✨ feat: Add AAAI as a new data source

backend/app/app/source/AAAI.py

@@ -0,0 +1,50 @@
+from typing import Any
+
+from scrapy.http import HtmlResponse
+
+from app.source.base import PaperRequestsTask
+
+import xml.dom.minidom
+
+
+class AAAI(PaperRequestsTask):
+    url: str = (
+        "https://dblp.uni-trier.de/search/publ/api?q=toc%3Adb/conf/aaai/aaai2023.bht%3A&h=1000&format=xml"
+    )
+    name: str = "AAAI"
+
+    @staticmethod
+    def parse_urls(response: HtmlResponse) -> list[str]:
+        _xml = response.text
+        domTree = xml.dom.minidom.parseString(_xml)
+        collection = domTree.documentElement
+
+        hits = collection.getElementsByTagName("hit")
+        urls = []
+        for hit in hits:
+            url = hit.getElementsByTagName("ee")[0]
+            urls.append(url.childNodes[0].data)
+        return urls
+
+    @staticmethod
+    def parse(response: HtmlResponse):
+        item = {
+            "title": response.css("h1.page_title::text").get().strip(),  # type: ignore
+            "abstract": response.css("section.abstract::text").getall()[1].strip(),  # type: ignore
+            "url": response.css("a.pdf::attr(href)").get(),
+            "keywords": response.css("section.keywords span.value::text")
+            .get()
+            .replace("\t", "")  # type: ignore
+            .replace("\n", "")
+            .split(", "),
+            "authors": response.css("span.name::text").getall(),
+        }
+
+        return item
+
+    @staticmethod
+    def post_parse(item: dict[str, Any]) -> dict[str, Any]:
+        if item["authors"] is not None:
+            for i, author in enumerate(item["authors"]):
+                item["authors"][i] = author.strip()
+        return item

backend/app/app/source/__init__.py

@@ -1,6 +1,8 @@
+from app.source.AAAI import AAAI
 from app.source.Arxiv import Arxiv
 from app.source.ICLR import ICLR
 from app.source.ICML import ICML
 from app.source.NIPS import NIPS
+from app.source.PMLR import PMLR
 
-__all__ = ["NIPS", "ICLR", "ICML", "Arxiv"]
+__all__ = ["NIPS", "ICLR", "ICML", "Arxiv", "AAAI", "PMLR"]