diff --git a/capstone/capapi/resources.py b/capstone/capapi/resources.py
index 75685a965..570fe650b 100644
--- a/capstone/capapi/resources.py
+++ b/capstone/capapi/resources.py
@@ -1,6 +1,6 @@
 import hashlib
 import concurrent.futures
-from copy import copy 
+from copy import copy
 from functools import reduce
 
 import rest_framework.request
@@ -13,6 +13,7 @@
 from django.db.models import QuerySet
 from django.http import QueryDict
 from django.test.utils import CaptureQueriesContext
+from django.test.client import RequestFactory
 from django.utils.functional import SimpleLazyObject
 from django_hosts import reverse as django_hosts_reverse
 from elasticsearch import Elasticsearch
@@ -269,3 +270,11 @@ def api_request(request, viewset, method, url_kwargs={}, get_params={}):
     api_request.GET.update(get_params)
 
     return viewset.as_view({'get': method})(api_request, **url_kwargs)
+
+
+def call_serializer(Serializer, item, query_params=None):
+    """
+        Make a fake DRF request so we can call a DRF serializer with the expected context.
+    """
+    request = rest_framework.request.Request(RequestFactory().get('/', query_params))
+    return Serializer(item, context={'request': request}).data
diff --git a/capstone/capapi/serializers.py b/capstone/capapi/serializers.py
index 3115802d7..0870154ce 100644
--- a/capstone/capapi/serializers.py
+++ b/capstone/capapi/serializers.py
@@ -546,49 +546,9 @@ def data(self):
         return super(DocumentSerializer, self).data
 
 
-class ConvertCaseDocumentSerializer(CaseDocumentSerializer):
-    first_page_order = serializers.CharField()
-    last_page_order = serializers.CharField()
-
-    def to_representation(self, instance):
-        first_page_order = self.context.get("first_page_order")
-        last_page_order = self.context.get("last_page_order")
-
-        data = super().to_representation(instance)
-
-        data.pop("reporter", None)
-        data.pop("volume", None)
-        data.pop("url", None)
-        data.pop("frontend_url", None)
-        data.pop("frontend_pdf_url", None)
-        try:
-            data["court"].pop("slug", None)
-            data["court"].pop("url", None)
-        except KeyError as err:
-            print(f"Cannot pop field {err} because 'court' doesn't exist")
-        try:
-            data["jurisdiction"].pop("slug", None)
-            data["jurisdiction"].pop("whitelisted", None)
-            data["jurisdiction"].pop("url", None)
-        except KeyError as err:
-            print(f"Cannot pop field {err} because 'jurisdiction' doesn't exist")
-
-        if "preview" in data:
-            data.pop("preview")
-        data["first_page_order"] = first_page_order
-        data["last_page_order"] = last_page_order
-        return data
-
-
 class ConvertNoLoginCaseDocumentSerializer(CaseDocumentSerializerWithCasebody):
-    first_page_order = serializers.CharField()
-    last_page_order = serializers.CharField()
-
     def to_representation(self, instance, check_permissions=False):
         """Tell get_casebody not to check for case download permissions."""
-        first_page_order = self.context.get("first_page_order")
-        last_page_order = self.context.get("last_page_order")
-
         data = super().to_representation(instance, check_permissions=check_permissions)
         try:
             data["casebody"] = data["casebody"]["data"]
@@ -615,8 +575,6 @@ def to_representation(self, instance, check_permissions=False):
 
         data.pop("preview", None)
 
-        data["first_page_order"] = first_page_order
-        data["last_page_order"] = last_page_order
         return data
 
     @property
diff --git a/capstone/capdb/tests/test_models.py b/capstone/capdb/tests/test_models.py
index d901c8795..998782fad 100644
--- a/capstone/capdb/tests/test_models.py
+++ b/capstone/capdb/tests/test_models.py
@@ -93,96 +93,8 @@ def test_volume_save_slug_update(volume_metadata):
 
 
 @pytest.mark.django_db(databases=["capdb"])
-def test_volume_unredact(reset_sequences, case_factory, monkeypatch, tmp_path):
-    # set up a redacted case
-    case = case_factory(volume__redacted=True, volume__pdf_file="redacted_volume.pdf")
-    structure = case.structure
-    page = structure.pages.first()
-    structure.opinions = [
-        # redacted paragraph
-        {
-            "type": "head",
-            "paragraphs": [
-                {
-                    "class": "parties",
-                    "block_ids": ["BL_1.1"],
-                    "id": "b1-1",
-                    "redacted": True,
-                }
-            ],
-        },
-        {
-            "type": "majority",
-            "paragraphs": [
-                # redacted content blocks
-                {
-                    "class": "p",
-                    "block_ids": ["BL_1.2", "BL_1.3"],
-                    "id": "b1-2",
-                },
-                # redacted image block
-                {
-                    "class": "image",
-                    "block_ids": ["BL_1.4"],
-                    "id": "b1-3",
-                },
-            ],
-            # redacted footnote
-            "footnotes": [
-                {
-                    # redacted footnote paragraph
-                    "paragraphs": [
-                        {
-                            "class": "p",
-                            "block_ids": ["BL_1.5"],
-                            "id": "b1-4",
-                        }
-                    ],
-                    "label": "1",
-                    "id": "footnote_1_1",
-                    "redacted": True,
-                }
-            ],
-        },
-    ]
-    structure.save()
-    page.blocks = [
-        {
-            "id": "BL_1.1",
-            "class": "p",
-            "tokens": ["Text 1"],
-            "rect": [25, 11, 300, 490],
-        },
-        {
-            "id": "BL_1.2",
-            "class": "p",
-            "tokens": ["Text 2"],
-            "redacted": True,
-            "rect": [4, 32, 100, 100],
-        },
-        {
-            "id": "BL_1.3",
-            "class": "p",
-            "tokens": [["redact"], "Text 3", ["/redact"]],
-            "rect": [225, 11, 430, 290],
-        },
-        {
-            "id": "BL_1.4",
-            "format": "image",
-            "redacted": True,
-            "class": "image",
-            "data": "image data",
-            "rect": [0, 0, 100, 100],
-        },
-        {
-            "id": "BL_1.5",
-            "class": "p",
-            "tokens": ["Text 4"],
-            "rect": [190, 312, 330, 490],
-        },
-    ]
-    page.encrypt()
-    page.save()
+def test_volume_unredact(reset_sequences, case_factory, monkeypatch, tmp_path, redacted_case_factory):
+    case = redacted_case_factory()
 
     # set up volume pdfs
     volume = case.volume
@@ -194,15 +106,16 @@ def test_volume_unredact(reset_sequences, case_factory, monkeypatch, tmp_path):
     download_files_storage.save(volume.pdf_file.name, StringIO("redacted"))
 
     # verify redacted case contents
-    case.sync_case_body_cache()
-    case.refresh_from_db()
-    assert case.body_cache.text == "\n\n"
+    assert case.body_cache.text == "\nnot redacted\n"
     assert xml_equal(
         case.body_cache.html,
-        '<section class="casebody" data-case-id="00000000" data-firstpage="4" data-lastpage="8">\n'
-        '  <section class="head-matter"/>\n'
-        '  <article class="opinion" data-type="majority"/>\n'
-        "</section>",
+        '<section class="casebody" data-case-id="00000000" data-firstpage="4" '
+            'data-lastpage="8">\n'
+            '  <section class="head-matter"></section>\n'
+            '  <article class="opinion" data-type="majority">\n'
+            '    <p id="b1-2" data-blocks=\'[["BL_1.2",0,[4,32,100,100]],["BL_1.3",0,[225,11,430,290]]]\'>not redacted</p>\n'
+            '  </article>\n'
+            '</section>\n',
     )
 
     # unredact
@@ -210,7 +123,7 @@ def test_volume_unredact(reset_sequences, case_factory, monkeypatch, tmp_path):
     volume.refresh_from_db()
     case.body_cache.refresh_from_db()
     assert volume.redacted is False
-    assert case.body_cache.text == "Text 1\nText 2Text 3\nText 4\n"
+    assert case.body_cache.text == "Text 1\nText 2Text 3not redacted\nText 4\n"
     assert html_equal(
         case.body_cache.html,
         dedent(
@@ -220,7 +133,7 @@ def test_volume_unredact(reset_sequences, case_factory, monkeypatch, tmp_path):
             <h4 class="parties" id="b1-1" data-blocks='[["BL_1.1",0,[25,11,300,490]]]'>Text 1</h4>
           </section>
           <article class="opinion" data-type="majority">
-            <p id="b1-2" data-blocks='[["BL_1.2",0,[4,32,100,100]],["BL_1.3",0,[225,11,430,290]]]'>Text 2Text 3</p>
+            <p id="b1-2" data-blocks='[["BL_1.2",0,[4,32,100,100]],["BL_1.3",0,[225,11,430,290]]]'>Text 2Text 3not redacted</p>
             <p class="image" id="b1-3" data-blocks='[["BL_1.4",0,[0,0,100,100]]]'>
               <img src="data:image%20data" class="image" width="100" height="100">
             </p>
diff --git a/capstone/config/celery.py b/capstone/config/celery.py
index f4df3a723..b27378866 100644
--- a/capstone/config/celery.py
+++ b/capstone/config/celery.py
@@ -17,7 +17,7 @@
     'scripts.update_snippets',
     'scripts.refactor_xml',
     'scripts.make_pdf',
-    'scripts.convert_s3',
+    'scripts.export_cap_static',
 ])
 
 # Using a string here means the worker doesn't have to serialize
diff --git a/capstone/config/settings/settings_base.py b/capstone/config/settings/settings_base.py
index 619f5d2c8..1f3b40552 100644
--- a/capstone/config/settings/settings_base.py
+++ b/capstone/config/settings/settings_base.py
@@ -385,6 +385,10 @@ def immutable_file_test(path, url):
     },
 }
 CELERY_TIMEZONE = 'UTC'
+CELERY_TASK_ROUTES = {
+    "scripts.export_cap_static.export_cases_by_volume": {"queue": "cap_static"},
+}
+
 
 ### CAP API settings ###
 
diff --git a/capstone/fabfile.py b/capstone/fabfile.py
index 2bc394af5..9d5444db1 100644
--- a/capstone/fabfile.py
+++ b/capstone/fabfile.py
@@ -7,6 +7,7 @@
 import subprocess
 import sys
 import tempfile
+import traceback
 from collections import defaultdict
 from contextlib import contextmanager
 from datetime import datetime
@@ -61,8 +62,8 @@
     validate_private_volumes as validate_private_volumes_script,
     export,
     update_snippets,
+    export_cap_static,
 )
-from scripts import convert_s3
 from scripts.helpers import (
     copy_file,
     volume_barcode_from_folder,
@@ -298,6 +299,7 @@ def import_web_volumes():
             try:
                 import_volume(f.name)
             except IntegrityError:
+                traceback.print_exc()
                 print(" - integrity error; volume already imported? skipping")
 
 
@@ -452,31 +454,30 @@ def retry_export_cases(version_string):
 
 
 @task
-def export_cases_to_s3(reporter="528"):
+def export_cap_static_cases(dest_dir="/tmp/cap_exports", reporter=None, volume=None, last_run_before=None):
     """
-    Export a version to S3 of all cases' texts and metadata
-    by reporter and volume.
+    First step of the static files export process: export cases, one celery task per volume.
     """
-    redacted = True
-    bucket = convert_s3.get_bucket_name(redacted)
-    convert_s3.export_cases_to_s3(bucket, redacted, reporter)
-
-
-@task
-def export_reporters_to_s3():
-    """
-    Run export of all reporters and their contents to S3.
-    """
-    convert_s3.put_reporters_on_s3(redacted=True)
+    print("Scheduling tasks to reindex volumes")
+    volumes = VolumeMetadata.objects.exclude(out_of_scope=True)
+    if volume:
+        volumes = volumes.filter(pk=volume)
+    if reporter:
+        volumes = volumes.filter(reporter_id=reporter)
+    tasks.run_task_for_volumes(
+        export_cap_static.export_cases_by_volume,
+        volumes,
+        last_run_before=last_run_before,
+        dest_dir=dest_dir,
+    )
 
 
 @task
-def export_reporters_to_s3_trial():
+def summarize_cap_static(dest_dir="/tmp/cap_exports"):
     """
-    Run export of all reporters  and their contents to S3
-    for first API page.
+    Second step of the static files export process: add summary files at the reporter level and top level.
     """
-    convert_s3.put_reporters_on_s3_trial(redacted=True)
+    export_cap_static.finalize_reporters(dest_dir)
 
