CEDA/economic/EPU.py

@@ -3,8 +3,9 @@ import requests
 import pandas as pd
 
 url = {
-    "EPU-China": "https://www.policyuncertainty.com/scmp_monthly.html",
-    "EPU-HKSAR": "https://www.policyuncertainty.com/hk_monthly.html",
+    "EPU-China": "https://economicpolicyuncertaintyinchina.weebly.com",
+    "EPU-HKSAR": "https://economicpolicyuncertaintyinchina.weebly.com/epu-in-hong-kong.html",
+    "EPU-MACAUSAR": "https://economicpolicyuncertaintyinchina.weebly.com/epu-in-macao.html",
     "EPU": "https://www.policyuncertainty.com/"
 }
 
@@ -51,6 +52,20 @@ class EPUData(object):
                 output_data.append(pd.read_excel(urls_data[i]))
             
             return {"data":output_data, "reference":urls_cite}
+
+        elif self.country == "MACAUSAR":
+            r = requests.get(url["EPU-MACAUSAR"])
+            webpage = html.fromstring(r.content)
+            urls = pd.Series(webpage.xpath("//a/@href"))
+            urls_data = urls[urls.str.contains("xlsx")]
+            urls_cite = urls[urls.str.contains("pdf")]
+            urls_data = [url["EPU-China"] + i for i in urls_data]
+            urls_cite = [url["EPU-China"] + i for i in urls_cite]
+            output_data = []
+            for i in range(0, len(urls_data)):
+                output_data.append(pd.read_excel(urls_data[i]))
+            
+            return {"data":output_data, "reference":urls_cite}
         
         else:
             r = requests.get(url["EPU"] + self.country.lower() + "_monthly.html")