Emergency script for Anthology that was abanonded. CSV updates. HackerRank notes

Scripts/API_Tests/antho-map-domains-from-csv.py

@@ -0,0 +1,52 @@
+import pandas as pd
+import requests
+import Apikeys
+
+MASTER = "~/Downloads/Anthology-Master-CSV-FirstChanges.csv"
+BASEURL = "https://api.northpass.com/v2/people"
+APIKEY = Apikeys.ANTHOLOGY
+HEADERS = {
+    "accept": "*/*",
+    "X-Api-Key": APIKEY,
+    "content-type": "application/json",
+}
+df = pd.read_csv(MASTER)
+df.dropna(how="all", axis=0, inplace=True)
+COUNT = 0
+
+for row in df.itertuples():
+    domain = row[1]
+    groups = row[2:]
+    # groups = list(groups)
+    tmplist = []
+    for group in groups:
+        group = str(group)
+        if "nan" not in group:
+            # Grab Group UUIDs
+            url = f"https://api.northpass.com/v2/groups?filter[name][eq]={group}"
+            response = requests.get(url, headers=HEADERS)
+            response = response.json()
+            data = response["data"]
+            for name in data:
+                id = name["id"]
+                tmplist.append(id)
+    rowdict = {domain: tmplist}
+
+    # Grab all people
+    personlist = []
+    COUNT += 1
+    url = BASEURL + f"?filter[email][cont]={domain}"
+    response = requests.get(url, headers=HEADERS)
+    response = response.json()
+    nextlink = response["links"]
+
+    for data in response["data"]:
+        person = data["id"]
+        personlist.append(person)
+
+    # if "next" not in nextlink:
+    #     break
+
+    # Construct Payload for Bulk API
+    payload = {"payload": {"person_ids": personlist, "group_ids": tmplist}}
+    print(payload)

Scripts/API_Tests/antho-pandas.py

@@ -0,0 +1,18 @@
+import pandas as pd
+import os
+
+file = "~/Downloads/Anthology-EngageT1T2-MCA-CSV.csv"
+df = pd.read_csv(file)
+df["engage"] = df["Groups"].str.contains("(T2)")
+# print(df["engage"].value_counts())
+print(df["Domain"].value_counts())
+df.sort_values("Email", inplace=True)
+df.drop_duplicates(subset="Email", keep=False, inplace=True)
+print(df["Domain"].value_counts())
+
+# df2 = df[[ "Domain", "Groups" ]].copy()
+# print(df2)
+
+# accounts = df["Domain"].unique().tolist()
+# for x in accounts:
+#     df_dict = {name: df.loc[df["Domain"] == name] for name in accounts}