data, dict):
+        if 'feedback' in data and isinstance(data['feedback'], dict):
+            feedback = data['feedback']
+            if 'subscription_target_id' in list(feedback.keys()):
+                return feedback
+
+        # Traverse the values of the dictionary and continue recursively searching
+        for value in data.values():
+            result = find_feedback_with_subscription_target_id(value)
+            if result:
+                return result
+
+    # If it is a list, traverse each element in the list and continue recursively searching
+    elif isinstance(data, list):
+        for item in data:
+            result = find_feedback_with_subscription_target_id(item)
+            if result:
+                return result
+
+    # If no matching feedback is found, return None
+    return None
+
+
+def find_message_text(data):
+    if isinstance(data, dict):
+        # type is dict，check 'story' key
+        if 'story' in data:
+            # if key 'story's value type is dict, and include 'message' key
+            if isinstance(data['story'], dict) and 'message' in data['story']:
+                # if key 'message's value type is dict, and include 'text' key
+                if isinstance(data['story']['message'], dict) and 'text' in data['story']['message']:
+                    # return 'text' key
+                    return data['story']['message']['text']
+
+        # recursively check each value in dict if can not find anything
+        for value in data.values():
+            result = find_message_text(value)
+            if result:
+                return result
+    elif isinstance(data, list):
+        # if array, check each element recursively
+        for item in data:
+            result = find_message_text(item)
+            if result:
+                return result
+    # 如果沒有符合條件的值，return None
+    return None
+
+
+def find_creation(data):
+    if isinstance(data, dict):
+        # If it's a dictionary, check if it contains the 'story' key
+        if 'story' in data:
+            # If the value of the 'story' key is a dictionary and contains the 'creation_time' key
+            if isinstance(data['story'], dict) and 'creation_time' in data['story']:
+                # Return the value of the 'creation_time' key
+                return data['story']['creation_time']
+
+        # If no matching condition is found, recursively check each value in the dictionary
+        for value in data.values():
+            result = find_creation(value)
+            if result:
+                return result
+
+    elif isinstance(data, list):
+        # If it's a list, recursively check each element in the list
+        for item in data:
+            result = find_creation(item)
+            if result:
+                return result
+    # If no matching condition is found, return None
+    return None
+
+
+def find_actors(data):
+    if isinstance(data, dict):
+        # If it's a dictionary, check if it contains the 'story' key
+        if 'story' in data:
+            # If the value of the 'story' key is a dictionary and contains the 'actors' key
+            if isinstance(data['story'], dict) and 'actors' in data['story']:
+                # Return the value of the 'id' key under 'actors'
+                return data['story']['actors']['id']
+
+        # If no matching condition is found, recursively check each value in the dictionary
+        for value in data.values():
+            result = find_actors(value)
+            if result:
+                return result
+
+    elif isinstance(data, list):
+        # If it's a list, recursively check each element in the list
+        for item in data:
+            result = find_actors(item)
+            if result:
+                return result
+    # If no matching condition is found, return None
+    return None
+
+
+def find_owning_profile(data):
+    if isinstance(data, dict):
+        # If it's a dictionary, check if it contains the 'story' key
+        if 'owning_profile' in data:
+            # If the value of the 'story' key is a dictionary and contains the 'actors' key
+            if isinstance(data['owning_profile'], dict):
+                # Return the value of the 'id' key under 'actors'
+                return data['owning_profile']
+
+        # If no matching condition is found, recursively check each value in the dictionary
+        for value in data.values():
+            result = find_owning_profile(value)
+            if result:
+                return result
+
+    elif isinstance(data, list):
+        # If it's a list, recursively check each element in the list
+        for item in data:
+            result = find_owning_profile(item)
+            if result:
+                return result
+    # If no matching condition is found, return None
+    return None
+
+
+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:
+                    pass
+                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 days_difference_from_now(tmp_creation_array: list) -> int:
+    """計算第一次發文日期與當前日間隔天數
+
+    Args:
+        tmp_creation_array (list): _description_
+
+    Returns:
+        int: 間隔天數
+    """
+    timestamp = min(tmp_creation_array)
+    current_date_time = datetime.now()
+    date_time_obj = datetime.fromtimestamp(timestamp)
+    difference = current_date_time - date_time_obj
+    return difference.days
+
+
+def is_date_exceed_limit(max_days_ago, days_limit: int = 61):
+    if max_days_ago > days_limit:
