From 598f2895f7b3b8e05934438cd9857c74c547cb3c Mon Sep 17 00:00:00 2001
From: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
Date: Thu, 5 Dec 2024 13:36:06 -0500
Subject: [PATCH] get-directors: append if output file is present

---
 src/letsrolld/cmd/get_directors.py | 26 ++++++++++++++++++++++----
 1 file changed, 22 insertions(+), 4 deletions(-)

diff --git a/src/letsrolld/cmd/get_directors.py b/src/letsrolld/cmd/get_directors.py
index bf13587..26bb84a 100644
--- a/src/letsrolld/cmd/get_directors.py
+++ b/src/letsrolld/cmd/get_directors.py
@@ -1,11 +1,13 @@
 import argparse
 import csv
+import os
 import sys
 import time
 import traceback
 
 from letsrolld import film
 from letsrolld import filmlist
+from letsrolld.directorlist import read_director_list
 
 _SEC_WAIT_ON_FAIL = 5
 
@@ -23,8 +25,9 @@ def get_directors_by_films(film_list):
                         directors[director.base_url] = director
                         yield director
                 break
-            except Exception as e:
-                # TODO: deduplicate error handling with update script
+            except (
+                Exception
+            ) as e:  # TODO: deduplicate error handling with update script
                 traceback.print_exception(e)
                 print(f"Retrying in {_SEC_WAIT_ON_FAIL} seconds...")
                 time.sleep(_SEC_WAIT_ON_FAIL)
@@ -42,11 +45,26 @@ def main():
 
     film_list = list(filmlist.read_film_list(args.input))
 
-    with open(args.output, "w", newline="") as csvfile:
+    directors = set()
+    if os.path.exists(args.output):
+        print(f"Output file {args.output} already exists, appending to it...")
+        sys.stdout.flush()
+
+        directors = {d.uri for d in read_director_list(args.output)}
+
+    mode = "a" if directors else "w"
+    with open(args.output, mode, newline="") as csvfile:
         writer = csv.writer(csvfile, dialect=csv.unix_dialect)
-        writer.writerow(["Name", "Letterboxd URI"])
+        if mode == "w":
+            writer.writerow(["Name", "Letterboxd URI"])
+        else:
+            csvfile.seek(0, os.SEEK_END)
 
         for i, director_ in enumerate(get_directors_by_films(film_list), start=1):
+            if director_.base_url in directors:
+                print(f"Skipping director #{i}: {director_.name}")
+                sys.stdout.flush()
+                continue
             print(f"Adding director #{i}: {director_.name}")
             sys.stdout.flush()
             writer.writerow([director_.name, director_.base_url])