Create a pacer.DocketReport.from_html_file() classmethod and use it consistently

juriscraper/pacer/docket_report.py

@@ -1,4 +1,5 @@
 import copy
+import os
 import pprint
 import re
 import sys
@@ -22,6 +23,7 @@
 from .docket_utils import normalize_party_types
 from .reports import BaseReport
 from .utils import (
+    get_doc_id_prefix_from_court_id,
     get_file_size_str_from_tr,
     get_input_value_from_tr,
     get_pacer_doc_id_from_doc1_url,
@@ -489,6 +491,34 @@ def __init__(self, court_id, pacer_session=None):
         self._parties = None
         self._docket_entries = None
 
+    @classmethod
+    def from_html_file(cls, path):
+        """Run the docket parser on an HTML file.
+
+        This is invokved by by the test runner
+        (tests/local/test_DocketParseTest.py), as well as the __main__
+        of this file, as well juriscraper/pacerdocket.py.
+
+        Bring the common code in here.
+        """
+
+        dirname, filename = os.path.split(path)
+        filename_sans_ext = filename.split(".")[0]
+        court = filename_sans_ext.split("_")[0]
+        # If filename doesn't begin with a valid court, just use 'cand'
+        # (N.D. Cal.)  Historically the __main__ runner would default
+        # to 'cand' but the pacerdocket.py runner would default to
+        # 'psc', but the 'psc' fails some vaidations.
+        try:
+            _ = get_doc_id_prefix_from_court_id(court)
+        except KeyError:
+            court = "cand"
+
+        report = DocketReport(court)
+        with open(path, "rb") as f:
+            report._parse_text(f.read().decode("utf-8"))
+        return report
+
     @property
     def docket_report_has_content(self) -> bool:
         """Checks if the docket report has content.
@@ -1749,10 +1779,6 @@ def _get_judge(self, regex):
         print("Usage: python -m juriscraper.pacer.docket_report filepath")
         print("Please provide a path to an HTML file to parse.")
         sys.exit(1)
-    report = DocketReport("cand")  # Court ID is only needed for querying.
-    filepath = sys.argv[1]
-    print(f"Parsing HTML file at {filepath}")
-    with open(filepath) as f:
-        text = f.read()
-    report._parse_text(text)
+
+    report = DocketReport.from_html_file(sys.argv[1])
     pprint.pprint(report.data, indent=2)

juriscraper/pacerdocket.py

@@ -8,13 +8,11 @@
 import jsondate3 as json
 
 from juriscraper.pacer import DocketReport
-from juriscraper.pacer.http import PacerSession
-
-pacer_session = PacerSession(username="tr1234", password="Pass!234")
-report = DocketReport("psc", pacer_session)
 
 for path in sys.argv[1:]:
-    with open(path) as f:
-        report._parse_text(f.read())
-    data = report.data
-    print(json.dumps(data, indent=2, sort_keys=True, separators=(",", ": ")))
+    report = DocketReport.from_html_file(path)
+    print(
+        json.dumps(
+            report.data, indent=2, sort_keys=True, separators=(",", ": ")
+        )
+    )

tests/local/test_DocketParseTest.py

@@ -40,11 +40,10 @@ def run_parsers_on_path(
                 dirname, filename = os.path.split(path)
                 filename_sans_ext = filename.split(".")[0]
                 json_path = os.path.join(dirname, f"{filename_sans_ext}.json")
+
                 court = filename_sans_ext.split("_")[0]
+                report = DocketReport.from_html_file(path)
 
-                report = DocketReport(court)
-                with open(path, "rb") as f:
-                    report._parse_text(f.read().decode("utf-8"))
                 data = report.data
 
                 if data != {}: