cnki:通过id下载

science_article_cnki/science_article_cnki/spiders/cnki_ids_download.py

@@ -0,0 +1,30 @@
+from typing import Any, List, Dict, Self, AsyncIterator
+
+import scrapy
+from scrapy.crawler import Crawler
+from science_article_cnki.models import cnki_model as model
+from science_article_cnki.configs import cnki as config
+
+
+class CnkiIdsDownloadSpider(scrapy.Spider):
+    name = "cnki_ids_download"
+    allowed_domains = ["cnki.net"]
+    start_urls = ["https://cnki.net"]
+
+    @classmethod
+    def from_crawler(cls, crawler: Crawler, *args: Any, **kwargs: Any) -> Self:
+        return super().from_crawler(crawler, *args, **kwargs)
+
+    def __init__(self):
+        scrapy.Spider.__init__(self)
+        self.id_list: List[Dict[str, str]] = None
+
+    async def start(self):
+        yield scrapy.FormRequest(
+            config.CNKI_EXPORT_XLS_OLD_API,
+            method='POST',
+            formdata=model.export_data(ids),
+        )
+
+    def parse(self, response):
+        pass