diff --git a/javdb/src/fetch.py b/javdb/src/fetch.py index ca42e7b..738b477 100644 --- a/javdb/src/fetch.py +++ b/javdb/src/fetch.py @@ -165,7 +165,7 @@ def fetch_performers_detail(): all_movies = [] while next_url: logging.info(f"Fetching data for actor ({person}), url {next_url} ...") - soup, status_code = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="div", identifier="movie-list h cols-4 vcols-5", attr_type="class")) + soup, status_code = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="span", identifier="actor-section-name", attr_type="class")) if soup: data, next_url = scraper.parse_actor_detail(soup, next_url) if data: diff --git a/javdb/src/scraper.py b/javdb/src/scraper.py index 644a63c..0dafe1c 100644 --- a/javdb/src/scraper.py +++ b/javdb/src/scraper.py @@ -166,8 +166,11 @@ def parse_actor_detail(soup, href): # 返回数据 actor = {} - - div_movies = soup.find("div", class_='movie-list h cols-4 vcols-5') + + # 使用正则表达式查找 class 包含 'movie-list h cols-4' 的 div 元素 + div_movies = soup.find("div", class_=re.compile(r'movie-list h cols-')) + #div_movies = soup.find("div", class_='movie-list h cols-4 vcols-5') + #div_movies = soup.find("div", class_='movie-list h cols-4 vcols-8') if not div_movies: logging.warning(f"Warning: No movies div found ") return None, None