cnki:测试:同一个筛选类型可以加入多个筛选项

science_article_cnki/starter/crawl_signal_result.py

@@ -0,0 +1,49 @@
+# -*- coding: utf-8 -*-
+# @Time    : 2026/1/6 14:31
+# @Author  : zhaoxiangpeng
+# @File    : crawl_signal_result.py
+from twisted.internet import defer
+from scrapy.crawler import CrawlerProcess
+from scrapy.utils.project import get_project_settings
+from science_article_cnki.spiders.cnki_article_tag_source import CnkiArticleTagSourceSpider
+
+"""
+def test_starter():
+    y = 2024
+    init_params = {
+        'query': '（作者单位：西南科技大学(模糊)）',
+        'query_condition': {'year': str(y)}
+    }
+
+    process = CrawlerProcess(get_project_settings())
+    process.crawl(CnkiArticleTagSourceSpider, **init_params)
+    process.start()
+"""
+
+
+def starter_by_year():
+    @defer.inlineCallbacks
+    def f(range_list: list = None):
+        for y in range_list:
+            init_params = {
+                'query': '（作者单位：西南科技大学(模糊)）',
+                'query_condition': {'year': str(y)},
+                'filters': [
+                    dict(project="年度", value=f"{y}", text_or_title=f"{y}年"),
+                ]
+            }
+            yield process.crawl(CnkiArticleTagSourceSpider, **init_params)
+
+    process = CrawlerProcess(get_project_settings())
+    f(list(range(2000, 2001)))
+    process.start()
+
+
+def starter():
+    process = CrawlerProcess(get_project_settings())
+    process.crawl(CnkiArticleTagSourceSpider)
+    process.start()
+
+
+if __name__ == '__main__':
+    starter_by_year()

science_article_cnki/tests/test_queryJson.py

@@ -0,0 +1,34 @@
+# -*- coding: utf-8 -*-
+# @Time    : 2026/1/9 15:27
+# @Author  : zhaoxiangpeng
+# @File    : test_queryJson.py
+
+from pprint import pprint
+from science_article_cnki.models import cnki_model as model
+
+
+def test_add_con():
+    years = [2022, 2023, 2024]
+    init_params = {
+        'query': '（作者单位：西南科技大学(模糊)）',
+        'filters': [
+            dict(project="年度", value=years, text_or_title=[f"{y}年" for y in years])
+        ]
+    }
+    m = init_params
+    filters = m.get('filters')
+    query_body = model.adv_refine_search(**m)
+    for f in filters:
+        model.add_muti_group(**f, base_query=query_body)
+
+    f2 = dict(project="年度", value=2025, text_or_title=f"{2025}年")
+    model.add_muti_group(**f2, base_query=query_body)
+
+    f3 = dict(project="年度", value=[2023, 2025], text_or_title=["2023年", "2025年"])
+    model.add_muti_group(**f3, base_query=query_body)
+
+    # f4 = dict(project="来源类别", value="CSSCI", text_or_title="CSSCI")
+    # model.add_muti_group(**f4, base_query=query_body)
+
+    pprint(query_body)
+    return query_body