 
 @task
diff --git a/capstone/scripts/convert_s3.py b/capstone/scripts/convert_s3.py
deleted file mode 100644
index 1179595af..000000000
--- a/capstone/scripts/convert_s3.py
+++ /dev/null
@@ -1,522 +0,0 @@
-import base64
-import boto3
-import hashlib
-import json
-import requests
-from botocore.exceptions import ClientError
-from collections import namedtuple
-from celery import group, shared_task
-
-from capapi.documents import CaseDocument
-from capapi.serializers import (
-    ConvertNoLoginCaseDocumentSerializer,
-)
-from capdb.models import Reporter, VolumeMetadata
-
-s3_client = boto3.client("s3")
-api_endpoint = "https://api.case.law/v1/"
-
-
-def put_reporters_on_s3_trial(redacted: bool) -> None:
-    """
-    Kicks off the full cascading S3 file creation series
-    for a subsection of reporters.
-    """
-    # set bucket name for all operations
-    bucket = get_bucket_name(redacted)
-
-    current_endpoint = f"{api_endpoint}reporters/"
-    print("Converting files from ", current_endpoint)
-    response = requests.get(current_endpoint)
-    results = response.json()
-    reporters_metadata = ""
-    all_volumes_metadata = ""
-
-    # write each entry into jsonl
-    for result in results["results"]:
-        # for each reporter, kick off cascading export to S3
-        reporter_metadata, subset_volumes_metadata = export_cases_to_s3(
-            bucket, redacted, result["id"]
-        )
-        reporters_metadata += reporter_metadata
-        all_volumes_metadata += subset_volumes_metadata
-
-    # uploads all reporters metadata to top level
-    hash_and_upload(
-        reporters_metadata,
-        bucket,
-        "ReportersMetadata.jsonl",
-        "application/jsonl",
-    )
-
-    # uploads all volumes metadata to top level
-    hash_and_upload(
-        all_volumes_metadata,
-        bucket,
-        "VolumesMetadata.jsonl",
-        "application/jsonl",
-    )
-
-
-def put_reporters_on_s3(redacted: bool) -> None:
-    """
-    Kicks off the full cascading file creation series.
-    """
-    # set bucket name for all operations
-    bucket = get_bucket_name(redacted)
-
-    current_endpoint = f"{api_endpoint}reporters/"
-    previous_cursor = None
-    current_cursor = ""
-    reporters_metadata = ""
-    all_volumes_metadata = ""
-
-    while current_endpoint:
-        print("Converting files from ", current_endpoint)
-        response = requests.get(current_endpoint)
-        results = response.json()
-
-        # write each entry into jsonl
-        for result in results["results"]:
-            # for each reporter, kick off cascading export to S3
-            reporter_metadata, subset_volumes_metadata = export_cases_to_s3(
-                bucket, redacted, result["id"]
-            )
-            reporters_metadata += reporter_metadata
-            all_volumes_metadata += subset_volumes_metadata
-
-        # update cursor to access next endpoint
-        current_cursor = results["next"]
-        if current_cursor != previous_cursor:
-            print("Update next to: ", current_cursor)
-
-        previous_cursor = current_cursor
-        current_endpoint = current_cursor
-
-    # uploads all reporters metadata to top level
-    hash_and_upload(
-        reporters_metadata,
-        bucket,
-        "ReportersMetadata.jsonl",
-        "application/jsonl",
-    )
-
-    # uploads all volumes metadata to top level
-    hash_and_upload(
-        all_volumes_metadata,
-        bucket,
-        "VolumesMetadata.jsonl",
-        "application/jsonl",
-    )
-
-
-def export_cases_to_s3(bucket: str, redacted: bool, reporter_id: str) -> tuple:
-    """
-    Write .jsonl file with all cases per reporter.
-    """
-    reporter = Reporter.objects.get(pk=reporter_id)
-
-    # Make sure there are volumes in the reporter
-    if not reporter.volumes.exclude(out_of_scope=True):
-        print("WARNING: Reporter '{}' contains NO VOLUMES.".format(reporter.full_name))
-        # Returning empty string to have something to append to reporter metadata
-        return ("", "")
-
-    # Make sure there are cases in the reporter
-    cases_search = CaseDocument.raw_search().filter("term", reporter__id=reporter.id)
-    if cases_search.count() == 0:
-        print("WARNING: Reporter '{}' contains NO CASES.".format(reporter.full_name))
-        # Returning empty string to have something to append to reporter metadata
-        return ("", "")
-
-    # TODO: address reporters that share slug
-    if reporter_id in reporter_slug_dict:
-        reporter_prefix = reporter_slug_dict[reporter_id]
-    else:
-        reporter_prefix = reporter.short_name_slug
-
-    # upload reporter metadata
-    reporter_metadata = put_reporter_metadata(bucket, reporter, reporter_prefix)
-
-    # get in-scope volumes with volume numbers in each reporter
-    subset_volumes_metadata = ""
-
-    job = group(
-        export_cases_by_volume.s(
-            volume=volume.barcode,
-            reporter_prefix=reporter_prefix,
-            dest_bucket=bucket,
-            redacted=redacted,
-        )
-        for volume in (
-                reporter.volumes.exclude(volume_number=None)
-                .exclude(volume_number="")
-                .exclude(out_of_scope=True)
-        )
-    )
-
-    results = job.apply_async()
-
-    for i in range(3):
-        try:
-            for volume_metadata in results.get():
-                subset_volumes_metadata += volume_metadata
-            break
-        except ClientError as err:
-            if err.response['Error']['Code'] == 'NoSuchKey':
-                print(f'NoSuchKey in {reporter_id} on try {i + 1}')
-            else:
-                raise
-
-    return (reporter_metadata, subset_volumes_metadata)
-
-
-@shared_task
-def export_cases_by_volume(
-    volume: str, reporter_prefix: str, dest_bucket: str, redacted: bool
-) -> str:
-    """
-    Write a .json file for each case per volume.
-    Write a .jsonl file with all cases' metadata per volume.
-    Write a .jsonl file with all volume metadata for this collection.
-    """
-
-    volume = VolumeMetadata.objects.get(pk=volume)
-
-    case_file_name_index = 1
-    prev_case_first_page = None
-
-    vars = {
-        "serializer": ConvertNoLoginCaseDocumentSerializer,
-        "query_params": {"body_format": "text"},
-    }
-
-    cases = list(volume.case_metadatas.select_related().order_by("case_id"))
-
-    if len(cases) == 0:
-        print("WARNING: Volume '{}' contains NO CASES.".format(volume.barcode))
-        # Returning empty string to have something to append to volume metadata
-        return ""
-
-    # open each volume and put case text or metadata into file based on format
-    cases_search = CaseDocument.raw_search().filter(
-        "term", volume__barcode=volume.barcode
-    )
-
-    # create a dictionary to grab data from each CaseDocument search object
-    cases_search_by_id = {
-        case_search["_source"]["id"]: case_search for case_search in cases_search.scan()
-    }
-
-    volume_prefix = f"{reporter_prefix}/{volume.volume_number}"
-    volume_metadata = put_volume_metadata(dest_bucket, volume, volume_prefix)
-
-    cases_key = f"{volume_prefix}/Cases/"
-
-    # fetch existing files to compare to what we have
-    s3_contents_hashes = fetch_s3_files(dest_bucket, cases_key)
-
-    # fake Request object used for serializing case with DRF's serializer
-    vars["fake_request"] = namedtuple("Request", ["query_params", "accepted_renderer"])(
-        query_params=vars["query_params"],
-        accepted_renderer=None,
-    )
-    # fake Request object used for serializing cases with DRF's serializer
-    vars["fake_request"] = namedtuple("Request", ["query_params", "accepted_renderer"])(
-        query_params={"body_format": "text"},
-        accepted_renderer=None,
-    )
-
-    # create a metadata contents string to append case metadata content
-    metadata_contents = ""
-
-    # store the serialized case data
-    for case in cases:
-        # identify associated search item to add additional data
-        try:
-            item = cases_search_by_id[case.id]
-        except KeyError:
-            continue
-
-        serializer = vars["serializer"](
-            item["_source"],
-            context={
-                "request": vars["fake_request"],
-                "first_page_order": case.first_page_order,
-                "last_page_order": case.last_page_order,
-            },
-        )
-
-        # add data to metadata_contents string without 'casebody'
-        metadata_data = serializer.data
-        metadata_data.pop("casebody", None)
-        metadata_contents += json.dumps(metadata_data) + "\n"
-
-        # compose each casefile with a hash
-        case_contents = json.dumps(serializer.data) + "\n"
-        hash_object = hashlib.sha256(case_contents.encode("utf-8"))
-        case_contents_hash = base64.b64encode(hash_object.digest()).decode()
-
-        # calculate casefile name
-        if prev_case_first_page == case.first_page:
-            case_file_name_index += 1
-        else:
-            case_file_name_index = 1
-        case_file_name = (
-            f"{case.first_page.zfill(4)}-{str(case_file_name_index).zfill(2)}.json"
-        )
-
-        # set so we can use to determine multiple cases on single page
-        prev_case_first_page = case.first_page
-
-        # identify key: hash pair for current case
-        dest_key = f"{cases_key}{case_file_name}"
-        s3_key_hash = s3_contents_hashes.pop(dest_key, None)
-
-        if s3_key_hash is None or s3_key_hash != case_contents_hash:
-            hash_and_upload(
-                case_contents,
-                dest_bucket,
-                dest_key,
-                "application/jsonl",
-            )
-
-    # remove files from S3 that would otherwise create repeats
-    for s3_case_key in s3_contents_hashes:
-        try:
-            s3_client.delete_object(
-                Bucket=dest_bucket,
-                Key=s3_case_key,
-            )
-        except ClientError as err:
-            if err.response['Error']['Code'] == 'NoSuchKey':
-                print(f"Couldn't delete {s3_case_key}, no such key")
-            else:
-                raise Exception(
-                    f"Couldn't delete {dest_bucket}/{s3_case_key}: %s" % err
-                )
-
-    hash_and_upload(
-        metadata_contents,
-        dest_bucket,
-        f"{volume_prefix}/CasesMetadata.jsonl",
-        "application/jsonl",
-    )
-
-    # copies each volume PDF to new location if it doesn't already exist
-    copy_volume_pdf(volume, volume_prefix, dest_bucket, redacted)
-    # return metadata for single volume
-    return volume_metadata
-
-
-# Reporter-specific helper functions
-
-# Some reporters share a slug, so we have to differentiate with ids
-reporter_slug_dict = {
-    "415": "us-ct-cl",
-    "657": "wv-ct-cl",
-    "580": "mass-app-div-annual",
-    "576": "mass-app-div",
-}
-
-
-def put_reporter_metadata(bucket: str, reporter: object, key: str) -> str:
-    """
-    Write a .json file with just the reporter metadata.
-    Return the line of reporter metadata to be used in all reporters metadata file.
-    """
-    response = requests.get(f"{api_endpoint}reporters/{reporter.id}/")
-    results = response.json()
-
-    # add additional fields from reporter obj
-    results["harvard_hollis_id"] = reporter.hollis
-
-    # remove unnecessary fields
-    results.pop("url", None)
-    results.pop("frontend_url", None)
-    try:
-        for jurisdiction in results["jurisdictions"]:
-            jurisdiction.pop("slug", None)
-            jurisdiction.pop("whitelisted", None)
-            jurisdiction.pop("url", None)
-    except KeyError as err:
-        print(f"Cannot pop field {err} because 'jurisdictions' doesn't exist")
-
-    reporter_metadata = json.dumps(results) + "\n"
-    # add each line to reporters_metadata string
-    hash_and_upload(
-        reporter_metadata, bucket, f"{key}/ReporterMetadata.json", "application/json"
-    )
-    return reporter_metadata
-
-
-# Volume-specific helper functions
-
-
-def put_volume_metadata(bucket: str, volume: object, key: str) -> str:
-    """
-    Write a .json file with just the single volume metadata.
-    """
-    response = requests.get(f"{api_endpoint}volumes/{volume.barcode}/")
-    results = response.json()
-    # change "barcode" key to "id" key
-    results["id"] = results.pop("barcode", None)
-
-    # add additional fields from model
-    results["harvard_hollis_id"] = volume.hollis_number
-    results["spine_start_year"] = volume.spine_start_year
-    results["spine_end_year"] = volume.spine_end_year
-    results["publication_city"] = volume.publication_city
-    results["second_part_of_id"] = volume.second_part_of_id
-
-    # add information about volume's nominative_reporter
-    if volume.nominative_reporter_id:
-        results["nominative_reporter"] = {}
-        results["nominative_reporter"]["id"] = volume.nominative_reporter_id
-        results["nominative_reporter"][
-            "short_name"
-        ] = volume.nominative_reporter.short_name
-        results["nominative_reporter"][
-            "full_name"
-        ] = volume.nominative_reporter.full_name
-        results["nominative_reporter"][
-            "volume_number"
-        ] = volume.nominative_volume_number
-        results.pop("nominative_volume_number", None)
-        results.pop("nominative_name", None)
-    elif volume.nominative_reporter_id is None and (
-        volume.nominative_volume_number or volume.nominative_name
-    ):
-        results["nominative_reporter"] = {}
-        results["nominative_reporter"][
-            "volume_number"
-        ] = volume.nominative_volume_number
-        results["nominative_reporter"]["nominative_name"] = volume.nominative_name
-    else:
-        results["nominative_reporter"] = None
-
-    # remove unnecessary fields
-    results.pop("reporter", None)
-    results.pop("reporter_url", None)
-    results.pop("url", None)
-    results.pop("pdf_url", None)
-    results.pop("frontend_url", None)
-    try:
-        for jurisdiction in results["jurisdictions"]:
-            jurisdiction.pop("slug", None)
-            jurisdiction.pop("whitelisted", None)
-            jurisdiction.pop("url", None)
-    except KeyError as err:
-        print(f"Cannot pop field {err} because 'jurisdictions' doesn't exist")
-
-    volume_metadata = json.dumps(results) + "\n"
-    hash_and_upload(
-        volume_metadata, bucket, f"{key}/VolumeMetadata.json", "application/json"
-    )
-    return volume_metadata
-
-
-def copy_volume_pdf(
-    volume: object, volume_prefix: str, dest_bucket: str, redacted: bool
-) -> None:
-    """
-    Copy PDF volume from original location to destination bucket
-    """
-    if redacted:
-        source_prefix = "pdf/redacted"
-    else:
-        source_prefix = "pdf/unredacted"
-
-    try:
-        s3_client.head_object(Bucket=dest_bucket, Key=f"{volume_prefix}/Volume.pdf")
-        print(f"{dest_bucket}/{volume_prefix}/Volume.pdf already uploaded!")
-    except ClientError as err:
-        if err.response["Error"]["Code"] == "404":
-            # "With a copy command, the checksum of the object is a direct checksum of the full object."
-            # https://docs.aws.amazon.com/AmazonS3/latest/userguide/checking-object-integrity.html
-            copy_source = {
-                "Bucket": "harvard-cap-archive",
-                "Key": f"{source_prefix}/{volume.barcode}.pdf",
-            }
-            copy_object_params = {
-                "Bucket": dest_bucket,
-                "Key": f"{volume_prefix}/Volume.pdf",
-                "CopySource": copy_source,
-            }
-
-            s3_client.copy_object(**copy_object_params)
-            print(
-                f"Copied {source_prefix}/{volume.barcode}.pdf to \
-                {volume_prefix}/Volume.pdf"
-            )
-        else:
-            raise Exception(
-                f"Cannot upload {source_prefix}/{volume.barcode}.pdf to \
-                {volume_prefix}/Volume.pdf: %s"
-                % err
-            )
-
-
-# Case-specific helper functions
-
-
-def fetch_s3_files(bucket: str, key: str) -> dict:
-    """
-    Return a dictionary of bucket contents format key: hash
-    """
-    try:
-        s3_contents_hash = {}
-        response = s3_client.list_objects_v2(Bucket=bucket, Prefix=key)
-    except ClientError as err:
-        raise Exception(f"Cannot list objects {bucket}/{key}: %s" % err)
-    if "Contents" not in response:
-        return s3_contents_hash
-    else:
-        for case in response["Contents"]:
-            # Get the object's metadata
-            try:
-                response = s3_client.get_object_attributes(
-                    Bucket=bucket, Key=case["Key"], ObjectAttributes=["Checksum"]
-                )
-
-                existing_hash = response.get("Checksum", {}).get("ChecksumSHA256")
-                s3_contents_hash[case["Key"]] = existing_hash
-            except ClientError as err:
-                raise Exception(f"Cannot check file {bucket}/{case['Key']}: %s" % err)
-
-    return s3_contents_hash
-
-
-# General helper functions
-
-
-def hash_and_upload(contents: str, bucket: str, key: str, content_type: str) -> None:
-    """
-    Hash created file and upload to S3
-    """
-    # Calculate the SHA256 hash of the contents data
-    hash_object = hashlib.sha256(contents.encode("utf-8"))
-    sha256_hash = base64.b64encode(hash_object.digest()).decode()
-    # upload file to S3
-    try:
-        s3_client.put_object(
-            Body=contents,
-            Bucket=bucket,
-            Key=key,
-            ContentType=content_type,
-            ChecksumSHA256=sha256_hash,
-        )
-        print(f"Completed {key}")
-    except ClientError as err:
-        raise Exception(f"Error uploading {key}: %s" % err)
-
-
-def get_bucket_name(redacted: bool) -> str:
-    """
-    Create bucket name based on redaction status
-    """
-    if redacted:
-        bucket = "cap-redacted"
-    else:
-        bucket = "cap-unredacted"
-    return bucket
diff --git a/capstone/scripts/export.py b/capstone/scripts/export.py
index c1134a3d0..a499ec337 100644
--- a/capstone/scripts/export.py
+++ b/capstone/scripts/export.py
@@ -3,7 +3,6 @@
 import tempfile
 import zipfile
 from io import StringIO
-from collections import namedtuple
 from datetime import date
 from pathlib import Path
 from celery import shared_task
@@ -13,6 +12,7 @@
 from django.utils import timezone
 
 from capapi.documents import CaseDocument
+from capapi.resources import call_serializer
 from capapi.serializers import NoLoginCaseDocumentSerializer, CaseDocumentSerializer
 from capdb.models import Jurisdiction, Reporter
 from capdb.storages import download_files_storage
@@ -155,12 +155,6 @@ def export_case_documents(cases, zip_path, filter_item, public=False):
                 "Bagging-Date: %s\n"
             ) % (filter_item, timezone.now().strftime("%Y-%m-%d"))
 
-            # fake Request object used for serializing cases with DRF's serializer
-            vars['fake_request'] = namedtuple('Request', ['query_params', 'accepted_renderer'])(
-                query_params=vars['query_params'],
-                accepted_renderer=None,
-            )
-
             # create new zip file in memory
             vars['out_spool'] = tempfile.TemporaryFile()
             vars['archive'] = zipfile.ZipFile(vars['out_spool'], 'w', zipfile.ZIP_STORED)
@@ -171,8 +165,8 @@ def export_case_documents(cases, zip_path, filter_item, public=False):
         # write each case
         for item in cases.scan():
             for format_name, vars in formats.items():
-                serializer = vars['serializer'](item['_source'], context={'request': vars['fake_request']})
-                vars['compressed_data_file'].write(bytes(json.dumps(serializer.data), 'utf8') + b'\n')
+                data = call_serializer(vars['serializer'], item['_source'], vars['query_params'])
+                vars['compressed_data_file'].write(bytes(json.dumps(data), 'utf8') + b'\n')
 
         # finish bag for each format
         for format_name, vars in formats.items():
diff --git a/capstone/scripts/export_cap_static.py b/capstone/scripts/export_cap_static.py
new file mode 100644
index 000000000..fbb436188
--- /dev/null
+++ b/capstone/scripts/export_cap_static.py
@@ -0,0 +1,334 @@
+import shutil
+import tempfile
+from pathlib import Path
+
+import boto3
+import json
+from botocore.exceptions import ClientError
+from celery import shared_task
+from django.conf import settings
+from django.db import transaction
+from tqdm import tqdm
+
+from capapi.documents import CaseDocument
+from capapi.resources import call_serializer
+from capapi.serializers import VolumeSerializer, NoLoginCaseDocumentSerializer, ReporterSerializer
+from capdb.models import Reporter, VolumeMetadata, Jurisdiction
+from scripts.update_snippets import get_map_numbers
+
+
+# steps:
+# - export volumes: fab export_cap_static_cases calls export_cases_by_volume()
+# - export reporter metadata: fab summarize_cap_static calls finalize_reporters()
+# - (not in codebase yet) copy PDFs and captars from one part of S3 to another
+
+
+def finalize_reporters(dest_dir: str) -> None:
+    """
+    """
+    dest_dir = Path(dest_dir)
+    for sub_dir in ("redacted", "unredacted"):
+        if (dest_dir / sub_dir).exists():
+            finalize_reporters_dir(dest_dir / sub_dir)
+
+def finalize_reporters_dir(dest_dir: Path) -> None:
+
+    # write missing reporter metadata
+    print("Writing missing reporter metadata")
+    all_volumes = []
+    for reporter_dir in tqdm(dest_dir.iterdir()):
+        if not reporter_dir.is_dir():
+            continue
+        reporter_metadata_path = reporter_dir / "ReporterMetadata.json"
+        if reporter_metadata_path.exists():
+            continue
+
+        # fetch reporter object
+        if reporter_dir.name in reporter_slug_dict_reverse:
+            reporter = Reporter.objects.get(pk=reporter_slug_dict_reverse[reporter_dir.name])
+        else:
+            reporter = Reporter.objects.get(short_name_slug=reporter_dir.name)
+
+        # export reporter metadata
+        reporter_dict = call_serializer(ReporterSerializer, reporter)
+        reporter_dict["harvard_hollis_id"] = reporter.hollis
+        reporter_dict["slug"] = reporter_dir.name
+        remove_keys(reporter_dict, ["url", "frontend_url", ("jurisdictions", ["slug", "whitelisted", "url"])])
+        write_json(reporter_metadata_path, reporter_dict)
+
+        # write reporter-level VolumesMetadata.json
+        print("Writing VolumesMetadata.json")
+        volumes_metadata = [json.loads(f.read_text()) for f in reporter_dir.glob("*/VolumeMetadata.json")]
+        write_json(reporter_dir / "VolumesMetadata.json", volumes_metadata)
+        all_volumes.extend(volumes_metadata)
+
+    # write ReportersMetadata.json
+    print("Writing ReportersMetadata.json")
+    reporters_metadata = [json.loads(f.read_text()) for f in dest_dir.glob("*/ReporterMetadata.json")]
+    write_json(dest_dir / "ReportersMetadata.json", reporters_metadata)
+
+    # write JurisdictionsMetadata.json
+    # this is the same data as ReportersMetadata.json, but with a list of reporters for each jurisdiction
+    # instead of a list of jurisdictions for each reporter
+    print("Writing JurisdictionsMetadata.json")
+    jurisdictions = {}
+    jurisdiction_counts = get_map_numbers()
+    for jurisdiction in Jurisdiction.objects.all():
+        if jurisdiction.slug not in jurisdiction_counts:
+            continue
+        jurisdictions[jurisdiction.id] = {
+            "id": jurisdiction.pk,
+            "slug": jurisdiction.slug,
+            "name": jurisdiction.name,
+            "name_long": jurisdiction.name_long,
+            **jurisdiction_counts[jurisdiction.slug],
+            "reporters": [],
+        }
+
+    for reporter in reporters_metadata:
+        reporter_jurisdictions = reporter.pop("jurisdictions")
+        for jurisdiction in reporter_jurisdictions:
+            jurisdictions[jurisdiction["id"]]["reporters"].append(reporter)
+
+    jurisdictions = [j for j in sorted(jurisdictions.values(), key=lambda j: j["name_long"])]
+    write_json(dest_dir / "JurisdictionsMetadata.json", jurisdictions)
+
+    # write top-level VolumesMetadata.json
+    print("Writing VolumesMetadata.json")
+    write_json(dest_dir / "VolumesMetadata.json", all_volumes)
+
+
+@shared_task
+def export_cases_by_volume(volume: str, dest_dir: str) -> None:
+    volume = VolumeMetadata.objects.select_related("reporter").get(pk=volume)
+    dest_dir = Path(dest_dir)
+    export_volume(volume, dest_dir / "redacted")
+
+    # export unredacted version of redacted volumes
+    if settings.REDACTION_KEY and volume.redacted:
+        # use a transaction to temporarily unredact the volume, then roll back
+        with transaction.atomic('capdb'):
+            volume.unredact(replace_pdf=False)
+            export_volume(volume, dest_dir / "unredacted")
+            transaction.set_rollback(True, using='capdb')
+
+def export_volume(volume: VolumeMetadata, dest_dir: Path) -> None:
+    """
+    Write a .json file for each case per volume.
+    Write an .html file for each case per volume.
+    Write a .json file with all case metadata per volume.
+    Write a .json file with all volume metadata for this collection.
+    """
+
+    # set up vars
+    print("Exporting volume", volume.get_frontend_url())
+    reporter_prefix = reporter_slug_dict.get(volume.reporter_id, volume.reporter.short_name_slug)
+    volume_dir = dest_dir / reporter_prefix / volume.volume_number
+
+    # don't overwrite existing volumes
+    if volume_dir.exists():
+        return
+
+    # find cases to write
+    cases = list(volume.case_metadatas.filter(in_scope=True).for_indexing().order_by('case_id'))
+    if not cases:
+        print(f"WARNING: Volume '{volume.barcode}' contains NO CASES.")
+        return
+
+    # set up temp volume dir
+    temp_dir = tempfile.TemporaryDirectory()
+    temp_volume_dir = Path(temp_dir.name)
+    cases_dir = temp_volume_dir / "cases"
+    cases_dir.mkdir()
+    html_dir = temp_volume_dir / "html"
+    html_dir.mkdir()
+    volume_metadata = volume_to_dict(volume)
+    write_json(temp_volume_dir / "VolumeMetadata.json", volume_metadata)
+
+    # variables for case export loop
+    case_file_name_index = 1
+    prev_case_first_page = None
+    case_metadatas = []
+    case_doc = CaseDocument()
+
+    # store the serialized case data
+    for case in cases:
+        # convert case model to search index format
+        search_item = case_doc.prepare(case)
+        search_item['last_updated'] = search_item['last_updated'].isoformat()
+        search_item['decision_date'] = search_item['decision_date'].isoformat()
+
+        # convert search index format to API format
+        case_data = call_serializer(NoLoginCaseDocumentSerializer, search_item, {"body_format": "text"})
+
+        # update case_data to match our output format:
+        if "casebody" in case_data:
+            case_data["casebody"] = case_data["casebody"]["data"]
+        case_data["first_page_order"] = case.first_page_order
+        case_data["last_page_order"] = case.last_page_order
+        remove_keys(case_data, [
+            "reporter",
+            "volume",
+            "url",
+            "frontend_url",
+            "frontend_pdf_url",
+            "preview",
+            ("court", ["slug", "url"]),
+            ("jurisdiction", ["slug", "whitelisted", "url"]),
+        ])
+        for cite in case_data["cites_to"]:
+            cite["opinion_index"] = cite.pop("opinion_id")
+
+        # calculate casefile name
+        first_page = case_data["first_page"]
+        if prev_case_first_page == first_page:
+            case_file_name_index += 1
+        else:
+            case_file_name_index = 1
+        prev_case_first_page = first_page
+        case_file_name = f"{first_page:0>4}-{case_file_name_index:0>2}.json"
+
+        # write casefile
+        write_json(cases_dir / case_file_name, case_data)
+
+        # write metadata without 'casebody'
+        case_data.pop("casebody", None)
+        case_metadatas.append(case_data)
+
+        # write html file
+        html_file_path = (html_dir / case_file_name).with_suffix(".html")
+        html_file_path.write_text(search_item["casebody_data"]["html"])
+
+    # write metadata file
+    write_json(temp_volume_dir / "CasesMetadata.json", case_metadatas)
+
+    # move to real directory
+    volume_dir.parent.mkdir(exist_ok=True, parents=True)
+    shutil.copytree(temp_volume_dir, volume_dir)
+
+
+def volume_to_dict(volume: VolumeMetadata) -> dict:
+    """
+    Write a .json file with just the single volume metadata.
+    """
+    volume_data = call_serializer(VolumeSerializer, volume)
+
+    # change "barcode" key to "id" key
+    volume_data["id"] = volume_data.pop("barcode", None)
+
+    # add additional fields from model
+    volume_data["harvard_hollis_id"] = volume.hollis_number
+    volume_data["spine_start_year"] = volume.spine_start_year
+    volume_data["spine_end_year"] = volume.spine_end_year
+    volume_data["publication_city"] = volume.publication_city
+    volume_data["second_part_of_id"] = volume.second_part_of_id
+
+    # add information about volume's nominative_reporter
+    if volume.nominative_reporter_id:
+        volume_data["nominative_reporter"] = {
+            "id": volume.nominative_reporter_id,
+            "short_name": volume.nominative_reporter.short_name,
+            "full_name": volume.nominative_reporter.full_name,
+            "volume_number": volume.nominative_volume_number
+        }
+    elif volume.nominative_volume_number or volume.nominative_name:
+        volume_data["nominative_reporter"] = {
+            "volume_number": volume.nominative_volume_number,
+            "nominative_name": volume.nominative_name,
+        }
+    else:
+        volume_data["nominative_reporter"] = None
+
+    # remove unnecessary fields
+    remove_keys(volume_data, [
+        "reporter",
+        "reporter_url",
+        "url",
+        "pdf_url",
+        "frontend_url",
+        "nominative_volume_number",
+        "nominative_name",
+        ("jurisdictions", ["slug", "whitelisted", "url"]),
+    ])
+
+    return volume_data
+
+
+def copy_volume_pdf(
+    volume: object, volume_prefix: str, dest_bucket: str, redacted: bool
+) -> None:
+    """
+    Copy PDF volume from original location to destination bucket
+    """
+    s3_client = boto3.client("s3")
+
+    if redacted:
+        source_prefix = "pdf/redacted"
+    else:
+        source_prefix = "pdf/unredacted"
+
+    try:
+        s3_client.head_object(Bucket=dest_bucket, Key=f"{volume_prefix}/Volume.pdf")
+        print(f"{dest_bucket}/{volume_prefix}/Volume.pdf already uploaded!")
+    except ClientError as err:
+        if err.response["Error"]["Code"] == "404":
+            # "With a copy command, the checksum of the object is a direct checksum of the full object."
+            # https://docs.aws.amazon.com/AmazonS3/latest/userguide/checking-object-integrity.html
+            copy_source = {
+                "Bucket": "harvard-cap-archive",
+                "Key": f"{source_prefix}/{volume.barcode}.pdf",
+            }
+            copy_object_params = {
+                "Bucket": dest_bucket,
+                "Key": f"{volume_prefix}/Volume.pdf",
+                "CopySource": copy_source,
+            }
+
+            s3_client.copy_object(**copy_object_params)
+            print(
+                f"Copied {source_prefix}/{volume.barcode}.pdf to \
+                {volume_prefix}/Volume.pdf"
+            )
+        else:
+            raise Exception(
+                f"Cannot upload {source_prefix}/{volume.barcode}.pdf to \
+                {volume_prefix}/Volume.pdf: %s"
+                % err
+            )
+
+
+
+### helpers ###
+
+# Some reporters share a slug, so we have to differentiate with ids
+reporter_slug_dict = {
+    415: "us-ct-cl",
+    657: "wv-ct-cl",
+    580: "mass-app-div-annual",
+    576: "mass-app-div",
+}
+reporter_slug_dict_reverse = {v: k for k, v in reporter_slug_dict.items()}
+
+def remove_keys(results: dict, keys: list) -> dict:
+    """
+    Remove keys from results dict
+    """
+    for key in keys:
+        if type(key) is tuple:
+            key, subkeys = key
+            if key in results:
+                value = results[key]
+                if type(value) is list:
+                    for subvalue in value:
+                        remove_keys(subvalue, subkeys)
+                else:
+                    remove_keys(value, subkeys)
+        else:
+            results.pop(key, None)
+    return results
+
+def write_json(path: Path, contents) -> None:
+    """
+    Write contents to path
+    """
+    path.write_text(json.dumps(contents, indent=2) + "\n")
diff --git a/capstone/scripts/tests/test_cap_static.py b/capstone/scripts/tests/test_cap_static.py
new file mode 100644
index 000000000..e90feed2e
--- /dev/null
+++ b/capstone/scripts/tests/test_cap_static.py
@@ -0,0 +1,48 @@
+import shutil
+from pathlib import Path
+
+import pytest
+from django.conf import settings
+
+from capdb.models import VolumeMetadata
+from fabfile import export_cap_static_cases, summarize_cap_static, update_elasticsearch_from_queue
+from test_data.test_fixtures.helpers import check_path
+
+
+@pytest.mark.django_db(databases=['capdb'])
+def test_export_cap_static(case_factory, jurisdiction_factory, redacted_case_factory, volume_metadata_factory, reporter_factory, tmp_path, pytestconfig, elasticsearch, django_assert_num_queries):
+    # set up a reporter with two volumes, each with three cases
+    jurisdiction = jurisdiction_factory(name_long="United States", name="U.S.", slug='us')
+    jurisdiction2 = jurisdiction_factory(name_long="Massachusetts", name="Mass.", slug='mass')
+    reporter = reporter_factory(full_name="United States Reports", short_name="U.S.", short_name_slug='us')
+    reporter.jurisdictions.set([jurisdiction, jurisdiction2])
+    volumes = [volume_metadata_factory(volume_number=volume_number, reporter=reporter, redacted=True) for volume_number in ("1", "2")]
+    for volume in volumes:
+        case_factory(volume=volume, first_page="1", reporter=reporter, jurisdiction=jurisdiction)
+        case_factory(volume=volume, first_page="2", reporter=reporter, jurisdiction=jurisdiction)
+        redacted_case_factory(volume=volume, first_page="2", reporter=reporter, jurisdiction=jurisdiction2)
+    # for some reason case_factory is creating extra volumes, so delete those
+    VolumeMetadata.objects.exclude(pk__in=[v.pk for v in volumes]).update(out_of_scope=True)
+    update_elasticsearch_from_queue()
+
+    # run export to temp dir
+    with django_assert_num_queries(select=37, update=8, insert=2, delete=2, rollback=2):
+        export_cap_static_cases(dest_dir=str(tmp_path))
+    with django_assert_num_queries(select=8):
+        summarize_cap_static(str(tmp_path))
+
+    # compare temp dir to test_data/cap_static
+    cap_static_dir = Path(settings.BASE_DIR, 'test_data/cap_static')
+    if pytestconfig.getoption('recreate_files'):
+        # if --recreate-files was passed, copy temp dir to test_data/cap_static instead of checking
+        if cap_static_dir.exists():
+            shutil.rmtree(cap_static_dir)
+        shutil.copytree(tmp_path, cap_static_dir)
+    else:
+        cap_static_paths = [p.relative_to(cap_static_dir) for p in cap_static_dir.rglob('*')]
+        tmp_paths = [p.relative_to(tmp_path) for p in tmp_path.rglob('*')]
+        assert cap_static_paths == tmp_paths, "Missing or extra files in cap_static export."
+        for path in tmp_path.rglob('*'):
+            if not path.is_file():
+                continue
+            check_path(pytestconfig, path, cap_static_dir / path.relative_to(tmp_path))
diff --git a/capstone/scripts/tests/test_fastcase.py b/capstone/scripts/tests/test_fastcase.py
index 78deefcf2..2c2f3d831 100644
--- a/capstone/scripts/tests/test_fastcase.py
+++ b/capstone/scripts/tests/test_fastcase.py
@@ -13,7 +13,7 @@
 from fabfile import refresh_case_body_cache
 from scripts.fastcase import ingest_fastcase
 from scripts.fastcase.format_fastcase import segment_paragraphs
-from test_data.test_fixtures.helpers import sort_nested_dict
+from test_data.test_fixtures.helpers import sort_nested_dict, check_path
 
 
 @pytest.mark.parametrize("input,expected", [
@@ -66,19 +66,6 @@ def test_fastcase_ingest(tmp_path, pytestconfig, elasticsearch):
     copy_tree(str(fastcase_dir), str(tmp_path))
     management.call_command('loaddata', 'capdb/fixtures/jurisdiction.capdb.json.gz', 'capdb/fixtures/reporter.capdb.json.gz', database='capdb')
 
-    # helper to check whether files have changed
-    def check_path(new_contents, saved_path):
-        if isinstance(new_contents, Path):
-            new_contents = new_contents.read_text()
-        old_contents = saved_path.read_text() if saved_path.exists() else ''
-        if new_contents != old_contents:
-            if pytestconfig.getoption('recreate_fastcase_files'):
-                saved_path.write_text(new_contents)
-            elif old_contents:
-                assert new_contents == old_contents, f"File {saved_path} has changed. Run pytest -k test_fastcase_ingest --recreate_fastcase_files to update."
-            else:
-                assert False, f"File {saved_path} does not exist. Run pytest -k test_fastcase_ingest --recreate_fastcase_files to update."
-
     # run the ingest
     ingest_fastcase.pack_volumes(tmp_path, recreate=True)
     ingest_fastcase.main(batch='test_batch', base_dir=tmp_path)
@@ -104,10 +91,11 @@ def check_path(new_contents, saved_path):
             case_data['has_body_cache'] = bool(case.body_cache)
             cases[case.case_id] = case_data
             # check case html for changes
-            check_path(case.body_cache.html, fastcase_dir.joinpath(case.fastcase_import.path).with_suffix('.html'))
+            check_path(pytestconfig, case.body_cache.html,
+                       fastcase_dir.joinpath(case.fastcase_import.path).with_suffix('.html'))
         volume_data['cases'] = cases
         data[volume.pk] = volume_data
     data = sort_nested_dict(data)
 
     # check metadata files for changes
-    check_path(yaml.dump(data), fastcase_dir / 'data.yml')
+    check_path(pytestconfig, yaml.dump(data), fastcase_dir / 'data.yml')
diff --git a/capstone/scripts/update_snippets.py b/capstone/scripts/update_snippets.py
index 4e0ba8643..f5ca6dc8b 100644
--- a/capstone/scripts/update_snippets.py
+++ b/capstone/scripts/update_snippets.py
@@ -112,6 +112,11 @@ def update_map_numbers():
     """ Write map_numbers snippet. """
     label = "map_numbers"
     snippet_format = "application/json"
+    output = get_map_numbers()
+    write_update(label, snippet_format, json.dumps(output))
+
+
+def get_map_numbers():
     cursor = connections['capdb'].cursor()
     cursor.execute(r"""
         SELECT 
@@ -121,16 +126,19 @@ def update_map_numbers():
           COUNT(DISTINCT c.reporter_id) AS reporter_count,
           SUM(CASE WHEN (c.first_page||c.last_page)~E'^\\d+$' THEN c.last_page::integer-c.first_page::integer+1 ELSE 1 END) AS page_count
         FROM capdb_jurisdiction j 
-          LEFT JOIN capdb_casemetadata c ON j.id=c.jurisdiction_id 
+          JOIN capdb_casemetadata c ON j.id=c.jurisdiction_id 
+          JOIN capdb_volumemetadata v ON c.volume_id=v.barcode
         WHERE
           c.in_scope IS True
+          AND v.out_of_scope IS False
         GROUP BY j.id;
     """)
     # get column names from sql query
     cols = [col[0] for col in cursor.description]
     # create output where each key is a jurisdiction and each value is a dict of values from the sql query
     output = {row[0]: dict(zip(cols[1:], row[1:])) for row in cursor.fetchall()}
-    write_update(label, snippet_format, json.dumps(output))
+    return output
+
 
