fix: id with weird path should also be extracted

setup.cfg

@@ -22,6 +22,3 @@ max-line-length = 160
 # Define setup.py command aliases here
 test = pytest
 
-[tool:pytest]
-collect_ignore = ['setup.py']
-

sked_parser/scraper.py

@@ -54,7 +54,7 @@ def create_id(sked_path, faculty_short, current_sem_str, extracted_semester):
     # Unqoute the URL first
     sked_path = unquote(sked_path)
     # Get a basic id from the url page, which is the last part excluding the .extension
-    id_re = re.compile(r'\w/.+/(.+?)\.+(html|csv)', re.IGNORECASE)
+    id_re = re.compile(r'\w/(?:.*/)?(.+?)\.+(html|csv)', re.IGNORECASE)
     m = id_re.search(sked_path)
     if not m:
         raise Exception(f"Path {sked_path} did not match to ID regex, so we can't extract an ID")

tests/test_scraper.py

@@ -134,6 +134,8 @@ def sked_path(part_str): return f"e/semester/{part_str}.html"
     # Mutliple special chars
     in_str = "b-.-eit"
     assert create_id(sked_path(in_str), faculty_short, current_sem_str, extracted_semester) == "e_b_eit_1_ws"
+    # Special URL for faculty E
+    assert create_id("e/E-IST.html", faculty_short, current_sem_str, extracted_semester) == "e_ist_1_ws"
     # Complicated semester specification
     in_str = "PSA_M_1. Semester_Schwerpunkt"
     assert create_id(sked_path(in_str), faculty_short, current_sem_str,