Upload 3 files

driver.py

@@ -17,6 +17,11 @@ from selenium.webdriver.common.by import By
 from selenium.webdriver.support.expected_conditions import presence_of_element_located
 from selenium.webdriver.support.wait import WebDriverWait
 
+CHROME_BIN = "/app/.chrome-for-testing/chrome-linux64/chrome"
+CHROME_DRIVER = "/app/.chrome-for-testing/chromedriver-linux64/chromedriver"
+DWL_DIR = "./downloads/"
+TEMP_DIR = "./temp/"
+
 class YoutubeDriver:
     def __init__(self, search_terms: str, max_results: int = 5):
         self.base_url = "https://youtube.com/results?search_query={0}"
@@ -149,3 +154,240 @@ class YoutubeDriver:
             "quiet": True,
             "logtostderr": False,
         }
+
+class ChromeDriver:
+    def __init__(self) -> None:
+        self.carbon_theme = [
+            "3024-night",
+            "a11y-dark",
+            "blackboard",
+            "base16-dark",
+            "base16-light",
+            "cobalt",
+            "duotone-dark",
+            "hopscotch",
+            "lucario",
+            "material",
+            "monokai",
+            "night-owl",
+            "nord",
+            "oceanic-next",
+            "one-light",
+            "one-dark",
+            "panda-syntax",
+            "paraiso-dark",
+            "seti",
+            "shades-of-purple",
+            "solarized+dark",
+            "solarized+light",
+            "synthwave-84",
+            "twilight",
+            "verminal",
+            "vscode",
+            "yeti",
+            "zenburn",
+        ]
+
+    def get(self):
+        if not CHROME_BIN:
+            return (
+                None,
+                "ChromeBinaryErr: No binary path found! Install Chromium or Google Chrome.",
+            )
+
+        try:
+            options = Options()
+            options.binary_location = CHROME_BIN
+            options.add_argument("--disable-dev-shm-usage")
+            options.add_argument("--ignore-certificate-errors")
+            options.add_argument("--disable-gpu")
+            options.add_argument("--headless=new")
+            options.add_argument("--test-type")
+            options.add_argument("--no-sandbox")
+            options.add_argument("--window-size=1920x1080")
+            options.add_experimental_option(
+                "prefs", {"download.default_directory": "./"}
+            )
+            service = Service(CHROME_DRIVER)
+            driver = webdriver.Chrome(options, service)
+            return driver, None
+        except Exception as e:
+            return None, f"ChromeDriverErr: {e}"
+
+    def close(self, driver: webdriver.Chrome):
+        driver.close()
+        driver.quit()
+
+    @property
+    def get_random_carbon(self) -> str:
+        url = "https://carbon.now.sh/?l=auto"
+        url += f"&t={random.choice(self.carbon_theme)}"
+        url += f"&bg=rgba%28{random.randint(1, 255)}%2C{random.randint(1, 255)}%2C{random.randint(1, 255)}%2C1%29"
+        url += "&code="
+        return url
+
+    async def generate_carbon(
+        self, driver: webdriver.Chrome, code: str, is_random: bool = False
+    ) -> str:
+        filename = f"{round(time.time())}"
+        BASE_URL = (
+            self.get_random_carbon
+            if is_random
+            else "https://carbon.now.sh/?l=auto&code="
+        )
+
+        driver.get(BASE_URL + format_text(quote_plus(code)))
+        driver.command_executor._commands["send_command"] = (
+            "POST",
+            "/session/$sessionId/chromium/send_command",
+        )
+        params = {
+            "cmd": "Page.setDownloadBehavior",
+            "params": {"behavior": "allow", "downloadPath": DWL_DIR},
+        }
+        driver.execute("send_command", params)
+
+        driver.find_element(By.XPATH, "//button[@id='export-menu']").click()
+        driver.find_element(By.XPATH, "//input[@title='filename']").send_keys(filename)
+        driver.find_element(By.XPATH, "//button[@id='export-png']").click()
+
+        return f"{DWL_DIR}/{filename}.png"
+
+class SCRAP_DATA:
+    """Class to get and handel scrapped data"""
+
+    def __init__(self, urls: list[str] | str) -> None:
+        self.urls = urls
+        self.path = "./scrapped/"
+        if not os.path.isdir(self.path):
+            os.makedirs("./scrapped/")
+
+    def get_images(self) -> list:
+        images = []
+        if isinstance(self.urls, str):
+            requested = requests.get(self.urls)
+            try:
+                name = self.path + f"img_{time.time()}.jpg"
+                with open(name, "wb") as f:
+                    f.write(requested.content)
+                images.append(name)
+            except Exception as e:
+                requested.close()
+        else:
+            for i in self.urls:
+                if i:
+                    requested = requests.get(i)
+                else:
+                    continue
+                try:
+                    name = self.path + f"img_{time.time()}.jpg"
+                    with open(name, "wb") as f:
+                        f.write(requested.content)
+                    images.append(name)
+                except Exception as e:
+
+                    requested.close()
+                    continue
+        return images
+
+    def get_videos(self) -> list:
+        videos = []
+        if isinstance(self.urls, str):
+            if i:
+                requested = requests.get(i)
+            else:
+                return []
+            try:
+                name = self.path + f"vid_{time.time()}.mp4"
+                with open(name, "wb") as f:
+                    f.write(requested.content)
+                videos.append(name)
+            except Exception as e:
+                requested.close()
+        else:
+            for i in self.urls:
+                if i:
+                    requested = requests.get(i)
+                else:
+                    continue
+                try:
+                    name = self.path + f"vid_{time.time()}.mp4"
+                    with open(name, "wb") as f:
+                        f.write(requested.content)
+                    videos.append(name)
+                except Exception as e:
+
+                    requested.close()
+                    continue
+        return videos
+
+
+class INSTAGRAM(ChromeDriver):
+    """Class to scrap data from instagram"""
+
+    def __init__(self, url: str) -> None:
+        self.url = url
+        self.article = "article._aa6a"
+        self.ul_class = "_acay"
+        self.image_class = "x5yr21d"
+        self.video_class = "x1lliihq"
+        self.next_button = "button._afxw"
+        self.return_dict = {"image": [], "video": []}
+        super().__init__()
+
+    def get_all(self):
+        driver, error = self.get()
+        if not driver:
+            return error
+
+        driver.get(self.url)
+        wait = WebDriverWait(driver, 30)
+        image_links = []
+        video_links = []
+        try:
+            element = wait.until(presence_of_element_located(
+                (By.CLASS_NAME, self.ul_class)))
+
+            while True:
+                sub_element = element.find_elements(
+                    By.CLASS_NAME, self.image_class)
+                for i in sub_element:
+                    url = i.get_attribute("src")
+                    image_links.append(url)
+
+                sub_element = element.find_elements(
+                    By.CLASS_NAME, self.video_class)
+                for i in sub_element:
+                    url = i.get_attribute("src")
+                    video_links.append(url)
+
+                try:
+                    driver.find_element(
+                        By.CSS_SELECTOR, self.next_button).click()
+                except:
+                    break
+        except:
+            element = wait.until(presence_of_element_located((By.CSS_SELECTOR, self.article)))
+            try:
+                sub_element = element.find_element(By.TAG_NAME, "img")
+                url = sub_element.get_attribute("src")
+                image_links.append(url)
+            except:
+                sub_element = element.find_element(By.TAG_NAME, "video")
+                url = sub_element.get_attribute("src")
+                video_links.append(url)
+
+        self.close(driver)
+        if image_links:
+            image_links = list(set(image_links))
+        if video_links:
+            video_links = list(set(video_links))
+            for i in video_links:
+                image_links.remove(i)
+
+        self.return_dict.get("image").extend(image_links)
+        self.return_dict.get("video").extend(video_links)
+        return self.return_dict
+
+
+Driver = ChromeDriver()

instagram.py

@@ -0,0 +1,78 @@
+import io
+import requests
+import os
+import re
+import uuid
+from PIL import Image, ImageEnhance
+from fastapi import APIRouter, Depends
+from fastapi.responses import StreamingResponse
+from fastapi import UploadFile
+from fastapi.responses import JSONResponse
+from fastapi import HTTPException
+from dotenv import load_dotenv
+from pydantic import BaseModel
+from pymongo import MongoClient
+from models import *
+from driver import Driver
+from huggingface_hub import InferenceClient
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.expected_conditions import (
+    presence_of_element_located, visibility_of_element_located)
+from selenium.webdriver.support.wait import WebDriverWait
+
+
+class FluxAI(BaseModel):
+    user_id: int
+    args: str
+    auto_enhancer: bool = False
+
+class MistralAI(BaseModel):
+    args: str
+
+router = APIRouter()
+
+def obtain_ids(user: str):
+    response = requests.get("https://www.instagram.com/" + user)
+    appid = re.search(r'appId":"(\d*)', response.text)[1]
+    serverid = re.search(r'server_revision":(\d*)', response.text)[1]
+    return appid, serverid
+
+@router.post("/akeno/instagram/reels", response_model=SuccessResponse, responses={422: {"model": SuccessResponse}})
+async def instagram_reels(payload: InstagramX):
+    isInstagramLink = lambda link: bool(
+        re.match(r"^https?://(?:www\.)?instagram\.com/reel/", link)
+    )
+    if not isInstagramLink(payload.link):
+        return SuccessResponse(
+            status="False",
+            randydev={"error": "Give a valid Instagram reels link."}
+        )
+    try:
+        driver, error_message = Driver.get()
+        if not driver:
+            return SuccessResponse(
+                status="False",
+                randydev={"error": error_message}
+            )
+        driver.get(payload.link)
+        wait = WebDriverWait(driver, 10)
+        element = wait.until(presence_of_element_located((By.TAG_NAME, "video")))
+        reels_url = element.get_attribute("src")
+        driver.quit()
+        if reels_url:
+            binary_content = requests.get(reels_url).content
+            file_name = f"reels_{int(time.time())}.mp4"
+            with open(file_name, "wb") as file:
+                file.write(binary_content)
+            with open(file_name, "rb") as video:
+                encoded_string = base64.b64encode(video.read()).decode('utf-8')
+            os.remove(file_name)
+            return SuccessResponse(
+                status="True",
+                randydev={"video_data": encoded_string}
+            )
+    except Exception as e:
+        return SuccessResponse(
+            status="False",
+            randydev={"error": f"An error occurred: {str(e)}"}
+        )

main.py

@@ -86,6 +86,7 @@ import logging
 import functions as code
 from fluxai import router as fluxai_router
 from whisper import router as whisper_router
+from instagram import router as instagram_router
 from driver import YoutubeDriver
 from yt_dlp import YoutubeDL
 
@@ -133,6 +134,7 @@ trans = SyncTranslator()
 app = FastAPI(docs_url=None, redoc_url="/")
 app.include_router(fluxai_router, prefix="/api/v1")
 app.include_router(whisper_router, prefix="/api/v1")
+app.include_router(instagram_router, prefix="/api/v1")
 
 timeout = 100