commit

downloaders/bomtoon.py

@@ -1,62 +0,0 @@
-
-from pathlib import Path
-from typing import TYPE_CHECKING
-from bs4 import BeautifulSoup
-import httpx
-import requests
-from data.path_constant import DOWNLOAD_DIR
-from data.webtoon_request import get_bomtoon_headers
-from downloaders.downloader import Downloader
-
-
-class Bomtoon(Downloader):
-    def __init__(self, webtoon_id):
-        super().__init__(webtoon_id)
-        
-        self.headers = get_bomtoon_headers()
-
-    def _fetch_information(self, url):
-        res = requests.get(url, headers=self.headers)
-        
-        if res.status_code == 200:
-            soup = BeautifulSoup(res.content, 'html.parser')
-            title = soup.find('title')
-            if title:
-                self.title = title.get_text().split('-')[0].strip()
-
-            author = soup.find('meta', attrs={'name': 'author'})
-            if author:
-                self.author = author.get('content')
-            
-            description = soup.find('meta', attrs={'property': 'og:description'})
-            if description:
-                self.description = description.get('content')
-
-            tags = soup.find('meta', attrs={'name': 'keywords'})
-            if tags:
-                tags_list = tags.get('content').split(',')
-                if '連載' in tags_list[0]:
-                    self.tag = tags_list[1]
-                else:
-                    self.tag = tags_list[0]
-
-            self.thumbnail_url = ""
-            self.thumbnail_name = self.webtoon_id + '.jpg'
-        else:
-            print(f"fetch_information: {res.status_code}")
-
-
-    def _fetch_episode_information(self):
-        pass
-
-
-    def _get_episode_image_urls(self, episode_index) -> list[str]:
-        pass
-    
-    async def _download_image(
-        self,
-        episode_path: Path,
-        url: str,
-        image_no: int
-    ) -> None:
-        pass

downloaders/decrypt.py

@@ -1,8 +1,7 @@
 import base64
 import hashlib
 from contextlib import suppress
-
-from WebtoonScraper.exceptions import MissingOptionalDependencyError
+# from Cryptodome.Cipher import AES
 
 class Decrypt :
     def __init__(self, aid, episodeId, timestamp, nonce, userId, zid):
@@ -18,7 +17,7 @@ class Decrypt :
         with suppress(AttributeError):
             return cls.AES
         try:
-            from Cryptodome.Cipher import AES
+            from Crypto.Cipher import AES
         except ImportError:
             raise ImportError("Missing optional dependency 'pycryptodomex'. Please install it to use this functionality.")
         

downloaders/downloader.py

@@ -2,7 +2,7 @@ import asyncio
 import html
 import json
 from pathlib import Path
-import pyfilename as pf
+#import pyfilename as pf
 import shutil
 import time
 from httpx import AsyncClient
@@ -53,11 +53,13 @@ class Downloader:
         if information_path.exists():
             with open(information_path, "r", encoding='utf-8') as json_file:
                 existing_information = json.load(json_file)
+                if (self.author == ""):
+                    save_necessary = False
                 if (
                     existing_information["title"] == self.title and
                     existing_information["author"] == self.author and
                     existing_information["description"] == self.description and
-                    existing_information["thumbnail_name"] == self.thumbnail_name
+                    existing_information["thumbnail"] == self.thumbnail_name
                 ):
                     save_necessary = False
         if (save_necessary):
@@ -66,7 +68,7 @@ class Downloader:
                 "author": self.author,
                 "tag": self.tag,
                 "description": self.description,
-                "thumbnail_name": self.thumbnail_name
+                "thumbnail": self.thumbnail_name
             }
 
             with open(information_path, 'w', encoding='utf-8') as json_file:
@@ -91,10 +93,15 @@ class Downloader:
 
     def _get_unobtained_episodes(self) -> list[int]:
         downloaded_episodes = []
-
+        
         for dir in self.webtoon_path.glob('*'):
             if dir.is_dir():
                 downloaded_episodes.append(int(dir.name.split('.')[0]))
+            
+        if self.title == "反派角色只有死亡結局":
+            downloaded_episodes = [i - 2 for i in downloaded_episodes]
+        if self.title == "成為我筆下男主角的妻子" or self.title == "領主夫人罷工中":
+            downloaded_episodes = [i - 1 for i in downloaded_episodes]
         
         if self.title in WEBTOON_18_BONUS:
             count = len(self.readablities_index_list) - len(downloaded_episodes)
@@ -114,6 +121,10 @@ class Downloader:
             for episode_index in episode_index_list:
                 episode_name = self.episode_titles[episode_index]
                 episode_title = self._get_safe_file_name(episode_index, episode_name)
+                if self.title == "反派角色只有死亡結局":
+                    episode_title = self._get_safe_file_name(episode_index + 2, episode_name)
+                if self.title == "成為我筆下男主角的妻子" or self.title == "領主夫人罷工中":
+                    episode_title = self._get_safe_file_name(episode_index + 1, episode_name)
                 # episode_title = self._get_safe_file_name(f"{episode_index}.{self.episode_titles[episode_index]}")
                 print(episode_title)
                 episode_path = self.webtoon_path / episode_title
@@ -165,4 +176,4 @@ class Downloader:
 
         episode_title = f"{episode_index}.{episode_name}"
 
-        return pf.convert(html.unescape(episode_title))
+        return html.unescape(episode_title)

downloaders/kakao_webtoon.py

@@ -10,6 +10,7 @@ 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 data.special_list import KAKAO_TO_TW
 from downloaders.decrypt import Decrypt
 from downloaders.downloader import Downloader
 
@@ -27,7 +28,7 @@ class KakaoWebtoon(Downloader):
         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"
+        url = f"https://gateway.webtoon.kakao.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
 
@@ -39,15 +40,22 @@ class KakaoWebtoon(Downloader):
             description = soup.find('meta', attrs={'name': 'description'})
             if description:
                 self.description = description.get('content')
+            self.description = ""
             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()
+            title = all_p[0].get_text()
+            if title in KAKAO_TO_TW:
+                self.title = KAKAO_TO_TW.get(title)
+                self.author = ""
+                self.tag = ""
+            else:
+                self.title = title 
+                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):
@@ -56,7 +64,7 @@ class KakaoWebtoon(Downloader):
         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}"
+            url = f"https://gateway-kw.kakao.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()
@@ -88,15 +96,15 @@ class KakaoWebtoon(Downloader):
         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]    
-    
+        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"
+        url = f"https://gateway-kw.kakao.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"]