feat: Improve logging and error handling in async session and parser; add unit tests for logging output

Author: areed1192

CHANGELOG.md

@@ -21,6 +21,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - **edgar/datasets.py**: Added `logger` — logs `info` on bulk download start, `debug` on per-file extraction with row counts.
 - **edgar/search.py**: Added `logger` — logs `debug` with EFTS search params before request.
 - **edgar/company.py**: Added `logger` — logs `debug` on identifier resolution path (CIK vs ticker).
+- **edgar/async_session.py**: Added `logger.error()` before each `raise EdgarRequestError`, matching `session.py` pattern for consistent error observability.
+
+### Added
+
+- **tests/test_logging.py**: 7 unit tests for logging output (cache hit/miss/set/invalidate, session error, rate-limit sleep, async session error).
+
+### Fixed
+
+- **edgar/parser.py**: Changed `except KeyError` to `except IndexError` in ticker symbol extraction — `values[2]` is a list index, not a dict key.
+
+### Removed
+
+- **edgar/utilis.py**: Deleted dead duplicate of `utils.py` (nothing imported it).
+- **edgar/parser.py**: Removed 3 commented-out `print()` debug lines.
 
 ## [0.2.0] - 2026-04-19
 

edgar/async_session.py

@@ -161,6 +161,7 @@ async def make_request(  # pylint: disable=too-many-positional-arguments
                 json=json_payload,
             )
         except httpx.HTTPError as exc:
+            logger.error("Request failed: %s", exc)
             raise EdgarRequestError(f"Request to {url} failed: {exc}") from exc
 
         retries = 0
@@ -186,6 +187,7 @@ async def make_request(  # pylint: disable=too-many-positional-arguments
                 )
             except httpx.HTTPError as exc:
                 if retries >= MAX_RETRIES:
+                    logger.error("Retry %s failed: %s", retries, exc)
                     raise EdgarRequestError(
                         f"Request to {url} failed after {MAX_RETRIES} retries: {exc}"
                     ) from exc
@@ -223,6 +225,7 @@ async def fetch_page(self, url: str) -> bytes | None:
         try:
             response = await self.http_client.get(url)
         except httpx.HTTPError as exc:
+            logger.error("Failed to fetch page %s: %s", url, exc)
             raise EdgarRequestError(f"Failed to fetch page {url}: {exc}") from exc
 
         if response.status_code == 200:
@@ -251,6 +254,7 @@ async def download(self, url: str, path: str | None = None) -> str | bytes:
         try:
             response = await self.http_client.get(url)
         except httpx.HTTPError as exc:
+            logger.error("Failed to download %s: %s", url, exc)
             raise EdgarRequestError(f"Failed to download {url}: {exc}") from exc
 
         if response.status_code != 200:

edgar/parser.py

@@ -337,7 +337,6 @@ def parse_transaction_report(self, table: Tag) -> list[dict]:
             values.insert(5, href)
 
             master_list.append(dict(zip(headers, values)))
-            # print([header.strip() for header in row.strings if header != '\n'])
 
         return master_list
 
@@ -499,7 +498,8 @@ def _parse_variable_product_page(self, product_page_soup: Tag) -> list[dict]:
                         # Set the Ticker symbol.
                         try:
                             row_dict["ticker_symbol"] = values[2]
-                        except KeyError:
+                        except IndexError:
+                            logger.debug("No ticker symbol at index 2 for %s", product_id)
                             row_dict["ticker_symbol"] = "null"
 
                         for link in row_links:
@@ -596,57 +596,6 @@ def parse_loc_elements(self, response_text: str) -> list[dict]:
             entries.append(location_dict)
 
         return entries
-
-    # def parse_series_filings(self, response_text: str) -> List[dict]:
-
-    #     root = ET.fromstring(response_text)
-
-    #     for elem in root.iterfind(
-    #         '.atom:entry/atom:content/atom:company-info/atom:sids/atom:sid',
-    #         namespaces=self.entries_namespace
-    #     ):
-    #         print(elem)
-
-    # soup = BeautifulSoup(response_text, 'html.parser')
-
-    # sid_data = []
-
-    # for sid in soup.find_all(name='sid'):
-
-    #     sid: Tag = sid
-    #     element_dict = {}
-
-    #     print(len(list(sid.children)))
-
-    #     for element in sid.children:
-
-    #         if not isinstance(element, NavigableString) and element.name != 'cids':
-    #             element_dict[
-    #                 element.name.replace('-', '_')
-    #             ] = element.text.strip()
-
-    #         elif not isinstance(element, NavigableString) and element.name == 'cids':
-    #             element_dict['cids'] = []
-
-    #             for cid in element.find_all('cid'):
-    #                 cid_dict = {}
-    #                 cid_dict['cid_id'] = cid['id']
-
-    #                 for cid_element in cid.find_all():
-    #                     cid_dict[
-    #                         cid_element.name.replace('-', '_').strip()
-    #                     ] = cid_element.text.strip()
-
-    #                 element_dict['cids'].append(
-    #                     cid_dict
-    #                 )
-
-    #     sid_data.append(
-    #         element_dict
-    #     )
-
-    # return sid_data
-
     def parse_series_table(self, response_text: str) -> list[dict]:
         """Parses the series table returned from a Series query.