 def search_jurisdiction_list():
     jurisdictions = [ (jurisdiction.slug, jurisdiction.name_long)
diff --git a/capstone/test_data/cap_static/redacted/JurisdictionsMetadata.json b/capstone/test_data/cap_static/redacted/JurisdictionsMetadata.json
new file mode 100644
index 000000000..459e5a1ac
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/JurisdictionsMetadata.json
@@ -0,0 +1,44 @@
+[
+  {
+    "id": 2,
+    "slug": "mass",
+    "name": "Mass.",
+    "name_long": "Massachusetts",
+    "case_count": 2,
+    "volume_count": 2,
+    "reporter_count": 1,
+    "page_count": 10,
+    "reporters": [
+      {
+        "id": 1,
+        "full_name": "United States Reports",
+        "short_name": "U.S.",
+        "start_year": 1900,
+        "end_year": 2000,
+        "harvard_hollis_id": [],
+        "slug": "us"
+      }
+    ]
+  },
+  {
+    "id": 1,
+    "slug": "us",
+    "name": "U.S.",
+    "name_long": "United States",
+    "case_count": 4,
+    "volume_count": 2,
+    "reporter_count": 1,
+    "page_count": 20,
+    "reporters": [
+      {
+        "id": 1,
+        "full_name": "United States Reports",
+        "short_name": "U.S.",
+        "start_year": 1900,
+        "end_year": 2000,
+        "harvard_hollis_id": [],
+        "slug": "us"
+      }
+    ]
+  }
+]
diff --git a/capstone/test_data/cap_static/redacted/ReportersMetadata.json b/capstone/test_data/cap_static/redacted/ReportersMetadata.json
new file mode 100644
index 000000000..d166b62ca
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/ReportersMetadata.json
@@ -0,0 +1,23 @@
+[
+  {
+    "id": 1,
+    "full_name": "United States Reports",
+    "short_name": "U.S.",
+    "start_year": 1900,
+    "end_year": 2000,
+    "jurisdictions": [
+      {
+        "id": 2,
+        "name": "Mass.",
+        "name_long": "Massachusetts"
+      },
+      {
+        "id": 1,
+        "name": "U.S.",
+        "name_long": "United States"
+      }
+    ],
+    "harvard_hollis_id": [],
+    "slug": "us"
+  }
+]
diff --git a/capstone/test_data/cap_static/redacted/VolumesMetadata.json b/capstone/test_data/cap_static/redacted/VolumesMetadata.json
new file mode 100644
index 000000000..72c2be61a
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/VolumesMetadata.json
@@ -0,0 +1,60 @@
+[
+  [
+    {
+      "volume_number": "1",
+      "title": null,
+      "publisher": null,
+      "publication_year": null,
+      "start_year": null,
+      "end_year": null,
+      "series_volume_number": null,
+      "jurisdictions": [
+        {
+          "id": 2,
+          "name": "Mass.",
+          "name_long": "Massachusetts"
+        },
+        {
+          "id": 1,
+          "name": "U.S.",
+          "name_long": "United States"
+        }
+      ],
+      "id": "4909170303750",
+      "harvard_hollis_id": null,
+      "spine_start_year": null,
+      "spine_end_year": null,
+      "publication_city": null,
+      "second_part_of_id": null,
+      "nominative_reporter": null
+    },
+    {
+      "volume_number": "2",
+      "title": null,
+      "publisher": null,
+      "publication_year": null,
+      "start_year": null,
+      "end_year": null,
+      "series_volume_number": null,
+      "jurisdictions": [
+        {
+          "id": 2,
+          "name": "Mass.",
+          "name_long": "Massachusetts"
+        },
+        {
+          "id": 1,
+          "name": "U.S.",
+          "name_long": "United States"
+        }
+      ],
+      "id": "5012832128833",
+      "harvard_hollis_id": null,
+      "spine_start_year": null,
+      "spine_end_year": null,
+      "publication_city": null,
+      "second_part_of_id": null,
+      "nominative_reporter": null
+    }
+  ]
+]
diff --git a/capstone/test_data/cap_static/redacted/us/1/CasesMetadata.json b/capstone/test_data/cap_static/redacted/us/1/CasesMetadata.json
new file mode 100644
index 000000000..fb954bb3f
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/1/CasesMetadata.json
@@ -0,0 +1,136 @@
+[
+  {
+    "id": 1,
+    "name": "First Foo0 versus First Bar0",
+    "name_abbreviation": "Foo0 v. Bar0",
+    "decision_date": "1900-01-01",
+    "docket_number": "",
+    "first_page": "1",
+    "last_page": "5",
+    "citations": [
+      {
+        "type": "official",
+        "cite": "28 U.S. 347"
+      }
+    ],
+    "court": {
+      "name_abbreviation": "Sound spend.",
+      "id": 1,
+      "name": "Father worry common past recognize."
+    },
+    "jurisdiction": {
+      "id": 1,
+      "name_long": "United States",
+      "name": "U.S."
+    },
+    "cites_to": [
+      {
+        "cite": "362 U.S. 816",
+        "category": null,
+        "reporter": null,
+        "opinion_index": -1
+      }
+    ],
+    "analysis": {
+      "random_id": 3210483407,
+      "random_bucket": 5839
+    },
+    "last_updated": "2023-12-04T18:17:29.088002+00:00",
+    "provenance": {
+      "date_added": "2023-12-04",
+      "source": "Harvard",
+      "batch": "2018"
+    },
+    "first_page_order": 3,
+    "last_page_order": 7
+  },
+  {
+    "id": 2,
+    "name": "First Foo1 versus First Bar1",
+    "name_abbreviation": "Foo1 v. Bar1",
+    "decision_date": "1901-01-01",
+    "docket_number": "",
+    "first_page": "2",
+    "last_page": "6",
+    "citations": [
+      {
+        "type": "official",
+        "cite": "257 U.S. 222"
+      }
+    ],
+    "court": {
+      "name_abbreviation": "Upon.",
+      "id": 2,
+      "name": "Opportunity cup speech."
+    },
+    "jurisdiction": {
+      "id": 1,
+      "name_long": "United States",
+      "name": "U.S."
+    },
+    "cites_to": [
+      {
+        "cite": "934 U.S. 230",
+        "category": null,
+        "reporter": null,
+        "opinion_index": -1
+      }
+    ],
+    "analysis": {
+      "random_id": 1950914210,
+      "random_bucket": 38562
+    },
+    "last_updated": "2023-12-04T18:17:29.088002+00:00",
+    "provenance": {
+      "date_added": "2023-12-04",
+      "source": "Harvard",
+      "batch": "2018"
+    },
+    "first_page_order": 4,
+    "last_page_order": 8
+  },
+  {
+    "id": 3,
+    "name": "First Foo2 versus First Bar2",
+    "name_abbreviation": "Foo2 v. Bar2",
+    "decision_date": "1902-01-01",
+    "docket_number": "",
+    "first_page": "2",
+    "last_page": "6",
+    "citations": [
+      {
+        "type": "official",
+        "cite": "311 U.S. 951"
+      }
+    ],
+    "court": {
+      "name_abbreviation": "Rule six your.",
+      "id": 3,
+      "name": "Little perhaps look many."
+    },
+    "jurisdiction": {
+      "id": 2,
+      "name_long": "Massachusetts",
+      "name": "Mass."
+    },
+    "cites_to": [],
+    "analysis": {
+      "cardinality": 2,
+      "char_count": 14,
+      "ocr_confidence": 0,
+      "sha256": "8874c1d06c05904e12fef4e76fcdd0ce48b33013e2067d5ebba936f78b8c5d89",
+      "simhash": "1:0000000000000000",
+      "word_count": 2,
+      "random_id": 2863198571,
+      "random_bucket": 61803
+    },
+    "last_updated": "2023-12-04T18:17:29.088002+00:00",
+    "provenance": {
+      "date_added": "2023-12-04",
+      "source": "Harvard",
+      "batch": "2018"
+    },
+    "first_page_order": 4,
+    "last_page_order": 8
+  }
+]
diff --git a/capstone/test_data/cap_static/redacted/us/1/VolumeMetadata.json b/capstone/test_data/cap_static/redacted/us/1/VolumeMetadata.json
new file mode 100644
index 000000000..2f4470a42
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/1/VolumeMetadata.json
@@ -0,0 +1,28 @@
+{
+  "volume_number": "1",
+  "title": null,
+  "publisher": null,
+  "publication_year": null,
+  "start_year": null,
+  "end_year": null,
+  "series_volume_number": null,
+  "jurisdictions": [
+    {
+      "id": 2,
+      "name": "Mass.",
+      "name_long": "Massachusetts"
+    },
+    {
+      "id": 1,
+      "name": "U.S.",
+      "name_long": "United States"
+    }
+  ],
+  "id": "4909170303750",
+  "harvard_hollis_id": null,
+  "spine_start_year": null,
+  "spine_end_year": null,
+  "publication_city": null,
+  "second_part_of_id": null,
+  "nominative_reporter": null
+}
diff --git a/capstone/test_data/cap_static/redacted/us/1/cases/0001-01.json b/capstone/test_data/cap_static/redacted/us/1/cases/0001-01.json
new file mode 100644
index 000000000..d9010b57b
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/1/cases/0001-01.json
@@ -0,0 +1,66 @@
+{
+  "id": 1,
+  "name": "First Foo0 versus First Bar0",
+  "name_abbreviation": "Foo0 v. Bar0",
+  "decision_date": "1900-01-01",
+  "docket_number": "",
+  "first_page": "1",
+  "last_page": "5",
+  "citations": [
+    {
+      "type": "official",
+      "cite": "28 U.S. 347"
+    }
+  ],
+  "court": {
+    "name_abbreviation": "Sound spend.",
+    "id": 1,
+    "name": "Father worry common past recognize."
+  },
+  "jurisdiction": {
+    "id": 1,
+    "name_long": "United States",
+    "name": "U.S."
+  },
+  "cites_to": [
+    {
+      "cite": "362 U.S. 816",
+      "category": null,
+      "reporter": null,
+      "opinion_index": -1
+    }
+  ],
+  "analysis": {
+    "random_id": 3210483407,
+    "random_bucket": 5839
+  },
+  "last_updated": "2023-12-04T18:17:29.088002+00:00",
+  "provenance": {
+    "date_added": "2023-12-04",
+    "source": "Harvard",
+    "batch": "2018"
+  },
+  "casebody": {
+    "judges": [
+      "Fearing, C.J., and Korsmo, J., concur."
+    ],
+    "parties": [
+      "In the Matter of the Marriage of Christy Lyle, Respondent, and Keith Lyle, Appellant."
+    ],
+    "opinions": [
+      {
+        "text": "Opinion text",
+        "type": "majority",
+        "author": "Pennell, J."
+      }
+    ],
+    "attorneys": [
+      "Matthew J. Dudley, for appellant.",
+      "Camerina I. Brokaw-Zorrozua (of Maxey Law Office PS), for respondent."
+    ],
+    "corrections": "",
+    "head_matter": "head matter"
+  },
+  "first_page_order": 3,
+  "last_page_order": 7
+}
diff --git a/capstone/test_data/cap_static/redacted/us/1/cases/0002-01.json b/capstone/test_data/cap_static/redacted/us/1/cases/0002-01.json
new file mode 100644
index 000000000..099ae6342
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/1/cases/0002-01.json
@@ -0,0 +1,66 @@
+{
+  "id": 2,
+  "name": "First Foo1 versus First Bar1",
+  "name_abbreviation": "Foo1 v. Bar1",
+  "decision_date": "1901-01-01",
+  "docket_number": "",
+  "first_page": "2",
+  "last_page": "6",
+  "citations": [
+    {
+      "type": "official",
+      "cite": "257 U.S. 222"
+    }
+  ],
+  "court": {
+    "name_abbreviation": "Upon.",
+    "id": 2,
+    "name": "Opportunity cup speech."
+  },
+  "jurisdiction": {
+    "id": 1,
+    "name_long": "United States",
+    "name": "U.S."
+  },
+  "cites_to": [
+    {
+      "cite": "934 U.S. 230",
+      "category": null,
+      "reporter": null,
+      "opinion_index": -1
+    }
+  ],
+  "analysis": {
+    "random_id": 1950914210,
+    "random_bucket": 38562
+  },
+  "last_updated": "2023-12-04T18:17:29.088002+00:00",
+  "provenance": {
+    "date_added": "2023-12-04",
+    "source": "Harvard",
+    "batch": "2018"
+  },
+  "casebody": {
+    "judges": [
+      "Fearing, C.J., and Korsmo, J., concur."
+    ],
+    "parties": [
+      "In the Matter of the Marriage of Christy Lyle, Respondent, and Keith Lyle, Appellant."
+    ],
+    "opinions": [
+      {
+        "text": "Opinion text",
+        "type": "majority",
+        "author": "Pennell, J."
+      }
+    ],
+    "attorneys": [
+      "Matthew J. Dudley, for appellant.",
+      "Camerina I. Brokaw-Zorrozua (of Maxey Law Office PS), for respondent."
+    ],
+    "corrections": "",
+    "head_matter": "head matter"
+  },
+  "first_page_order": 4,
+  "last_page_order": 8
+}
diff --git a/capstone/test_data/cap_static/redacted/us/1/cases/0002-02.json b/capstone/test_data/cap_static/redacted/us/1/cases/0002-02.json
new file mode 100644
index 000000000..3dd2a37bc
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/1/cases/0002-02.json
@@ -0,0 +1,58 @@
+{
+  "id": 3,
+  "name": "First Foo2 versus First Bar2",
+  "name_abbreviation": "Foo2 v. Bar2",
+  "decision_date": "1902-01-01",
+  "docket_number": "",
+  "first_page": "2",
+  "last_page": "6",
+  "citations": [
+    {
+      "type": "official",
+      "cite": "311 U.S. 951"
+    }
+  ],
+  "court": {
+    "name_abbreviation": "Rule six your.",
+    "id": 3,
+    "name": "Little perhaps look many."
+  },
+  "jurisdiction": {
+    "id": 2,
+    "name_long": "Massachusetts",
+    "name": "Mass."
+  },
+  "cites_to": [],
+  "analysis": {
+    "cardinality": 2,
+    "char_count": 14,
+    "ocr_confidence": 0,
+    "sha256": "8874c1d06c05904e12fef4e76fcdd0ce48b33013e2067d5ebba936f78b8c5d89",
+    "simhash": "1:0000000000000000",
+    "word_count": 2,
+    "random_id": 2863198571,
+    "random_bucket": 61803
+  },
+  "last_updated": "2023-12-04T18:17:29.088002+00:00",
+  "provenance": {
+    "date_added": "2023-12-04",
+    "source": "Harvard",
+    "batch": "2018"
+  },
+  "casebody": {
+    "judges": [],
+    "parties": [],
+    "opinions": [
+      {
+        "text": "not redacted",
+        "type": "majority",
+        "author": null
+      }
+    ],
+    "attorneys": [],
+    "corrections": "",
+    "head_matter": ""
+  },
+  "first_page_order": 4,
+  "last_page_order": 8
+}
diff --git a/capstone/test_data/cap_static/redacted/us/1/html/0001-01.html b/capstone/test_data/cap_static/redacted/us/1/html/0001-01.html
new file mode 100644
index 000000000..5357a97ee
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/1/html/0001-01.html
@@ -0,0 +1 @@
+<p>Case html 0</p>
\ No newline at end of file
diff --git a/capstone/test_data/cap_static/redacted/us/1/html/0002-01.html b/capstone/test_data/cap_static/redacted/us/1/html/0002-01.html
new file mode 100644
index 000000000..56e046328
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/1/html/0002-01.html
@@ -0,0 +1 @@
+<p>Case html 1</p>
\ No newline at end of file
diff --git a/capstone/test_data/cap_static/redacted/us/1/html/0002-02.html b/capstone/test_data/cap_static/redacted/us/1/html/0002-02.html
new file mode 100644
index 000000000..13bc3490b
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/1/html/0002-02.html
@@ -0,0 +1,6 @@
+<section class="casebody" data-case-id="00000002" data-firstpage="2" data-lastpage="6">
+  <section class="head-matter"></section>
+  <article class="opinion" data-type="majority">
+    <p id="b1-2" data-blocks='[["BL_1.2",2,[4,32,100,100]],["BL_1.3",2,[225,11,430,290]]]'>not redacted</p>
+  </article>
+</section>
diff --git a/capstone/test_data/cap_static/redacted/us/2/CasesMetadata.json b/capstone/test_data/cap_static/redacted/us/2/CasesMetadata.json
new file mode 100644
index 000000000..6d1ea2ac7
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/2/CasesMetadata.json
@@ -0,0 +1,136 @@
+[
+  {
+    "id": 4,
+    "name": "First Foo3 versus First Bar3",
+    "name_abbreviation": "Foo3 v. Bar3",
+    "decision_date": "1903-01-01",
+    "docket_number": "",
+    "first_page": "1",
+    "last_page": "5",
+    "citations": [
+      {
+        "type": "official",
+        "cite": "447 U.S. 189"
+      }
+    ],
+    "court": {
+      "name_abbreviation": "Quickly walk.",
+      "id": 4,
+      "name": "Focus detail several position."
+    },
+    "jurisdiction": {
+      "id": 1,
+      "name_long": "United States",
+      "name": "U.S."
+    },
+    "cites_to": [
+      {
+        "cite": "524 U.S. 591",
+        "category": null,
+        "reporter": null,
+        "opinion_index": -1
+      }
+    ],
+    "analysis": {
+      "random_id": 3673096554,
+      "random_bucket": 362
+    },
+    "last_updated": "2023-12-04T18:17:29.088002+00:00",
+    "provenance": {
+      "date_added": "2023-12-04",
+      "source": "Harvard",
+      "batch": "2018"
+    },
+    "first_page_order": 3,
+    "last_page_order": 7
+  },
+  {
+    "id": 5,
+    "name": "First Foo4 versus First Bar4",
+    "name_abbreviation": "Foo4 v. Bar4",
+    "decision_date": "1904-01-01",
+    "docket_number": "",
+    "first_page": "2",
+    "last_page": "6",
+    "citations": [
+      {
+        "type": "official",
+        "cite": "872 U.S. 266"
+      }
+    ],
+    "court": {
+      "name_abbreviation": "Like area.",
+      "id": 5,
+      "name": "Commercial edge agency ground risk."
+    },
+    "jurisdiction": {
+      "id": 1,
+      "name_long": "United States",
+      "name": "U.S."
+    },
+    "cites_to": [
+      {
+        "cite": "596 U.S. 768",
+        "category": null,
+        "reporter": null,
+        "opinion_index": -1
+      }
+    ],
+    "analysis": {
+      "random_id": 2595981630,
+      "random_bucket": 35134
+    },
+    "last_updated": "2023-12-04T18:17:29.088002+00:00",
+    "provenance": {
+      "date_added": "2023-12-04",
+      "source": "Harvard",
+      "batch": "2018"
+    },
+    "first_page_order": 4,
+    "last_page_order": 8
+  },
+  {
+    "id": 6,
+    "name": "First Foo5 versus First Bar5",
+    "name_abbreviation": "Foo5 v. Bar5",
+    "decision_date": "1905-01-01",
+    "docket_number": "",
+    "first_page": "2",
+    "last_page": "6",
+    "citations": [
+      {
+        "type": "official",
+        "cite": "958 U.S. 5"
+      }
+    ],
+    "court": {
+      "name_abbreviation": "Same religious.",
+      "id": 6,
+      "name": "Size fish back degree."
+    },
+    "jurisdiction": {
+      "id": 2,
+      "name_long": "Massachusetts",
+      "name": "Mass."
+    },
+    "cites_to": [],
+    "analysis": {
+      "cardinality": 2,
+      "char_count": 14,
+      "ocr_confidence": 0,
+      "sha256": "8874c1d06c05904e12fef4e76fcdd0ce48b33013e2067d5ebba936f78b8c5d89",
+      "simhash": "1:0000000000000000",
+      "word_count": 2,
+      "random_id": 3120486931,
+      "random_bucket": 55827
+    },
+    "last_updated": "2023-12-04T18:17:29.088002+00:00",
+    "provenance": {
+      "date_added": "2023-12-04",
+      "source": "Harvard",
+      "batch": "2018"
+    },
+    "first_page_order": 4,
+    "last_page_order": 8
+  }
+]
diff --git a/capstone/test_data/cap_static/redacted/us/2/VolumeMetadata.json b/capstone/test_data/cap_static/redacted/us/2/VolumeMetadata.json
new file mode 100644
index 000000000..34bd2f2f0
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/2/VolumeMetadata.json
@@ -0,0 +1,28 @@
+{
+  "volume_number": "2",
+  "title": null,
+  "publisher": null,
+  "publication_year": null,
+  "start_year": null,
+  "end_year": null,
+  "series_volume_number": null,
+  "jurisdictions": [
+    {
+      "id": 2,
+      "name": "Mass.",
+      "name_long": "Massachusetts"
+    },
+    {
+      "id": 1,
+      "name": "U.S.",
+      "name_long": "United States"
+    }
+  ],
+  "id": "5012832128833",
+  "harvard_hollis_id": null,
+  "spine_start_year": null,
+  "spine_end_year": null,
+  "publication_city": null,
+  "second_part_of_id": null,
+  "nominative_reporter": null
+}
diff --git a/capstone/test_data/cap_static/redacted/us/2/cases/0001-01.json b/capstone/test_data/cap_static/redacted/us/2/cases/0001-01.json
new file mode 100644
index 000000000..f2556140b
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/2/cases/0001-01.json
@@ -0,0 +1,66 @@
+{
+  "id": 4,
+  "name": "First Foo3 versus First Bar3",
+  "name_abbreviation": "Foo3 v. Bar3",
+  "decision_date": "1903-01-01",
+  "docket_number": "",
+  "first_page": "1",
+  "last_page": "5",
+  "citations": [
+    {
+      "type": "official",
+      "cite": "447 U.S. 189"
+    }
+  ],
+  "court": {
+    "name_abbreviation": "Quickly walk.",
+    "id": 4,
+    "name": "Focus detail several position."
+  },
+  "jurisdiction": {
+    "id": 1,
+    "name_long": "United States",
+    "name": "U.S."
+  },
+  "cites_to": [
+    {
+      "cite": "524 U.S. 591",
+      "category": null,
+      "reporter": null,
+      "opinion_index": -1
+    }
+  ],
+  "analysis": {
+    "random_id": 3673096554,
+    "random_bucket": 362
+  },
+  "last_updated": "2023-12-04T18:17:29.088002+00:00",
+  "provenance": {
+    "date_added": "2023-12-04",
+    "source": "Harvard",
+    "batch": "2018"
+  },
+  "casebody": {
+    "judges": [
+      "Fearing, C.J., and Korsmo, J., concur."
+    ],
+    "parties": [
+      "In the Matter of the Marriage of Christy Lyle, Respondent, and Keith Lyle, Appellant."
+    ],
+    "opinions": [
+      {
+        "text": "Opinion text",
+        "type": "majority",
+        "author": "Pennell, J."
+      }
+    ],
+    "attorneys": [
+      "Matthew J. Dudley, for appellant.",
+      "Camerina I. Brokaw-Zorrozua (of Maxey Law Office PS), for respondent."
+    ],
+    "corrections": "",
+    "head_matter": "head matter"
+  },
+  "first_page_order": 3,
+  "last_page_order": 7
+}
diff --git a/capstone/test_data/cap_static/redacted/us/2/cases/0002-01.json b/capstone/test_data/cap_static/redacted/us/2/cases/0002-01.json
new file mode 100644
index 000000000..db6983ef4
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/2/cases/0002-01.json
@@ -0,0 +1,66 @@
+{
+  "id": 5,
+  "name": "First Foo4 versus First Bar4",
+  "name_abbreviation": "Foo4 v. Bar4",
+  "decision_date": "1904-01-01",
+  "docket_number": "",
+  "first_page": "2",
+  "last_page": "6",
+  "citations": [
+    {
+      "type": "official",
+      "cite": "872 U.S. 266"
+    }
+  ],
+  "court": {
+    "name_abbreviation": "Like area.",
+    "id": 5,
+    "name": "Commercial edge agency ground risk."
+  },
+  "jurisdiction": {
+    "id": 1,
+    "name_long": "United States",
+    "name": "U.S."
+  },
+  "cites_to": [
+    {
+      "cite": "596 U.S. 768",
+      "category": null,
+      "reporter": null,
+      "opinion_index": -1
+    }
+  ],
+  "analysis": {
+    "random_id": 2595981630,
+    "random_bucket": 35134
+  },
+  "last_updated": "2023-12-04T18:17:29.088002+00:00",
+  "provenance": {
+    "date_added": "2023-12-04",
+    "source": "Harvard",
+    "batch": "2018"
+  },
+  "casebody": {
+    "judges": [
+      "Fearing, C.J., and Korsmo, J., concur."
+    ],
+    "parties": [
+      "In the Matter of the Marriage of Christy Lyle, Respondent, and Keith Lyle, Appellant."
+    ],
+    "opinions": [
+      {
+        "text": "Opinion text",
+        "type": "majority",
+        "author": "Pennell, J."
+      }
+    ],
+    "attorneys": [
+      "Matthew J. Dudley, for appellant.",
+      "Camerina I. Brokaw-Zorrozua (of Maxey Law Office PS), for respondent."
+    ],
+    "corrections": "",
+    "head_matter": "head matter"
+  },
+  "first_page_order": 4,
+  "last_page_order": 8
+}
diff --git a/capstone/test_data/cap_static/redacted/us/2/cases/0002-02.json b/capstone/test_data/cap_static/redacted/us/2/cases/0002-02.json
new file mode 100644
index 000000000..007da6102
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/2/cases/0002-02.json
@@ -0,0 +1,58 @@
+{
+  "id": 6,
+  "name": "First Foo5 versus First Bar5",
+  "name_abbreviation": "Foo5 v. Bar5",
+  "decision_date": "1905-01-01",
+  "docket_number": "",
+  "first_page": "2",
+  "last_page": "6",
+  "citations": [
+    {
+      "type": "official",
+      "cite": "958 U.S. 5"
+    }
+  ],
+  "court": {
+    "name_abbreviation": "Same religious.",
+    "id": 6,
+    "name": "Size fish back degree."
+  },
+  "jurisdiction": {
+    "id": 2,
+    "name_long": "Massachusetts",
+    "name": "Mass."
+  },
+  "cites_to": [],
+  "analysis": {
+    "cardinality": 2,
+    "char_count": 14,
+    "ocr_confidence": 0,
+    "sha256": "8874c1d06c05904e12fef4e76fcdd0ce48b33013e2067d5ebba936f78b8c5d89",
+    "simhash": "1:0000000000000000",
+    "word_count": 2,
+    "random_id": 3120486931,
+    "random_bucket": 55827
+  },
+  "last_updated": "2023-12-04T18:17:29.088002+00:00",
+  "provenance": {
+    "date_added": "2023-12-04",
+    "source": "Harvard",
+    "batch": "2018"
+  },
+  "casebody": {
+    "judges": [],
+    "parties": [],
+    "opinions": [
+      {
+        "text": "not redacted",
+        "type": "majority",
+        "author": null
+      }
+    ],
+    "attorneys": [],
+    "corrections": "",
+    "head_matter": ""
+  },
+  "first_page_order": 4,
+  "last_page_order": 8
+}
diff --git a/capstone/test_data/cap_static/redacted/us/2/html/0001-01.html b/capstone/test_data/cap_static/redacted/us/2/html/0001-01.html
new file mode 100644
index 000000000..682bfc16f
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/2/html/0001-01.html
@@ -0,0 +1 @@
+<p>Case html 3</p>
\ No newline at end of file
diff --git a/capstone/test_data/cap_static/redacted/us/2/html/0002-01.html b/capstone/test_data/cap_static/redacted/us/2/html/0002-01.html
new file mode 100644
index 000000000..75d3446a8
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/2/html/0002-01.html
@@ -0,0 +1 @@
+<p>Case html 4</p>
\ No newline at end of file
diff --git a/capstone/test_data/cap_static/redacted/us/2/html/0002-02.html b/capstone/test_data/cap_static/redacted/us/2/html/0002-02.html
new file mode 100644
index 000000000..75cea3a52
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/2/html/0002-02.html
@@ -0,0 +1,6 @@
+<section class="casebody" data-case-id="00000005" data-firstpage="2" data-lastpage="6">
+  <section class="head-matter"></section>
+  <article class="opinion" data-type="majority">
+    <p id="b1-2" data-blocks='[["BL_1.2",5,[4,32,100,100]],["BL_1.3",5,[225,11,430,290]]]'>not redacted</p>
+  </article>
+</section>
diff --git a/capstone/test_data/cap_static/redacted/us/ReporterMetadata.json b/capstone/test_data/cap_static/redacted/us/ReporterMetadata.json
new file mode 100644
index 000000000..85516ff50
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/ReporterMetadata.json
@@ -0,0 +1,21 @@
+{
+  "id": 1,
+  "full_name": "United States Reports",
+  "short_name": "U.S.",
+  "start_year": 1900,
+  "end_year": 2000,
+  "jurisdictions": [
+    {
+      "id": 2,
+      "name": "Mass.",
+      "name_long": "Massachusetts"
+    },
+    {
+      "id": 1,
+      "name": "U.S.",
+      "name_long": "United States"
+    }
+  ],
+  "harvard_hollis_id": [],
+  "slug": "us"
+}
diff --git a/capstone/test_data/cap_static/redacted/us/VolumesMetadata.json b/capstone/test_data/cap_static/redacted/us/VolumesMetadata.json
new file mode 100644
index 000000000..1a24582d4
--- /dev/null
+++ b/capstone/test_data/cap_static/redacted/us/VolumesMetadata.json
@@ -0,0 +1,58 @@
+[
+  {
+    "volume_number": "1",
+    "title": null,
+    "publisher": null,
+    "publication_year": null,
+    "start_year": null,
+    "end_year": null,
+    "series_volume_number": null,
+    "jurisdictions": [
+      {
+        "id": 2,
+        "name": "Mass.",
+        "name_long": "Massachusetts"
+      },
+      {
+        "id": 1,
+        "name": "U.S.",
+        "name_long": "United States"
+      }
+    ],
+    "id": "4909170303750",
+    "harvard_hollis_id": null,
+    "spine_start_year": null,
+    "spine_end_year": null,
