Merge pull request #102 from openzim/fix_title_and_report

Fix title and report

CHANGELOG.md

@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Fixed
+- Fix ZIM Title still not ok
+- Fix crash when using the stats report (#100)
+
 ## [0.3.0] - 2024-03-02
 
 ### Changed

src/ifixit2zim/entrypoint.py

@@ -275,8 +275,6 @@ def main():
         sys.exit(scraper.run())
     except Exception as exc:
         logger.error("FAILED. An error occurred", exc_info=exc)
-        if args.debug:
-            logger.exception(exc)
         raise SystemExit(1) from None
 
 

src/ifixit2zim/executor.py

@@ -14,8 +14,10 @@
 
 
 def excepthook(args):
-    logger.error(f"UNHANDLED Exception in {args.thread.name}: {args.exc_type}")
-    logger.exception(args.exc_value)
+    logger.error(
+        f"UNHANDLED Exception in {args.thread.name}: {args.exc_type}",
+        exc_info=args.exc_value,
+    )
 
 
 threading.excepthook = excepthook
@@ -104,8 +106,7 @@ def worker(self):
             try:
                 func(**kwargs)
             except Exception as exc:
-                logger.error(f"Error processing {func} with {kwargs=}")
-                logger.exception(exc)
+                logger.error(f"Error processing {func} with {kwargs=}", exc_info=exc)
                 if raises:
                     self.exceptions.append(exc)
                     self.shutdown()

src/ifixit2zim/imager.py

@@ -157,9 +157,9 @@ def process_image(
                 fileobj = self.get_image_data(url.geturl())
             except Exception as exc:
                 logger.error(
-                    f"Failed to download/convert/optim source  at {url.geturl()}"
+                    f"Failed to download/convert/optim source  at {url.geturl()}",
+                    exc_info=exc,
                 )
-                logger.exception(exc)
                 self.add_missing_image_to_zim(
                     path=path,
                 )
@@ -195,8 +195,7 @@ def process_image(
             # don't have it, not a donwload error. we'll upload after processing
             pass
         except Exception as exc:
-            logger.error(f"Failed to download '{path}' from cache: {exc}")
-            logger.exception(exc)
+            logger.error(f"Failed to download '{path}' from cache", exc_info=exc)
             download_failed = True
         else:
             self.add_image_to_zim(
@@ -211,8 +210,10 @@ def process_image(
         try:
             fileobj = self.get_image_data(url.geturl())
         except Exception as exc:
-            logger.error(f"Failed to download/convert/optim source  at {url.geturl()}")
-            logger.exception(exc)
+            logger.error(
+                f"Failed to download/convert/optim source  at {url.geturl()}",
+                exc_info=exc,
+            )
             self.add_missing_image_to_zim(
                 path=path,
             )
@@ -230,6 +231,6 @@ def process_image(
             try:
                 s3_storage.upload_fileobj(fileobj=fileobj, key=path, meta=meta)
             except Exception as exc:
-                logger.error(f"{path} failed to upload to cache: {exc}")
+                logger.error(f"{path} failed to upload to cache", exc_info=exc)
 
         return path

src/ifixit2zim/scraper.py

@@ -44,6 +44,8 @@ def __init__(self, **kwargs):
 
         self.utils = Utils(configuration=self.configuration)
 
+        self.scrapers = []
+
     @property
     def build_path(self):
         return self.configuration.build_path
@@ -104,7 +106,6 @@ def sanitize_inputs(self):
                 self.configuration.title = TITLE["en"][
                     f"title_{self.configuration.lang_code}"
                 ]
-            self.configuration.title = self.metadata["title"]
         self.configuration.title = self.configuration.title.strip()
 
         (
@@ -232,13 +233,15 @@ def _raise_helper(msg):
         self.scraper_category = ScraperCategory(context=context)
         self.scraper_info = ScraperInfo(context=context)
         self.scraper_user = ScraperUser(context=context)
-        self.scrapers = [
-            self.scraper_homepage,
-            self.scraper_category,
-            self.scraper_guide,
-            self.scraper_info,
-            self.scraper_user,
-        ]
+        self.scrapers.extend(
+            [
+                self.scraper_homepage,
+                self.scraper_category,
+                self.scraper_guide,
+                self.scraper_info,
+                self.scraper_user,
+            ]
+        )
 
         self.processor.get_guide_link_from_props = (
             self.scraper_guide.get_guide_link_from_props
@@ -403,8 +406,7 @@ def run(self):
             if isinstance(exc, KeyboardInterrupt):
                 logger.error("KeyboardInterrupt, exiting.")
             else:
-                logger.error(f"Interrupting process due to error: {exc}")
-                logger.exception(exc)
+                logger.error("Interrupting process due to error", exc_info=exc)
             self.imager.abort()
             self.img_executor.shutdown(wait=False)
             return 1

src/ifixit2zim/scraper_generic.py

@@ -1,4 +1,3 @@
-import traceback
 from abc import ABC, abstractmethod
 from queue import Queue
 
@@ -147,12 +146,12 @@ def scrape_items(self):
             )
             try:
                 self.scrape_one_item(item_key, item_data)
-            except Exception as ex:
+            except Exception as exc:
                 self.error_items_keys.add(item_key)
                 logger.warning(
-                    f"Error while processing {self.get_items_name()} {item_key}: {ex}"
+                    f"Error while processing {self.get_items_name()} {item_key}",
+                    exc_info=exc,
                 )
-                traceback.print_exc()
                 self.add_item_error_redirect(item_key, item_data)
             finally:
                 if (

src/ifixit2zim/utils.py

@@ -115,18 +115,16 @@ def get_version_ident_for(self, url: str) -> str | None:
             resp = requests.head(url, timeout=10)
             headers = resp.headers
         except Exception as exc:
-            logger.warning(f"Unable to HEAD {url}")
-            logger.exception(exc)
+            logger.warning(f"Unable to HEAD {url}", exc_info=exc)
             try:
                 _, headers = stream_file(
                     url=url,
                     byte_stream=io.BytesIO(),
                     block_size=1,
                     only_first_block=True,
                 )
-            except Exception as exc2:
-                logger.warning(f"Unable to query image at {url}")
-                logger.exception(exc2)
+            except Exception as exc:
+                logger.warning(f"Unable to query image at {url}", exc_info=exc)
                 return
 
         for header in ("ETag", "Last-Modified", "Content-Length"):