modify scripts

scrapy_proj/cmd.txt

@@ -1,54 +0,0 @@
-1010  scrapy crawl iafd -a debug=1 -s STATS_EXPORT_INTERVAL=60
- 1011  scrapy crawl u3c3 -a debug=1 -s STATS_EXPORT_INTERVAL=60
- 1012  scrapy crawl iafd -a debug=1 cmd=performers -s STATS_EXPORT_INTERVAL=60
- 1014  scrapy crawl --help
- 1015  scrapy crawl iafd -a debug=1 -a cmd=performers -s STATS_EXPORT_INTERVAL=60
- 1016  scrapy crawl u3c3 -s STATS_EXPORT_INTERVAL=60 -s DEBUG=True
- 1017  scrapy crawl u3c3 -a debug=1 -s STATS_EXPORT_INTERVAL=60
- 1018  scrapy crawl iafd -a debug=1 -a cmd=performers -s STATS_EXPORT_INTERVAL=60
- 1019  scrapy crawl u3c3 -a debug=1 -s STATS_EXPORT_INTERVAL=60
- 1020  scrapy crawl u3c3
- 1021  scrapy crawl u3c3 -a debug=1 -s STATS_EXPORT_INTERVAL=60
- 1022  scrapy crawl u3c3 -a debug=1 -s STATS_EXPORT_INTERVAL=60 -s LOG_LEVEL=DEBUG
- 1023  scrapy crawl u3c3 -a debug=1 -s STATS_EXPORT_INTERVAL=60 -s LOG_LEVEL='DEBUG'
- 1024  scrapy crawl u3c3 -a debug=1 -s STATS_EXPORT_INTERVAL=60 
- 1025  scrapy crawl sis -a debug=1 -s STATS_EXPORT_INTERVAL=60 
- 1026  scrapy crawl sis -a debug=1 -s STATS_EXPORT_INTERVAL=60 -s LOG_LEVEL='DEBUG'
- 1027  scrapy crawl sis -a debug=1 -s STATS_EXPORT_INTERVAL=60
- 1028  scrapy crawl iafd -a debug=1 -a cmd=performers -s STATS_EXPORT_INTERVAL=60
- 1029  scrapy crawl --help
- 1034  cd projects/resources/scrapy_proj/
- 1037  scrapy crawl sis 
- 1038  scrapy crawl sis -a debug=1 -s STATS_EXPORT_INTERVAL=60
- 1039  scrapy crawl iafd -a debug=1 -a cmd=performers -s STATS_EXPORT_INTERVAL=60
- 1040  scrapy crawl u3c3 -a debug=1 -s STATS_EXPORT_INTERVAL=60 
- 1041  scrapy crawl iafd -a debug=1 -a cmd=performers -s STATS_EXPORT_INTERVAL=60
- 1042  scrapy crawl sis -a debug=1 -s STATS_EXPORT_INTERVAL=60
- 1043  scrapy crawl sis
- 1044  scrapy crawl sis -a debug=1 -s STATS_EXPORT_INTERVAL=60
- 1045  scrapy crawl iafd -a debug=1 -a cmd=performers -s STATS_EXPORT_INTERVAL=60
- 1046  scrapy crawl sis -a debug=1 -s STATS_EXPORT_INTERVAL=60
- 1047  scrapy crawl u3c3 -a debug=1 -s STATS_EXPORT_INTERVAL=60 
- 1048  scrapy crawl u3c3 -a begin=2025-07-04
- 1049  scrapy crawl u3c3 -a begin='2025-07-04'
- 1050  scrapy crawl sis -a begin='2025-07-04'
- 1051  scrapy crawl u3c3 -a begin='2025-07-04'
- 1052  scrapy crawl sis -a begin='2025-07-04'
- 1053  scrapy crawl u3c3 -a debug=1 -s STATS_EXPORT_INTERVAL=60 
- 1054  scrapy crawl sis -a debug=1 -s STATS_EXPORT_INTERVAL=60
- 1055  scrapy crawl iafd -a debug=1 -a cmd=performers -s STATS_EXPORT_INTERVAL=60
- 1056  scrapy crawl u3c3 -a debug=1 -s STATS_EXPORT_INTERVAL=60 -s LOG_LEVEL=DEBUG
- 1057  scrapy crawl iafd -a debug=1 -a cmd=performers -s STATS_EXPORT_INTERVAL=60 -s LOG_LEVEL=DEBUG
- 1058  scrapy crawl pbox -s LOG_LEVEL=DEBUG
- 1059  scrapy crawl pbox
- 1060  scrapy crawl pbox -a debug=1 
- 1061  scrapy crawl pbox -a debug=1 -s LOG_LEVEL=DEBUG
- 1064  scrapy crawl pbox -a debug=1 -s LOG_LEVEL=DEBUG
- 1067  scrapy crawl pbox -a debug=1 -s LOG_LEVEL=DEBUG
- 1068  scrapy crawl pbox -a debug=1 
- 1070  scrapy crawl pbox -a debug=1 cmd=studio
- 1071  scrapy crawl pbox -a debug=1 -a cmd=studio
- 1072  scrapy crawl pbox -a debug=1 -a cmd=movies
- 1073  scrapy crawl pbox -a debug=1 -a cmd=studio
- 1074  scrapy crawl pbox -a debug=1 -a cmd=movies
- 1094  sqlite3 ~/sharedata/sqlite/scrapy.db '.schema' > ./sqlite_tools/scrapy_db_schema.sql

scrapy_proj/scrapy_proj/db_wapper/spider_db_handler.py

@@ -1119,12 +1119,23 @@ class IAFDDBHandler(SQLiteDBHandler):
             # 插入影片列表，可能有 personal 和 director 两个身份
             if movies_update:
                 credits = data.get('credits', {})
+                # 强制转换为字典（防止非字典类型）
+                if not isinstance(credits, dict):
+                    credits = {}
                 for role, movies in credits.items():
+                    # 确保movies是可迭代对象（列表/元组），否则跳过
+                    if not isinstance(movies, (list, tuple)):
+                        continue
                     if movies:
                         for movie in movies:
                             movie_id = self.get_id_by_key(tbl=self.tbl_name_movies, uniq_key='href', val=movie['href'])
                             # 影片不存在，先插入
                             if movie_id is None:
+                                release_year=0
+                                try:
+                                    release_year=int(movie['year'])
+                                except Exception as e:
+                                    release_year=0
                                 movie_id = self.insert_movie_index(movie['title'], movie['href'], release_year=int(movie['year']), from_performer_list=1)
                             if movie_id:
                                 tmp_id = self.insert_performer_movie(performer_id, movie_id, role, movie['notes'])