+    "publication_city": null,
+    "second_part_of_id": null,
+    "nominative_reporter": null
+  },
+  {
+    "volume_number": "2",
+    "title": null,
+    "publisher": null,
+    "publication_year": null,
+    "start_year": null,
+    "end_year": null,
+    "series_volume_number": null,
+    "jurisdictions": [
+      {
+        "id": 2,
+        "name": "Mass.",
+        "name_long": "Massachusetts"
+      },
+      {
+        "id": 1,
+        "name": "U.S.",
+        "name_long": "United States"
+      }
+    ],
+    "id": "5012832128833",
+    "harvard_hollis_id": null,
+    "spine_start_year": null,
+    "spine_end_year": null,
+    "publication_city": null,
+    "second_part_of_id": null,
+    "nominative_reporter": null
+  }
+]
diff --git a/capstone/test_data/cap_static/unredacted/JurisdictionsMetadata.json b/capstone/test_data/cap_static/unredacted/JurisdictionsMetadata.json
new file mode 100644
index 000000000..459e5a1ac
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/JurisdictionsMetadata.json
@@ -0,0 +1,44 @@
+[
+  {
+    "id": 2,
+    "slug": "mass",
+    "name": "Mass.",
+    "name_long": "Massachusetts",
+    "case_count": 2,
+    "volume_count": 2,
+    "reporter_count": 1,
+    "page_count": 10,
+    "reporters": [
+      {
+        "id": 1,
+        "full_name": "United States Reports",
+        "short_name": "U.S.",
+        "start_year": 1900,
+        "end_year": 2000,
+        "harvard_hollis_id": [],
+        "slug": "us"
+      }
+    ]
+  },
+  {
+    "id": 1,
+    "slug": "us",
+    "name": "U.S.",
+    "name_long": "United States",
+    "case_count": 4,
+    "volume_count": 2,
+    "reporter_count": 1,
+    "page_count": 20,
+    "reporters": [
+      {
+        "id": 1,
+        "full_name": "United States Reports",
+        "short_name": "U.S.",
+        "start_year": 1900,
+        "end_year": 2000,
+        "harvard_hollis_id": [],
+        "slug": "us"
+      }
+    ]
+  }
+]
diff --git a/capstone/test_data/cap_static/unredacted/ReportersMetadata.json b/capstone/test_data/cap_static/unredacted/ReportersMetadata.json
new file mode 100644
index 000000000..d166b62ca
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/ReportersMetadata.json
@@ -0,0 +1,23 @@
+[
+  {
+    "id": 1,
+    "full_name": "United States Reports",
+    "short_name": "U.S.",
+    "start_year": 1900,
+    "end_year": 2000,
+    "jurisdictions": [
+      {
+        "id": 2,
+        "name": "Mass.",
+        "name_long": "Massachusetts"
+      },
+      {
+        "id": 1,
+        "name": "U.S.",
+        "name_long": "United States"
+      }
+    ],
+    "harvard_hollis_id": [],
+    "slug": "us"
+  }
+]
diff --git a/capstone/test_data/cap_static/unredacted/VolumesMetadata.json b/capstone/test_data/cap_static/unredacted/VolumesMetadata.json
new file mode 100644
index 000000000..72c2be61a
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/VolumesMetadata.json
@@ -0,0 +1,60 @@
+[
+  [
+    {
+      "volume_number": "1",
+      "title": null,
+      "publisher": null,
+      "publication_year": null,
+      "start_year": null,
+      "end_year": null,
+      "series_volume_number": null,
+      "jurisdictions": [
+        {
+          "id": 2,
+          "name": "Mass.",
+          "name_long": "Massachusetts"
+        },
+        {
+          "id": 1,
+          "name": "U.S.",
+          "name_long": "United States"
+        }
+      ],
+      "id": "4909170303750",
+      "harvard_hollis_id": null,
+      "spine_start_year": null,
+      "spine_end_year": null,
+      "publication_city": null,
+      "second_part_of_id": null,
+      "nominative_reporter": null
+    },
+    {
+      "volume_number": "2",
+      "title": null,
+      "publisher": null,
+      "publication_year": null,
+      "start_year": null,
+      "end_year": null,
+      "series_volume_number": null,
+      "jurisdictions": [
+        {
+          "id": 2,
+          "name": "Mass.",
+          "name_long": "Massachusetts"
+        },
+        {
+          "id": 1,
+          "name": "U.S.",
+          "name_long": "United States"
+        }
+      ],
+      "id": "5012832128833",
+      "harvard_hollis_id": null,
+      "spine_start_year": null,
+      "spine_end_year": null,
+      "publication_city": null,
+      "second_part_of_id": null,
+      "nominative_reporter": null
+    }
+  ]
+]
diff --git a/capstone/test_data/cap_static/unredacted/us/1/CasesMetadata.json b/capstone/test_data/cap_static/unredacted/us/1/CasesMetadata.json
new file mode 100644
index 000000000..f5ef1c8ff
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/1/CasesMetadata.json
@@ -0,0 +1,134 @@
+[
+  {
+    "id": 1,
+    "name": "First Foo0 versus First Bar0",
+    "name_abbreviation": "Foo0 v. Bar0",
+    "decision_date": "1900-01-01",
+    "docket_number": "",
+    "first_page": "1",
+    "last_page": "5",
+    "citations": [
+      {
+        "type": "official",
+        "cite": "28 U.S. 347"
+      }
+    ],
+    "court": {
+      "name_abbreviation": "Sound spend.",
+      "id": 1,
+      "name": "Father worry common past recognize."
+    },
+    "jurisdiction": {
+      "id": 1,
+      "name_long": "United States",
+      "name": "U.S."
+    },
+    "cites_to": [],
+    "analysis": {
+      "cardinality": 6,
+      "char_count": 47,
+      "ocr_confidence": 1.0,
+      "sha256": "da95df9d6d5d506285c9a8f9010560fa57905f64b3e94748b8854d678e18f0cc",
+      "simhash": "1:6e45862a08eb1d4c",
+      "word_count": 11,
+      "random_id": 3210483407,
+      "random_bucket": 5839
+    },
+    "last_updated": "2023-12-04T18:17:29.088002+00:00",
+    "provenance": {
+      "date_added": "2023-12-04",
+      "source": "Harvard",
+      "batch": "2018"
+    },
+    "first_page_order": 3,
+    "last_page_order": 7
+  },
+  {
+    "id": 2,
+    "name": "First Foo1 versus First Bar1",
+    "name_abbreviation": "Foo1 v. Bar1",
+    "decision_date": "1901-01-01",
+    "docket_number": "",
+    "first_page": "2",
+    "last_page": "6",
+    "citations": [
+      {
+        "type": "official",
+        "cite": "257 U.S. 222"
+      }
+    ],
+    "court": {
+      "name_abbreviation": "Upon.",
+      "id": 2,
+      "name": "Opportunity cup speech."
+    },
+    "jurisdiction": {
+      "id": 1,
+      "name_long": "United States",
+      "name": "U.S."
+    },
+    "cites_to": [],
+    "analysis": {
+      "cardinality": 6,
+      "char_count": 47,
+      "ocr_confidence": 1.0,
+      "sha256": "da95df9d6d5d506285c9a8f9010560fa57905f64b3e94748b8854d678e18f0cc",
+      "simhash": "1:6e45862a08eb1d4c",
+      "word_count": 11,
+      "random_id": 1950914210,
+      "random_bucket": 38562
+    },
+    "last_updated": "2023-12-04T18:17:29.088002+00:00",
+    "provenance": {
+      "date_added": "2023-12-04",
+      "source": "Harvard",
+      "batch": "2018"
+    },
+    "first_page_order": 4,
+    "last_page_order": 8
+  },
+  {
+    "id": 3,
+    "name": "First Foo2 versus First Bar2",
+    "name_abbreviation": "Foo2 v. Bar2",
+    "decision_date": "1902-01-01",
+    "docket_number": "",
+    "first_page": "2",
+    "last_page": "6",
+    "citations": [
+      {
+        "type": "official",
+        "cite": "311 U.S. 951"
+      }
+    ],
+    "court": {
+      "name_abbreviation": "Rule six your.",
+      "id": 3,
+      "name": "Little perhaps look many."
+    },
+    "jurisdiction": {
+      "id": 2,
+      "name_long": "Massachusetts",
+      "name": "Mass."
+    },
+    "cites_to": [],
+    "analysis": {
+      "cardinality": 6,
+      "char_count": 39,
+      "ocr_confidence": 0,
+      "sha256": "e0819f285636dcbd644be2d72c1ef1e0e616ca51d3445280adbf00eab401e7c5",
+      "simhash": "1:03208952f875022c",
+      "word_count": 8,
+      "random_id": 2863198571,
+      "random_bucket": 61803
+    },
+    "last_updated": "2023-12-04T18:17:29.088002+00:00",
+    "provenance": {
+      "date_added": "2023-12-04",
+      "source": "Harvard",
+      "batch": "2018"
+    },
+    "first_page_order": 4,
+    "last_page_order": 8
+  }
+]
diff --git a/capstone/test_data/cap_static/unredacted/us/1/VolumeMetadata.json b/capstone/test_data/cap_static/unredacted/us/1/VolumeMetadata.json
new file mode 100644
index 000000000..2f4470a42
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/1/VolumeMetadata.json
@@ -0,0 +1,28 @@
+{
+  "volume_number": "1",
+  "title": null,
+  "publisher": null,
+  "publication_year": null,
+  "start_year": null,
+  "end_year": null,
+  "series_volume_number": null,
+  "jurisdictions": [
+    {
+      "id": 2,
+      "name": "Mass.",
+      "name_long": "Massachusetts"
+    },
+    {
+      "id": 1,
+      "name": "U.S.",
+      "name_long": "United States"
+    }
+  ],
+  "id": "4909170303750",
+  "harvard_hollis_id": null,
+  "spine_start_year": null,
+  "spine_end_year": null,
+  "publication_city": null,
+  "second_part_of_id": null,
+  "nominative_reporter": null
+}
diff --git a/capstone/test_data/cap_static/unredacted/us/1/cases/0001-01.json b/capstone/test_data/cap_static/unredacted/us/1/cases/0001-01.json
new file mode 100644
index 000000000..151f59be7
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/1/cases/0001-01.json
@@ -0,0 +1,60 @@
+{
+  "id": 1,
+  "name": "First Foo0 versus First Bar0",
+  "name_abbreviation": "Foo0 v. Bar0",
+  "decision_date": "1900-01-01",
+  "docket_number": "",
+  "first_page": "1",
+  "last_page": "5",
+  "citations": [
+    {
+      "type": "official",
+      "cite": "28 U.S. 347"
+    }
+  ],
+  "court": {
+    "name_abbreviation": "Sound spend.",
+    "id": 1,
+    "name": "Father worry common past recognize."
+  },
+  "jurisdiction": {
+    "id": 1,
+    "name_long": "United States",
+    "name": "U.S."
+  },
+  "cites_to": [],
+  "analysis": {
+    "cardinality": 6,
+    "char_count": 47,
+    "ocr_confidence": 1.0,
+    "sha256": "da95df9d6d5d506285c9a8f9010560fa57905f64b3e94748b8854d678e18f0cc",
+    "simhash": "1:6e45862a08eb1d4c",
+    "word_count": 11,
+    "random_id": 3210483407,
+    "random_bucket": 5839
+  },
+  "last_updated": "2023-12-04T18:17:29.088002+00:00",
+  "provenance": {
+    "date_added": "2023-12-04",
+    "source": "Harvard",
+    "batch": "2018"
+  },
+  "casebody": {
+    "judges": [],
+    "parties": [
+      "Case text 0"
+    ],
+    "opinions": [
+      {
+        "text": "Case text 1Case text 2\nCase text 3",
+        "type": "majority",
+        "author": null
+      }
+    ],
+    "attorneys": [],
+    "corrections": "",
+    "head_matter": "Case text 0"
+  },
+  "first_page_order": 3,
+  "last_page_order": 7
+}
diff --git a/capstone/test_data/cap_static/unredacted/us/1/cases/0002-01.json b/capstone/test_data/cap_static/unredacted/us/1/cases/0002-01.json
new file mode 100644
index 000000000..e6350e473
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/1/cases/0002-01.json
@@ -0,0 +1,60 @@
+{
+  "id": 2,
+  "name": "First Foo1 versus First Bar1",
+  "name_abbreviation": "Foo1 v. Bar1",
+  "decision_date": "1901-01-01",
+  "docket_number": "",
+  "first_page": "2",
+  "last_page": "6",
+  "citations": [
+    {
+      "type": "official",
+      "cite": "257 U.S. 222"
+    }
+  ],
+  "court": {
+    "name_abbreviation": "Upon.",
+    "id": 2,
+    "name": "Opportunity cup speech."
+  },
+  "jurisdiction": {
+    "id": 1,
+    "name_long": "United States",
+    "name": "U.S."
+  },
+  "cites_to": [],
+  "analysis": {
+    "cardinality": 6,
+    "char_count": 47,
+    "ocr_confidence": 1.0,
+    "sha256": "da95df9d6d5d506285c9a8f9010560fa57905f64b3e94748b8854d678e18f0cc",
+    "simhash": "1:6e45862a08eb1d4c",
+    "word_count": 11,
+    "random_id": 1950914210,
+    "random_bucket": 38562
+  },
+  "last_updated": "2023-12-04T18:17:29.088002+00:00",
+  "provenance": {
+    "date_added": "2023-12-04",
+    "source": "Harvard",
+    "batch": "2018"
+  },
+  "casebody": {
+    "judges": [],
+    "parties": [
+      "Case text 0"
+    ],
+    "opinions": [
+      {
+        "text": "Case text 1Case text 2\nCase text 3",
+        "type": "majority",
+        "author": null
+      }
+    ],
+    "attorneys": [],
+    "corrections": "",
+    "head_matter": "Case text 0"
+  },
+  "first_page_order": 4,
+  "last_page_order": 8
+}
diff --git a/capstone/test_data/cap_static/unredacted/us/1/cases/0002-02.json b/capstone/test_data/cap_static/unredacted/us/1/cases/0002-02.json
new file mode 100644
index 000000000..23937392e
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/1/cases/0002-02.json
@@ -0,0 +1,60 @@
+{
+  "id": 3,
+  "name": "First Foo2 versus First Bar2",
+  "name_abbreviation": "Foo2 v. Bar2",
+  "decision_date": "1902-01-01",
+  "docket_number": "",
+  "first_page": "2",
+  "last_page": "6",
+  "citations": [
+    {
+      "type": "official",
+      "cite": "311 U.S. 951"
+    }
+  ],
+  "court": {
+    "name_abbreviation": "Rule six your.",
+    "id": 3,
+    "name": "Little perhaps look many."
+  },
+  "jurisdiction": {
+    "id": 2,
+    "name_long": "Massachusetts",
+    "name": "Mass."
+  },
+  "cites_to": [],
+  "analysis": {
+    "cardinality": 6,
+    "char_count": 39,
+    "ocr_confidence": 0,
+    "sha256": "e0819f285636dcbd644be2d72c1ef1e0e616ca51d3445280adbf00eab401e7c5",
+    "simhash": "1:03208952f875022c",
+    "word_count": 8,
+    "random_id": 2863198571,
+    "random_bucket": 61803
+  },
+  "last_updated": "2023-12-04T18:17:29.088002+00:00",
+  "provenance": {
