log reset added

.github/workflows/static.yml

@@ -1,8 +1,8 @@
 # Simple workflow for deploying static content to GitHub Pages
-name: Deploy static content to Pages
+# name: Deploy static content to Pages
 
-# Run events
-on:
+# # Run events
+# on:
   # # On push
   # push:
   #   branches: ["main"]

index.html

@@ -26,7 +26,7 @@
         <h1>Ofsted ILACS Summary</h1>
         <p>Summarised outcomes of published short and standard ILACS inspection reports by Ofsted, refreshed daily.<br/>An expanded version of the shown summary sheet, refreshed concurrently, is available to <a href='ofsted_childrens_services_overview.xlsx'>download here</a> as an .xlsx file. <br/>Data summary is based on the original <i>ILACS Outcomes Summary</i> published periodically by the ADCS:<a href='https://adcs.org.uk/inspection/article/ilacs-outcomes-summary'>https://adcs.org.uk/inspection/article/ilacs-outcomes-summary</a>.</p>
         <p>Disclaimer: This summary is built from scraped data direct from https://reports.ofsted.gov.uk/ and the published PDF inspection report files. As a result of the nuances|variance within the inspection report content or pdf encoding, we're noting some problematic data extraction for a small number of LA's*.<br/> <a href="mailto:[email protected]?subject=Ofsted-Scrape-Tool">Feedback</a> on specific problems|inaccuracies|suggestions welcomed.<br/>**LA reports with issues: southend-on-sea, [overall, help_and_protection_grade,care_leavers_grade], nottingham,[inspection_framework, inspection_date], redcar and cleveland,[inspection_framework, inspection_date], knowsley,[inspector_name], stoke-on-trent,[inspector_name]</p>
-        <p><b>Summary data last updated: 29 05 2024 13:50</b></p>
+        <p><b>Summary data last updated: 31 05 2024 07:19</b></p>
         <p><b>LA inspections last updated: []</b></p>
         <div class="container">
     <table border="1" class="dataframe">

ofsted_childrens_services_inspection_scrape.py

@@ -76,7 +76,6 @@
 from datetime import datetime
 import nltk
 import json
-import logging
 import git
 
 # pdf search/data extraction
@@ -105,17 +104,25 @@
 except ModuleNotFoundError:
     print("Please install 'scikit-learn' using pip")
 
+# Configure logging/logging module
+import warnings
+import logging
+
+# wipe / reset the logging file 
+with open('output.log', 'w'):
+    # comment out if maintaining ongoing/historic log
+    pass
 
 # Keep warnings quiet unless priority
-import warnings
 logging.getLogger('org.apache.pdfbox').setLevel(logging.ERROR)
 warnings.filterwarnings('ignore')
-
-# Configure the logging module
+
 logging.basicConfig(filename='output.log', level=logging.INFO, format='%(asctime)s - %(message)s')
 
-nltk.download('punkt')
-nltk.download('stopwords')
+
+# text analysis libs
+nltk.download('punkt')      # tokeniser models/sentence segmentation
+nltk.download('stopwords')  # stop words ready for text analysis|NLP preprocessing