skip empty, pull citations again

1 files changed, 10 insertions, 6 deletions

diff --git a/scraper/util.py b/scraper/util.py
index a435f91a..c02f018c 100644
--- a/scraper/util.py
+++ b/scraper/util.py
@@ -259,7 +259,7 @@ class AddressBook (object):
   def __init__(self):
     entities = {}
     lookup = {}
-    data = fetch_google_sheet()
+    keys, data = fetch_google_sheet()
     # keys, data = read_csv('reports/pdf_institutions_deduped.csv', keys=True)
     for index, line in enumerate(data):
       if line[0] == line[1] or line[0] not in entities:
@@ -283,16 +283,20 @@ class AddressBook (object):
         return self.data[index]
     return None
 
-def fetch_worksheet():
+def fetch_spreadsheet():
   scope = ['https://spreadsheets.google.com/feeds','https://www.googleapis.com/auth/drive']
   credentials = ServiceAccountCredentials.from_json_keyfile_name('./.creds/Megapixels-ef28f91112a9.json', scope)
   docid = "1denb7TjYsN9igHyvYah7fQ0daABW32Z30lwV7QrDJQc"
   client = gspread.authorize(credentials)
   spreadsheet = client.open_by_key(docid)
-  return spreadsheet.worksheet("institutions")
+  return spreadsheet
 
-def fetch_google_sheet():
-  rows = fetch_worksheet().get_all_values()
+def fetch_worksheet(name="institutions"):
+  spreadsheet = fetch_spreadsheet()
+  return spreadsheet.worksheet(name)
+
+def fetch_google_sheet(name="institutions"):
+  rows = fetch_worksheet(name).get_all_values()
   keys = rows[0]
   lines = rows[1:]
-  return lines
+  return keys, lines