Initial commit: Add webtoon downloader

downloaders/kakao_webtoon.py

@@ -0,0 +1,141 @@
+from pathlib import Path
+import random
+import sys
+import time
+
+from bs4 import BeautifulSoup
+from httpx import AsyncClient, RequestError, HTTPStatusError
+import httpx
+import requests
+from data.path_constant import DOWNLOAD_DIR, DOWNLOAD_LIST_TXT
+from data.kakao_cookie import Cookie
+from data.kakao_request import KakaoRequest
+from downloaders.decrypt import Decrypt
+from downloaders.downloader import Downloader
+
+
+class KakaoWebtoon(Downloader):
+    def __init__(self, webtoon_id: int, cookie: Cookie):
+        super().__init__(webtoon_id)
+        self._timestamp = int(time.time() * 1000)
+        chars = [*range(0x30, 0x3A), *range(0x61, 0x7B)]
+        self._nonce = "".join(chr(i) for i in random.choices(chars, k=10))
+        
+        self.kakaoRequest = KakaoRequest(self._timestamp, self._nonce)
+        self.cookie = cookie
+        self.episode_headers = self.kakaoRequest.get_episode_headers(self.cookie.ant)
+        self.post_headers = self.kakaoRequest.get_post_headers(self.cookie.ant)
+
+    def verify_cookie(self) -> bool:
+        url = f"https://gateway.tw.kakaowebtoon.com/episode/v2/views/content-home/contents/{self.webtoon_id}/episodes?sort=-NO&offset=0&limit=30"
+        res = requests.get(url, headers=self.episode_headers)
+        return res.status_code == 200
+
+    def _fetch_information(self, url):
+        res = requests.get(url, headers=self.episode_headers)
+        
+        if res.status_code == 200:
+            soup = BeautifulSoup(res.content, 'html.parser')
+            description = soup.find('meta', attrs={'name': 'description'})
+            if description:
+                self.description = description.get('content')
+            thumbnail_url = soup.find('meta', attrs={'property': 'og:image'})
+            if thumbnail_url:
+                self.thumbnail_url = thumbnail_url.get('content')
+
+            all_p = soup.find_all('p')
+
+            self.title = all_p[0].get_text()
+            self.author = all_p[1].get_text()
+            self.tag = all_p[2].get_text()
+            self.thumbnail_name = self.webtoon_id + '.' + self.thumbnail_url.split('.')[-1]
+
+    def _fetch_episode_information(self):
+        offset = 0
+        limit = 30
+        is_last: bool = False
+        webtoon_episodes_data = []
+        while not is_last:
+            url = f"https://gateway.tw.kakaowebtoon.com/episode/v2/views/content-home/contents/{self.webtoon_id}/episodes?sort=-NO&offset={offset}&limit={limit}"
+            res = requests.get(url, headers=self.episode_headers)
+            if res.status_code == 200:
+                json_data = res.json()
+
+                webtoon_episodes_data += json_data["data"]["episodes"]
+                offset += limit
+                is_last = json_data["meta"]["pagination"]["last"]
+            else:
+                print("_fetch_episode_information")
+                print(self.cookie.name)
+                print(res.status_code)
+                sys.exit()
+
+
+        episode_ids: list[int] = []
+        seo_ids: list[str] = []
+        numbers: list[int] = []
+        episode_titles: list[str] = []
+        readablities: list[bool] = []
+        
+        for information in reversed(webtoon_episodes_data):
+            episode_ids.append(information["id"])
+            seo_ids.append(information["seoId"])
+            numbers.append(information["no"])
+            episode_titles.append(information["title"])
+            readablities.append(information["readable"])
+
+        
+        self.episode_ids = episode_ids
+        self.seo_ids = seo_ids
+        self.episode_titles = episode_titles
+        self.readablities_index_list = [index for index, value in enumerate(readablities) if value == True]    
+    
+    def _get_episode_image_urls(self, episode_index) -> list[tuple[str, bytes, bytes]] | None:
+        episode_id = self.episode_ids[episode_index]
+                
+        url = f"https://gateway.tw.kakaowebtoon.com/episode/v1/views/viewer/episodes/{episode_id}/media-resources"
+        payload = self.kakaoRequest.get_payload(episode_id)
+        res = requests.post(url, headers=self.post_headers, json=payload)
+
+        data = res.json()["data"]
+
+        aid = data["media"]["aid"]
+        zid = data["media"]["zid"]
+        
+        self.decrypt = Decrypt(aid, episode_id, self._timestamp, self._nonce, self.cookie.userID, zid)
+        key, iv = self.decrypt.get_decrypt_infomations()
+
+        return [(i["url"], key, iv) for i in data["media"]["files"]]
+    
+    async def _download_image(
+        self,
+        episode_path: Path,
+        url: tuple[str, bytes, bytes],
+        image_no: int
+    ) -> None:
+        real_url, key, iv = url
+        file_extension = 'webp'
+        file_name = f"{image_no:03d}.{file_extension}"
+        file_path = episode_path /file_name
+        
+        try:
+            image_raw: bytes = (await self.client.get(real_url, headers=self.episode_headers)).content
+        except httpx.RequestError as e:
+            print(f"An error occurred while requesting {url}: {e}")
+        except httpx.HTTPStatusError as e:
+            print(f"HTTP error occurred: {e}")
+        except httpx.TimeoutException as e:
+            print(f"Timeout error occurred: {e}")
+        except httpx.UnsupportedProtocol as e:
+            print(f"Unsupported protocol error occurred: {e}")
+        except Exception as e:
+            print(f"An unexpected error occurred: {e}")
+        except Exception as e:
+            print(f"Error get image_raw: {file_path}: {e}")
+    
+        decrypted_data = self.decrypt._decrypt(image_raw, key, iv)
+
+        file_path.write_bytes(decrypted_data)
+
+    async def close(self):
+        await self.client.aclose()