+        return True
+    return False
+
+def pause(pause_time: int = 1):
+    time.sleep(pause_time)
+
+
+def get_payload(doc_id_in: str, id_in: str, before_time: str = None):
+    variables_dict = {
+        "afterTime": None,
+        "beforeTime": before_time,
+        "count": 3,
+        "cursor": None,
+        "feedLocation": "TIMELINE",
+        "feedbackSource": 0,
+        "focusCommentID": None,
+        "memorializedSplitTimeFilter": None,
+        "omitPinnedPost": True,
+        "postedBy": {"group": "OWNER"},
+        "privacy": {"exclusivity": "INCLUSIVE", "filter": "ALL"},
+        "privacySelectorRenderLocation": "COMET_STREAM",
+        "renderLocation": "timeline",
+        "scale": 3,
+        "stream_count": 1,
+        "taggedInOnly": False,
+        "useDefaultActor": False,
+        "id": id_in,
+        "__relay_internal__pv__CometImmersivePhotoCanUserDisable3DMotionrelayprovider": False,
+        "__relay_internal__pv__IsWorkUserrelayprovider": False,
+        "__relay_internal__pv__IsMergQAPollsrelayprovider": False,
+        "__relay_internal__pv__CometUFIReactionsEnableShortNamerelayprovider": False,
+        "__relay_internal__pv__CometUFIShareActionMigrationrelayprovider": False,
+        "__relay_internal__pv__StoriesArmadilloReplyEnabledrelayprovider": False,
+        "__relay_internal__pv__StoriesTrayShouldShowMetadatarelayprovider": False,
+        "__relay_internal__pv__StoriesRingrelayprovider": False,
+        "__relay_internal__pv__EventCometCardImage_prefetchEventImagerelayprovider": False
+    }
+
+    payload_out = {
+        "variables": json.dumps(variables_dict),
+        "doc_id": doc_id_in
+    }
+    return payload_out
+
+def get_next_payload(
+    doc_id_in:str, 
+    id_in:str, 
+    before_time:str, 
+    cursor_in:str
+):
+    variables_dict = {
+        "afterTime": None,
+        "beforeTime": before_time,
+        "count": 3,
+        "cursor": cursor_in,
+        "feedLocation": "TIMELINE",
+        "feedbackSource": 0,
+        "focusCommentID": None,
+        "memorializedSplitTimeFilter": None,
+        "omitPinnedPost": True,
+        "postedBy": {"group": "OWNER"},
+        "privacy": {"exclusivity": "INCLUSIVE", "filter": "ALL"},
+        "privacySelectorRenderLocation": "COMET_STREAM",
+        "renderLocation": "timeline",
+        "scale": 3,
+        "stream_count": 1,
+        "taggedInOnly": False,
+        "useDefaultActor": False,
+        "id": id_in,
+        "__relay_internal__pv__CometImmersivePhotoCanUserDisable3DMotionrelayprovider": False,
+        "__relay_internal__pv__IsWorkUserrelayprovider": False,
+        "__relay_internal__pv__IsMergQAPollsrelayprovider": False,
+        "__relay_internal__pv__CometUFIReactionsEnableShortNamerelayprovider": False,
+        "__relay_internal__pv__CometUFIShareActionMigrationrelayprovider": False,
+        "__relay_internal__pv__StoriesArmadilloReplyEnabledrelayprovider": False,
+        "__relay_internal__pv__StoriesTrayShouldShowMetadatarelayprovider": False,
+        "__relay_internal__pv__StoriesRingrelayprovider": False,
+        "__relay_internal__pv__EventCometCardImage_prefetchEventImagerelayprovider": False
+    }
+    payload_out = {
+        "variables": json.dumps(variables_dict),
+        "doc_id": doc_id_in
+    }
+    return payload_out
+
+def get_next_cursor(body_content_in):
+    for i in range(len(body_content_in)-1, -1, -1):
+        try:
+            json_tail = json.loads(body_content_in[i])
+            nex_cursor = json_tail.get("data").get(
+                "page_info").get("end_cursor")
+            return nex_cursor
+        except AttributeError:
+            pass
+
+def get_next_page_status(body_content):
+    for each_body in body_content:
+        try:
+            tmp_json = json.loads(each_body)
+            next_page_status = tmp_json.get("data").get(
+                "page_info").get("has_next_page")
+            return next_page_status
+        except Exception as e:
+            pass
+    return True # sometimes, scraper can not collect API's "has_next" info, Program choose return True, I will improve this step in the near future.
+
+
+def compare_timestamp(timestamp: int, days_limit: int, display_progress: bool) -> bool:
+    timestamp_date = datetime.utcfromtimestamp(timestamp).date()
+    current_date = datetime.utcnow().date()
+    past_date = current_date - timedelta(days=days_limit)
+    if display_progress:
+        days_remaining = (timestamp_date - past_date).days
+        if days_remaining > 0:
+            print(f"{days_remaining} more days of posts to collect.")
+        else:
+            print("Target days reached or exceeded.")
+    return timestamp_date < past_date
+
+
+def get_before_time(time_zone='Asia/Taipei'):
+    location_tz = pytz.timezone(time_zone)
+    current_time = datetime.now(location_tz)
+    timestamp = str(int(current_time.timestamp()))
+    return timestamp
+
+def get_posts_image(post_id:str):
+    url = f"https://www.facebook.com/plugins/post.php?href=https%3A%2F%2Fwww.facebook.com%2Ftoolbox003%2Fposts%2F{post_id}&show_text=true&width=800"
+    """You can check out the content through the link 
+    to better understand what I'm talking about haha"""
+    response = requests.get(url=url)
+    response.status_code
+    soup = BeautifulSoup(response.text, "html.parser")
+    pattern = re.compile(r"^https://scontent")
+    all_src_links = [tag['src'] for tag in soup.find_all(src=pattern)]
+    return all_src_links

