1 files changed, 30 insertions, 13 deletions
diff --git a/python/parse_citi_pdf.py b/python/parse_citi_pdf.py
index 71bdc4c8..39a33f5a 100644
--- a/python/parse_citi_pdf.py
+++ b/python/parse_citi_pdf.py
@@ -3,19 +3,28 @@ import subprocess
 from bs4 import BeautifulSoup
 from env import DAILY_DIR
 
+
 def load_pdf(file_path):
-    proc = subprocess.run(["pdftohtml", "-xml", "-stdout", "-i",
-                           file_path.as_posix()],
-                          capture_output=True)
+    proc = subprocess.run(
+        ["pdftohtml", "-xml", "-stdout", "-i", file_path.as_posix()],
+        capture_output=True,
+    )
     soup = BeautifulSoup(proc.stdout, features="lxml")
     l = soup.findAll("text")
     l = sorted(l, key=lambda x: (int(x["top"]), int(x["left"])))
     return l
 
+
 def get_col(l, top, bottom, left, right):
-    return [c.text for c in l if int(c["left"]) >= left and \
-            int(c["left"]) < right and \
-            int(c["top"]) >= top and int(c["top"]) < bottom ]
+    return [
+        c.text
+        for c in l
+        if int(c["left"]) >= left
+        and int(c["left"]) < right
+        and int(c["top"]) >= top
+        and int(c["top"]) < bottom
+    ]
+
 
 def parse_num(s):
     s = s.replace(",", "")
@@ -24,18 +33,24 @@ def parse_num(s):
     else:
         return float(s)
 
+
 def get_df(l, col1, col2, col3):
-    df = pd.DataFrame({"amount": get_col(l, *col2),
-                       "currency": get_col(l, *col3)},
-                      index=get_col(l, *col1))
+    df = pd.DataFrame(
+        {"amount": get_col(l, *col2), "currency": get_col(l, *col3)},
+        index=get_col(l, *col1),
+    )
     df.amount = df.amount.apply(parse_num)
     df.index = df.index.str.lstrip()
     return df
 
+
 def get_citi_collateral(d):
     try:
-        fname = next((DAILY_DIR / "CITI_reports").
-                     glob(f"262966_MarginNotice_{d.strftime('%Y%m%d')}_*.pdf"))
+        fname = next(
+            (DAILY_DIR / "CITI_reports").glob(
+                f"262966_MarginNotice_{d.strftime('%Y%m%d')}_*.pdf"
+            )
+        )
     except StopIteration:
         raise FileNotFoundError(f"CITI file not found for date {d.date()}")
     l = load_pdf(fname)
@@ -51,5 +66,7 @@ def get_citi_collateral(d):
     col2 = (top, bottom, 100, 500)
     col3 = (top, bottom, 500, 600)
     initial_margin = get_df(l, col1, col2, col3)
-    return variation_margin.loc["VM Total Collateral", "amount"] + \
-        initial_margin.loc["Non Reg IM Total Collateral", "amount"]
+    return (
+        variation_margin.loc["VM Total Collateral", "amount"]
+        + initial_margin.loc["Non Reg IM Total Collateral", "amount"]
+    )