Merge pull request #157 from gwydion67/master

change from ghostscript to pdfium

requirements.txt

@@ -2,6 +2,7 @@ beautifulsoup4==4.13.1
 blinker==1.9.0
 bs4==0.0.2
 cachetools==5.5.1
+camelot-py==1.0.0
 certifi==2025.1.31
 cffi==1.17.1
 chardet==5.2.0
@@ -28,19 +29,19 @@ MarkupSafe==3.0.2
 numpy==2.2.2
 oauth2client==4.1.3
 oauthlib==3.2.2
-opencv-python==4.11.0.86
+opencv-python-headless==4.11.0.86
 openpyxl==3.1.5
 packaging==24.2
 pandas==2.2.3
 pdfminer.six==20240706
+pillow==11.1.0
 proto-plus==1.26.0
 protobuf==5.29.3
 pyasn1==0.6.1
 pyasn1_modules==0.4.1
 pycparser==2.22
 pyparsing==3.2.1
 pypdf==5.2.0
-pypdf_table_extraction==1.0.1
 pypdfium2==4.30.1
 python-dateutil==2.9.0.post0
 pytz==2025.1
@@ -56,4 +57,3 @@ typing_extensions==4.12.2
 tzdata==2025.1
 uritemplate==4.1.1
 urllib3==2.3.0
-Werkzeug==3.1.3

utils/academic_calander_handler.py

@@ -89,8 +89,12 @@ def upzip_and_delete_zip(zip_file_name,result_folder_name):
 
 def export_json():
     filename = get_latest_calendar_name()
+    ## [NOTE]
     ## ignore the read_pdf not found warning
-    tables = camelot.read_pdf(filename,pages="all")
+    ## also the devs of camelot have mismached backend names so ghostscript points to pdfium and vice versa ... 
+    ## so basically this is using pdfium but backend name needs to be ghostscript
+    ## in future if this gets fixed this need to be changed back
+    tables = camelot.read_pdf(filename,pages="all",backend="ghostscript") 
 
     print("Checking for pre-existing folder")
     delete_file(JSON_FOLDER_NAME)