def translate_movie_info(info: MovieInfo):
"""根据配置翻译影片信息"""
# 翻译标题
if info.title and cfg.Translate.translate_title:
result = translate(info.title, cfg.Translate.engine, info.actress)
if 'trans' in result:
info.ori_title = info.title
info.title = result['trans']
# 如果有的话，附加断句信息
if 'orig_break' in result:
setattr(info, 'ori_title_break', result['orig_break'])
if 'trans_break' in result:
setattr(info, 'title_break', result['trans_break'])
else:
logger.error('翻译标题时出错: ' + result['error'])
return False
# 翻译简介
if info.plot and cfg.Translate.translate_plot:
result = translate(info.plot, cfg.Translate.engine, info.actress)
if 'trans' in result:
# 只有翻译过plot的影片才可能需要ori_plot属性，因此在运行时动态添加，而不添加到类型定义里
setattr(info, 'ori_plot', info.plot)
info.plot = result['trans']
else:
logger.error('翻译简介时出错: ' + result['error'])
return False
return True
def info_summary(movie: Movie, all_info):
"""汇总多个来源的在线数据生成最终数据"""
final_info = MovieInfo(movie)
########## 部分字段配置了专门的选取逻辑，先处理这些字段 ##########
# genre
if 'javdb' in all_info:
final_info.genre = all_info['javdb'].genre
########## 然后检查所有字段，如果某个字段还是默认值，则按照优先级选取数据 ##########
# parser直接更新了all_info中的项目，而初始all_info是按照优先级生成的，已经符合配置的优先级顺序了
# 按照优先级取出各个爬虫获取到的信息
attrs = [i for i in dir(final_info) if not i.startswith('_')]
covers, big_covers = [], []
for name, data in all_info.items():
absorbed = []
# 遍历所有属性，如果某一属性当前值为空而爬取的数据中含有该属性，则采用爬虫的属性
for attr in attrs:
incoming = getattr(data, attr)
if attr == 'cover':
if incoming and (incoming not in covers):
covers.append(incoming)
absorbed.append(attr)
elif attr == 'big_cover':
if incoming and (incoming not in big_covers):
big_covers.append(incoming)
absorbed.append(attr)
else:
current = getattr(final_info, attr)
if (not current) and (incoming):
setattr(final_info, attr, incoming)
absorbed.append(attr)
if absorbed:
logger.debug(f"从'{name}'中获取了字段: " + ' '.join(absorbed))
setattr(final_info, 'covers', covers)
setattr(final_info, 'big_covers', big_covers)
# 对cover和big_cover赋值，避免后续检查必须字段时出错
if covers:
final_info.cover = covers[0]
if big_covers:
final_info.big_cover = big_covers[0]
########## 部分字段放在最后进行检查 ##########
# title
if cfg.Crawler.title__chinese_first and 'airav' in all_info:
if all_info[
'airav'].title and final_info.title != all_info['airav'].title:
final_info.ori_title = final_info.title
final_info.title = all_info['airav'].title
# 检查是否所有必需的字段都已经获得了值
for attr in cfg.Crawler.required_keys:
if not getattr(final_info, attr, None):
logger.error(f"所有爬虫均未获取到字段: '{attr}'，抓取失败")
return False
# 必需字段均已获得了值：将最终的数据附加到movie
movie.info = final_info
return True
def parse_clean_data(movie: MovieInfo):
"""解析指定番号的影片数据并进行清洗"""
success = parse_data(movie)
if not success:
return
movie.genre_norm = genre_map.map(movie.genre_id)
movie.genre_id = None # 没有别的地方需要再用到，清空genre id（表明已经完成转换）
# 将此功能放在各个抓取器以保持数据的一致，避免影响转换（写入nfo时的信息来自多个抓取器的汇总，数据来源一致性不好）
if cfg.Crawler.title__remove_actor:
new_title = remove_trail_actor_in_title(movie.title, movie.actress)
if new_title != movie.title:
movie.ori_title = movie.title
movie.title = new_title