vieles

scrape_bev.py

@@ -1,16 +1,50 @@
 import requests
 from bs4 import BeautifulSoup
+import db_model as db
+import datetime
 
-countrys = ["Germany"]
 
+TYP = "prozent_bev"
 URL = "https://countrymeters.info/en/"
 
 
+def letzten_eintrag_ermitteln(quelle, country_region):
+    ts = db.CoronaStatistik.select(
+        db.CoronaStatistik.ts).where((db.CoronaStatistik.typ == TYP) &
+                                     (db.CoronaStatistik.quelle == quelle) &
+                                     (db.CoronaStatistik.country_region == country_region)
+                                     ).order_by(db.CoronaStatistik.ts.desc()).limit(1).scalar()
+    if ts is None:
+        ts = datetime.datetime(1970, 1, 1)
+    return ts
+
+
+def auslesen_unverarbeiteter_daten(quelle, land, bev_zahl, CoronaStatistik):
+    ts = letzten_eintrag_ermitteln(quelle, land)
+    daten = []
+    query = db.CoronaDaten.select(db.CoronaDaten.ts, db.CoronaDaten.confirmed).where(
+        (db.CoronaDaten.quelle == quelle) & (db.CoronaDaten.country_region == land) & (
+                    db.CoronaDaten.ts > ts)).namedtuples()
+    for datensatz in query:
+        prozent_bev = datensatz.confirmed / bev_zahl[land] * 100
+        prozent_bev = round(prozent_bev, 8)
+        print(f"Im Land {land} {prozent_bev}% infiziert")
+        daten.append(CoronaStatistik(datensatz.ts, quelle, land, TYP, prozent_bev))
+    return daten
+
+
 def scrape_bev(land):
     r = requests.get(f"{URL}{land}")
     soup = BeautifulSoup(r.text, features="html5lib")
     table = soup.find("div", {"id": "cp1"})
-    print(table)
+    try:
+        value = table.get_text()
+    except AttributeError:
+        value = None
+    else:
+        value = int(value.replace(",", ""))
+    return value
 
 
-scrape_bev("Germany")
+if __name__ == "__main__":
+    scrape_bev("Germany")