{fb_scraper_request-0.2.3 → fb_scraper_request-0.2.5}/fb_scraper_request.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fb_scraper_request
-Version: 0.2.3
+Version: 0.2.5
 Summary: Facebook GraphQL Scraper - No login required, simple API to scrape public Facebook posts
 Author-email: Nguyen Minh Quang <quangforwork1203@gmail.com>
 License: MIT
@@ -24,6 +24,7 @@ License-File: LICENSE
 Requires-Dist: requests>=2.28.0
 Requires-Dist: pytz
 Requires-Dist: pip>=26.0.1
+Requires-Dist: beautifulsoup4>=4.12.0
 Provides-Extra: dev
 Requires-Dist: build>=0.8.0; extra == "dev"
 Requires-Dist: twine>=4.0.0; extra == "dev"

fb_scraper_request-0.2.5/fb_scraper_request.egg-info/SOURCES.txt

@@ -0,0 +1,19 @@
+LICENSE
+README.md
+pyproject.toml
+fb_scraper_request/__init__.py
+fb_scraper_request/example.py
+fb_scraper_request/facebook_graphql_scraper.py
+fb_scraper_request.egg-info/PKG-INFO
+fb_scraper_request.egg-info/SOURCES.txt
+fb_scraper_request.egg-info/dependency_links.txt
+fb_scraper_request.egg-info/requires.txt
+fb_scraper_request.egg-info/top_level.txt
+fb_scraper_request/base/__init__.py
+fb_scraper_request/base/base_page.py
+fb_scraper_request/pages/__init__.py
+fb_scraper_request/pages/page_optional.py
+fb_scraper_request/tests/__init__.py
+fb_scraper_request/utils/__init__.py
+fb_scraper_request/utils/parser.py
+fb_scraper_request/utils/utils.py

{fb_scraper_request-0.2.3 → fb_scraper_request-0.2.5}/fb_scraper_request.egg-info/requires.txt

@@ -1,6 +1,7 @@
 requests>=2.28.0
 pytz
 pip>=26.0.1
+beautifulsoup4>=4.12.0
 
 [dev]
 build>=0.8.0

{fb_scraper_request-0.2.3 → fb_scraper_request-0.2.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "fb_scraper_request"
-version = "0.2.3"
+version = "0.2.5"
 description = "Facebook GraphQL Scraper - No login required, simple API to scrape public Facebook posts"
 readme = "README.md"
 requires-python = ">=3.9"
@@ -25,6 +25,7 @@ dependencies = [
     "requests>=2.28.0",
     "pytz",
     "pip>=26.0.1",
+    "beautifulsoup4>=4.12.0",
 ]
 
 [project.optional-dependencies]
@@ -42,5 +43,6 @@ Issues = "https://github.com/DOCUTEE/fb_crawl_request/issues"
 requires = ["setuptools>=45", "wheel"]
 build-backend = "setuptools.build_meta"
 
-[tool.setuptools]
-packages = ["fb_scraper_request"]
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["fb_scraper_request*"]

fb_scraper_request-0.2.3/fb_scraper_request.egg-info/SOURCES.txt

@@ -1,11 +0,0 @@
-LICENSE
-README.md
-pyproject.toml
-fb_scraper_request/__init__.py
-fb_scraper_request/example.py
-fb_scraper_request/facebook_graphql_scraper.py
-fb_scraper_request.egg-info/PKG-INFO
-fb_scraper_request.egg-info/SOURCES.txt
-fb_scraper_request.egg-info/dependency_links.txt
-fb_scraper_request.egg-info/requires.txt
-fb_scraper_request.egg-info/top_level.txt