[WIP] issue codeforpdx#1063 parse DA

this is strictly for parsing and testing the district attorney number
unsure whether to go with least invasive additions or fully robust
case_parser new member as optional so as not to have to add arguments when calling
  the constructor throughout the project
you'll see in the new parsing method __parse_distr_atty that there's potential to return
  all the values from upper right of a given case html file but i just return DA number
would it be preferred to return more values? or return None instead of empty str?
also added testing methods to test_case_parser

src/backend/expungeservice/crawler/parsers/case_parser.py

@@ -21,12 +21,14 @@ class CaseParserData:
     hashed_dispo_data: Dict[int, Dict[str, str]]
     balance_due: str
     probation_revoked: Optional[date]
+    distr_atty: str
 
 
 class CaseParser:
     @staticmethod
     def feed(data) -> CaseParserData:
         soup = BeautifulSoup(data, "html.parser")
+        distr_atty = CaseParser.__parse_distr_atty(soup)
         hashed_charge_data = CaseParser.__build_charge_table_data(soup)
         (
             hashed_dispo_data,
@@ -37,8 +39,19 @@ def feed(data) -> CaseParserData:
             probation_revoked = date.fromdatetime(datetime.strptime(probation_revoked_date_string, "%m/%d/%Y"))
         else:
             probation_revoked = None  # type: ignore
-        return CaseParserData(hashed_charge_data, hashed_dispo_data, balance_due, probation_revoked)
+        return CaseParserData(hashed_charge_data, hashed_dispo_data, balance_due, probation_revoked, distr_atty)
 
+    @staticmethod
+    def __parse_distr_atty(soup) -> str:
+        distr_atty_key = "District Attorney Number:"
+        labels = soup.find_all("th", "ssTableHeaderLabel", limit=10)
+        table = {}
+        for tag in labels:
+            table[tag.string] = tag.parent.find("td").string
+        if distr_atty_key in table:
+            return table[distr_atty_key]
+        return ""
+
     @staticmethod
     def __build_charge_table_data(soup) -> Dict[int, Dict[str, str]]:
         hashed_charge_data = {}

src/backend/expungeservice/models/case.py

@@ -19,6 +19,7 @@ class CaseSummary:
     case_detail_link: str
     balance_due_in_cents: int
     edit_status: EditStatus
+    distr_atty: str=""
 
     def get_balance_due(self):
         return self.balance_due_in_cents / 100
@@ -46,6 +47,7 @@ def empty(case_number: str):
             CaseSummary(
                 name="",
                 birth_year=1900,
+                # distr_atty="",
                 case_number=case_number,
                 citation_number="",
                 location="",
@@ -90,6 +92,7 @@ def create(
             case_detail_link,
             balance_due_in_cents,
             EditStatus.UNCHANGED,
+            "", # distr_atty
         )
 
     @staticmethod

src/backend/tests/parser/test_case_parser.py

@@ -49,6 +49,9 @@ def test_charge_data_is_formatted(self):
     def test_probation_revoked_is_parsed(self):
         assert not self.parser.probation_revoked
 
+    def test_distr_atty_is_parsed(self):
+        assert self.parser.distr_atty == ""
+
 
 class TestCaseWithoutFinancialTable(unittest.TestCase):
     def setUp(self):
@@ -75,6 +78,10 @@ def test_charge_data_is_formatted(self):
 
     def test_probation_revoked_is_parsed(self):
         assert not self.parser.probation_revoked
+
+    def test_distr_atty_is_parsed(self):
+        assert self.parser.distr_atty == "01234567"
+
 
 
 class TestCaseWithPartialDisposition(unittest.TestCase):
@@ -117,6 +124,9 @@ def test_charge_data_is_formatted(self):
 
     def test_probation_revoked_is_parsed(self):
         assert not self.parser.probation_revoked
+
+    def test_distr_atty_is_parsed(self):
+        assert self.parser.distr_atty == "555555-1"
 
 
 class TestCaseWithoutDisposition(unittest.TestCase):
@@ -152,6 +162,9 @@ def test_charge_data_is_formatted(self):
 
     def test_probation_revoked_is_parsed(self):
         assert not self.parser.probation_revoked
+
+    def test_distr_atty_is_parsed(self):
+        assert self.parser.distr_atty == "2377315-1"
 
 
 class TestParkingViolationCase(unittest.TestCase):
@@ -176,6 +189,9 @@ def test_charge_data_is_formatted(self):
 
     def test_probation_revoked_is_parsed(self):
         assert not self.parser.probation_revoked
+
+    def test_distr_atty_is_parsed(self):
+        assert self.parser.distr_atty == ""
 
 
 class TestCaseWithRelatedCases(unittest.TestCase):
@@ -203,6 +219,9 @@ def test_charge_data_is_formatted(self):
 
     def test_probation_revoked_is_parsed(self):
         assert not self.parser.probation_revoked
+
+    def test_distr_atty_is_parsed(self):
+        assert self.parser.distr_atty == "555555-B"
 
 
 class TestFelicia(unittest.TestCase):
@@ -237,6 +256,9 @@ def test_charge_data_is_formatted(self):
 
     def test_probation_revoked_is_parsed(self):
         assert not self.parser.probation_revoked
+
+    def test_distr_atty_is_parsed(self):
+        assert self.parser.distr_atty == "555555"
 
 
 class TestRevokedProbation(unittest.TestCase):
@@ -271,6 +293,9 @@ def test_charge_data_is_formatted(self):
 
     def test_probation_revoked_is_parsed(self):
         assert self.parser.probation_revoked
+
+    def test_distr_atty_is_parsed(self):
+        assert self.parser.distr_atty == "55555555"
 
 
 class TestSpacesExistingInChargeInfoCells(unittest.TestCase):