Deleted a bunch of files and cleaned things up. Started the script for finding correct domain names for Anthology. Recast templates. Todolist.

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

@@ -0,0 +1,8 @@
+import pandas as pd
+import requests
+
+MASTER = "~/Downloads/Anthology-Master-CSV-FirstChanges.csv"
+df = pd.read_csv(MASTER)
+
+for row in df.iterrows():
+    print(row)

Scripts/Anthology/antho_domains.py

@@ -0,0 +1,26 @@
+import csv
+import pandas as pd
+
+
+def grab_vals():
+    file = "/Users/normrasmussen/Downloads/antho_domains.csv"
+    final_array = []
+    with open(file, 'r') as file:
+        reader = csv.reader(file)
+        for row in reader:
+            for item in row:
+                if item != '':
+                    final_array.append(item)
+
+    print(len(final_array))
+    final_list = list(set(final_array))
+    print(len(final_list))
+
+    final = ["@"+domain for domain in final_list]
+    # print(final)
+    filecsv = pd.DataFrame(final)
+    filecsv.to_csv("/Users/normrasmussen/Downloads/final_domains.csv")
+
+
+if __name__ == "__main__":
+    grab_vals()

Scripts/Anthology/anthology-parse-csv-test2.csv

@@ -0,0 +1,4 @@
+domain,  group_1, ,
+newanthology.com,  Anthology 101 - (T1),  Anthology 101 - (T2),
+sometest.com,  Anthology 101 - (T1), Anthology 101 - (T4),
+tc.columbia.edu,  Anthology 101 - (T2), ,

Scripts/Anthology/find_domain_names.py

@@ -0,0 +1,10 @@
+from requests_html import HTMLSession
+from domains_list import DOMAINS
+
+for domain in DOMAINS:
+    URL = f"https://{domain}"
+    session = HTMLSession()
+    resp = session.get(URL)
+    title = resp.html.find('head > title', first=True)
+    group_name = title.text.split("|")[0]
+    print(group_name)