Remove print statements

NOTICE

@@ -1,4 +1,4 @@
-WordPress Site Extractor
+WPextract
 Copyright 2022-2024 The University of Sheffield
 
 Portions of this code are derived from WPJsonScraper, which is available under the MIT license. For details, see src/wpextract/download/LICENSE.

pyproject.toml

@@ -77,7 +77,8 @@ select = [
     "PT",
     "B",
     "UP",
-    "RUF"
+    "RUF",
+    "T20"
 ]
 
 ignore = [

src/wpextract/cli/_download.py

@@ -142,7 +142,6 @@ def download(
     OUT_JSON is the directory to output the downloaded JSON to. It must be an existing empty directory or a non-existent directory which will be created.
     """
     setup_logging(verbose, log)
-    print(verbose)
 
     types_to_dl = set(dl_types) - set(skip_types)
 

src/wpextract/download/requestsession.py

@@ -278,7 +278,6 @@ def do_request(self, method, url, data=None, stream=False):
                 logging.error(f"Connection reset by {url}")
                 raise ConnectionReset from e
             else:
-                print(e)
                 raise e
         except requests.Timeout as e:
             logging.error(f"Request timed out fetching {url}")

src/wpextract/download/wpapi.py

@@ -1,4 +1,5 @@
 import copy
+import logging
 import math
 from json.decoder import JSONDecodeError
 from urllib.parse import urlencode
@@ -156,7 +157,7 @@ def crawl_pages(
                 ) and "X-WP-Total" in req.headers:
                     total_entries = int(req.headers["X-WP-Total"])
                     total_pages = int(req.headers["X-WP-TotalPages"])
-                    print("Total number of entries: %d" % total_entries)
+                    logging.info("Total number of entries: %d" % total_entries)
                     if start is not None and total_entries < start:
                         start = total_entries - 1
             except HTTPErrorInvalidPage:

src/wpextract/downloader.py

@@ -68,16 +68,16 @@ def download_media_files(self, session: RequestSession, dest: Path):
             session: the request session to use
             dest: destination directory for media
         """
-        print("Pulling media URLs")
+        logging.info("Pulling media URLs")
         media, slugs = self.scanner.get_media_urls("all", cache=True)
 
         if len(media) == 0:
             logging.warning("No media found corresponding to the criteria")
             return
-        print(f"{len(media)} media URLs found")
+        logging.info(f"{len(media)} media URLs found")
 
         number_dl = Exporter.download_media(session, media, dest)
-        print(f"Downloaded {number_dl} media files")
+        logging.info(f"Downloaded {number_dl} media files")
 
     def _get_fetch_or_list_type(self, obj_type, plural=False):
         """Returns a dict containing all necessary metadata about the obj_type to list and fetch data.
@@ -117,7 +117,7 @@ def _get_fetch_or_list_type(self, obj_type, plural=False):
 
     def _list_obj(self, obj_type, start=None, limit=None, cache=True):
         prop = self._get_fetch_or_list_type(obj_type, plural=True)
-        print(prop["obj_name"] + " details")
+        logging.info(f"Downloading {prop['obj_name']}")
 
         try:
             kwargs = {}
@@ -138,7 +138,7 @@ def _list_obj(self, obj_type, start=None, limit=None, cache=True):
             logging.error("The API does not support WP V2")
         except OSError as e:
             logging.error(f"Could not open {e.filename} for writing")
-        print()
+        logging.info(f"Completed downloading {prop['obj_name']}")
 
     @staticmethod
     def export_decorator(