diff --git a/utils/scraper.py b/utils/scraper.py index 7a63a5a..d9caaba 100644 --- a/utils/scraper.py +++ b/utils/scraper.py @@ -18,6 +18,9 @@ from .typings import BoardPath, SearchType from models import Attachment, Post +LIST_MAX_POSTS = 200 + + class Scraper(ClientSession): def __init__(self, *args, **kwargs): @@ -29,7 +32,7 @@ class Scraper(ClientSession): # 게시글 목록 조회로 한 번에 불러올 항목 수 self.cookie_jar.update_cookies({ - 'list_count': '200' + 'list_count': LIST_MAX_POSTS }) async def __aenter__(self) -> 'Scraper': @@ -84,7 +87,7 @@ class Scraper(ClientSession): for tag in document.select('.gall-detail-lnktb') ] - async def view(self, post: Post): + async def view(self, post: Post) -> Post: """ 게시글 내용을 조회합니다 @@ -137,8 +140,8 @@ class Scraper(ClientSession): # 불필요한 본문 요소 제거 for tag in post.body.select('script, style'): tag.extract() - - print(f'{post.board_id}/{post.id}: {post.title}') + + return post async def fetch_voice(self, id: str): """