+    "date_added": "2023-12-04",
+    "source": "Harvard",
+    "batch": "2018"
+  },
+  "casebody": {
+    "judges": [],
+    "parties": [
+      "Text 1"
+    ],
+    "opinions": [
+      {
+        "text": "Text 2Text 3not redacted\nText 4",
+        "type": "majority",
+        "author": null
+      }
+    ],
+    "attorneys": [],
+    "corrections": "",
+    "head_matter": "Text 1"
+  },
+  "first_page_order": 4,
+  "last_page_order": 8
+}
diff --git a/capstone/test_data/cap_static/unredacted/us/1/html/0001-01.html b/capstone/test_data/cap_static/unredacted/us/1/html/0001-01.html
new file mode 100644
index 000000000..46b815f9c
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/1/html/0001-01.html
@@ -0,0 +1,12 @@
+<section class="casebody" data-case-id="00000000" data-firstpage="1" data-lastpage="5">
+  <section class="head-matter">
+    <h4 class="parties" id="b81-4" data-blocks='[["BL_81.3",0,[226,1320,752,926]]]'>Case text 0</h4>
+  </section>
+  <article class="opinion" data-type="majority">
+    <p id="b83-6" data-blocks='[["BL_83.6",0,[226,1320,752,926]],["BL_83.7",0,[226,1320,752,926]]]'>Case text 1Case text 2</p>
+    <aside data-label="1" class="footnote" id="footnote_1_1">
+      <a href="#ref_footnote_1_1">1</a>
+      <p id="b83-11" data-blocks='[["BL_83.16",0,[226,1320,752,926]]]'>Case text 3</p>
+    </aside>
+  </article>
+</section>
diff --git a/capstone/test_data/cap_static/unredacted/us/1/html/0002-01.html b/capstone/test_data/cap_static/unredacted/us/1/html/0002-01.html
new file mode 100644
index 000000000..bbefaa490
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/1/html/0002-01.html
@@ -0,0 +1,12 @@
+<section class="casebody" data-case-id="00000001" data-firstpage="2" data-lastpage="6">
+  <section class="head-matter">
+    <h4 class="parties" id="b81-4" data-blocks='[["BL_81.3",0,[226,1320,752,926]]]'>Case text 0</h4>
+  </section>
+  <article class="opinion" data-type="majority">
+    <p id="b83-6" data-blocks='[["BL_83.6",0,[226,1320,752,926]],["BL_83.7",0,[226,1320,752,926]]]'>Case text 1Case text 2</p>
+    <aside data-label="1" class="footnote" id="footnote_1_1">
+      <a href="#ref_footnote_1_1">1</a>
+      <p id="b83-11" data-blocks='[["BL_83.16",0,[226,1320,752,926]]]'>Case text 3</p>
+    </aside>
+  </article>
+</section>
diff --git a/capstone/test_data/cap_static/unredacted/us/1/html/0002-02.html b/capstone/test_data/cap_static/unredacted/us/1/html/0002-02.html
new file mode 100644
index 000000000..9d537bcb2
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/1/html/0002-02.html
@@ -0,0 +1,15 @@
+<section class="casebody" data-case-id="00000002" data-firstpage="2" data-lastpage="6">
+  <section class="head-matter">
+    <h4 class="parties" id="b1-1" data-blocks='[["BL_1.1",2,[25,11,300,490]]]'>Text 1</h4>
+  </section>
+  <article class="opinion" data-type="majority">
+    <p id="b1-2" data-blocks='[["BL_1.2",2,[4,32,100,100]],["BL_1.3",2,[225,11,430,290]]]'>Text 2Text 3not redacted</p>
+    <p class="image" id="b1-3" data-blocks='[["BL_1.4",2,[0,0,100,100]]]'>
+      <img src="data:image%20data" class="image" width="100" height="100">
+    </p>
+    <aside data-label="1" class="footnote" id="footnote_1_1">
+      <a href="#ref_footnote_1_1">1</a>
+      <p id="b1-4" data-blocks='[["BL_1.5",2,[190,312,330,490]]]'>Text 4</p>
+    </aside>
+  </article>
+</section>
diff --git a/capstone/test_data/cap_static/unredacted/us/2/CasesMetadata.json b/capstone/test_data/cap_static/unredacted/us/2/CasesMetadata.json
new file mode 100644
index 000000000..29ed827d1
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/2/CasesMetadata.json
@@ -0,0 +1,134 @@
+[
+  {
+    "id": 4,
+    "name": "First Foo3 versus First Bar3",
+    "name_abbreviation": "Foo3 v. Bar3",
+    "decision_date": "1903-01-01",
+    "docket_number": "",
+    "first_page": "1",
+    "last_page": "5",
+    "citations": [
+      {
+        "type": "official",
+        "cite": "447 U.S. 189"
+      }
+    ],
+    "court": {
+      "name_abbreviation": "Quickly walk.",
+      "id": 4,
+      "name": "Focus detail several position."
+    },
+    "jurisdiction": {
+      "id": 1,
+      "name_long": "United States",
+      "name": "U.S."
+    },
+    "cites_to": [],
+    "analysis": {
+      "cardinality": 6,
+      "char_count": 47,
+      "ocr_confidence": 1.0,
+      "sha256": "da95df9d6d5d506285c9a8f9010560fa57905f64b3e94748b8854d678e18f0cc",
+      "simhash": "1:6e45862a08eb1d4c",
+      "word_count": 11,
+      "random_id": 3673096554,
+      "random_bucket": 362
+    },
+    "last_updated": "2023-12-04T18:17:29.088002+00:00",
+    "provenance": {
+      "date_added": "2023-12-04",
+      "source": "Harvard",
+      "batch": "2018"
+    },
+    "first_page_order": 3,
+    "last_page_order": 7
+  },
+  {
+    "id": 5,
+    "name": "First Foo4 versus First Bar4",
+    "name_abbreviation": "Foo4 v. Bar4",
+    "decision_date": "1904-01-01",
+    "docket_number": "",
+    "first_page": "2",
+    "last_page": "6",
+    "citations": [
+      {
+        "type": "official",
+        "cite": "872 U.S. 266"
+      }
+    ],
+    "court": {
+      "name_abbreviation": "Like area.",
+      "id": 5,
+      "name": "Commercial edge agency ground risk."
+    },
+    "jurisdiction": {
+      "id": 1,
+      "name_long": "United States",
+      "name": "U.S."
+    },
+    "cites_to": [],
+    "analysis": {
+      "cardinality": 6,
+      "char_count": 47,
+      "ocr_confidence": 1.0,
+      "sha256": "da95df9d6d5d506285c9a8f9010560fa57905f64b3e94748b8854d678e18f0cc",
+      "simhash": "1:6e45862a08eb1d4c",
+      "word_count": 11,
+      "random_id": 2595981630,
+      "random_bucket": 35134
+    },
+    "last_updated": "2023-12-04T18:17:29.088002+00:00",
+    "provenance": {
+      "date_added": "2023-12-04",
+      "source": "Harvard",
+      "batch": "2018"
+    },
+    "first_page_order": 4,
+    "last_page_order": 8
+  },
+  {
+    "id": 6,
+    "name": "First Foo5 versus First Bar5",
+    "name_abbreviation": "Foo5 v. Bar5",
+    "decision_date": "1905-01-01",
+    "docket_number": "",
+    "first_page": "2",
+    "last_page": "6",
+    "citations": [
+      {
+        "type": "official",
+        "cite": "958 U.S. 5"
+      }
+    ],
+    "court": {
+      "name_abbreviation": "Same religious.",
+      "id": 6,
+      "name": "Size fish back degree."
+    },
+    "jurisdiction": {
+      "id": 2,
+      "name_long": "Massachusetts",
+      "name": "Mass."
+    },
+    "cites_to": [],
+    "analysis": {
+      "cardinality": 6,
+      "char_count": 39,
+      "ocr_confidence": 0,
+      "sha256": "e0819f285636dcbd644be2d72c1ef1e0e616ca51d3445280adbf00eab401e7c5",
+      "simhash": "1:03208952f875022c",
+      "word_count": 8,
+      "random_id": 3120486931,
+      "random_bucket": 55827
+    },
+    "last_updated": "2023-12-04T18:17:29.088002+00:00",
+    "provenance": {
+      "date_added": "2023-12-04",
+      "source": "Harvard",
+      "batch": "2018"
+    },
+    "first_page_order": 4,
+    "last_page_order": 8
+  }
+]
diff --git a/capstone/test_data/cap_static/unredacted/us/2/VolumeMetadata.json b/capstone/test_data/cap_static/unredacted/us/2/VolumeMetadata.json
new file mode 100644
index 000000000..34bd2f2f0
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/2/VolumeMetadata.json
@@ -0,0 +1,28 @@
+{
+  "volume_number": "2",
+  "title": null,
+  "publisher": null,
+  "publication_year": null,
+  "start_year": null,
+  "end_year": null,
+  "series_volume_number": null,
+  "jurisdictions": [
+    {
+      "id": 2,
+      "name": "Mass.",
+      "name_long": "Massachusetts"
+    },
+    {
+      "id": 1,
+      "name": "U.S.",
+      "name_long": "United States"
+    }
+  ],
+  "id": "5012832128833",
+  "harvard_hollis_id": null,
+  "spine_start_year": null,
+  "spine_end_year": null,
+  "publication_city": null,
+  "second_part_of_id": null,
+  "nominative_reporter": null
+}
diff --git a/capstone/test_data/cap_static/unredacted/us/2/cases/0001-01.json b/capstone/test_data/cap_static/unredacted/us/2/cases/0001-01.json
new file mode 100644
index 000000000..847039168
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/2/cases/0001-01.json
@@ -0,0 +1,60 @@
+{
+  "id": 4,
+  "name": "First Foo3 versus First Bar3",
+  "name_abbreviation": "Foo3 v. Bar3",
+  "decision_date": "1903-01-01",
+  "docket_number": "",
+  "first_page": "1",
+  "last_page": "5",
+  "citations": [
+    {
+      "type": "official",
+      "cite": "447 U.S. 189"
+    }
+  ],
+  "court": {
+    "name_abbreviation": "Quickly walk.",
+    "id": 4,
+    "name": "Focus detail several position."
+  },
+  "jurisdiction": {
+    "id": 1,
+    "name_long": "United States",
+    "name": "U.S."
+  },
+  "cites_to": [],
+  "analysis": {
+    "cardinality": 6,
+    "char_count": 47,
+    "ocr_confidence": 1.0,
+    "sha256": "da95df9d6d5d506285c9a8f9010560fa57905f64b3e94748b8854d678e18f0cc",
+    "simhash": "1:6e45862a08eb1d4c",
+    "word_count": 11,
+    "random_id": 3673096554,
+    "random_bucket": 362
+  },
+  "last_updated": "2023-12-04T18:17:29.088002+00:00",
+  "provenance": {
+    "date_added": "2023-12-04",
+    "source": "Harvard",
+    "batch": "2018"
+  },
+  "casebody": {
+    "judges": [],
+    "parties": [
+      "Case text 0"
+    ],
+    "opinions": [
+      {
+        "text": "Case text 1Case text 2\nCase text 3",
+        "type": "majority",
+        "author": null
+      }
+    ],
+    "attorneys": [],
+    "corrections": "",
+    "head_matter": "Case text 0"
+  },
+  "first_page_order": 3,
+  "last_page_order": 7
+}
diff --git a/capstone/test_data/cap_static/unredacted/us/2/cases/0002-01.json b/capstone/test_data/cap_static/unredacted/us/2/cases/0002-01.json
new file mode 100644
index 000000000..5ec8f1fc9
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/2/cases/0002-01.json
@@ -0,0 +1,60 @@
+{
+  "id": 5,
+  "name": "First Foo4 versus First Bar4",
+  "name_abbreviation": "Foo4 v. Bar4",
+  "decision_date": "1904-01-01",
+  "docket_number": "",
+  "first_page": "2",
+  "last_page": "6",
+  "citations": [
+    {
+      "type": "official",
+      "cite": "872 U.S. 266"
+    }
+  ],
+  "court": {
+    "name_abbreviation": "Like area.",
+    "id": 5,
+    "name": "Commercial edge agency ground risk."
+  },
+  "jurisdiction": {
+    "id": 1,
+    "name_long": "United States",
+    "name": "U.S."
+  },
+  "cites_to": [],
+  "analysis": {
+    "cardinality": 6,
+    "char_count": 47,
+    "ocr_confidence": 1.0,
+    "sha256": "da95df9d6d5d506285c9a8f9010560fa57905f64b3e94748b8854d678e18f0cc",
+    "simhash": "1:6e45862a08eb1d4c",
+    "word_count": 11,
+    "random_id": 2595981630,
+    "random_bucket": 35134
+  },
+  "last_updated": "2023-12-04T18:17:29.088002+00:00",
+  "provenance": {
+    "date_added": "2023-12-04",
+    "source": "Harvard",
+    "batch": "2018"
+  },
+  "casebody": {
+    "judges": [],
+    "parties": [
+      "Case text 0"
+    ],
+    "opinions": [
+      {
+        "text": "Case text 1Case text 2\nCase text 3",
+        "type": "majority",
+        "author": null
+      }
+    ],
+    "attorneys": [],
+    "corrections": "",
+    "head_matter": "Case text 0"
+  },
+  "first_page_order": 4,
+  "last_page_order": 8
+}
diff --git a/capstone/test_data/cap_static/unredacted/us/2/cases/0002-02.json b/capstone/test_data/cap_static/unredacted/us/2/cases/0002-02.json
new file mode 100644
index 000000000..68917d4e2
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/2/cases/0002-02.json
@@ -0,0 +1,60 @@
+{
+  "id": 6,
+  "name": "First Foo5 versus First Bar5",
+  "name_abbreviation": "Foo5 v. Bar5",
+  "decision_date": "1905-01-01",
+  "docket_number": "",
+  "first_page": "2",
+  "last_page": "6",
+  "citations": [
+    {
+      "type": "official",
+      "cite": "958 U.S. 5"
+    }
+  ],
+  "court": {
+    "name_abbreviation": "Same religious.",
+    "id": 6,
+    "name": "Size fish back degree."
+  },
+  "jurisdiction": {
+    "id": 2,
+    "name_long": "Massachusetts",
+    "name": "Mass."
+  },
+  "cites_to": [],
+  "analysis": {
+    "cardinality": 6,
+    "char_count": 39,
+    "ocr_confidence": 0,
+    "sha256": "e0819f285636dcbd644be2d72c1ef1e0e616ca51d3445280adbf00eab401e7c5",
+    "simhash": "1:03208952f875022c",
+    "word_count": 8,
+    "random_id": 3120486931,
+    "random_bucket": 55827
+  },
+  "last_updated": "2023-12-04T18:17:29.088002+00:00",
+  "provenance": {
+    "date_added": "2023-12-04",
+    "source": "Harvard",
+    "batch": "2018"
+  },
+  "casebody": {
+    "judges": [],
+    "parties": [
+      "Text 1"
+    ],
+    "opinions": [
+      {
+        "text": "Text 2Text 3not redacted\nText 4",
+        "type": "majority",
+        "author": null
+      }
+    ],
+    "attorneys": [],
+    "corrections": "",
+    "head_matter": "Text 1"
+  },
+  "first_page_order": 4,
+  "last_page_order": 8
+}
diff --git a/capstone/test_data/cap_static/unredacted/us/2/html/0001-01.html b/capstone/test_data/cap_static/unredacted/us/2/html/0001-01.html
new file mode 100644
index 000000000..0449b9be6
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/2/html/0001-01.html
@@ -0,0 +1,12 @@
+<section class="casebody" data-case-id="00000003" data-firstpage="1" data-lastpage="5">
+  <section class="head-matter">
+    <h4 class="parties" id="b81-4" data-blocks='[["BL_81.3",3,[226,1320,752,926]]]'>Case text 0</h4>
+  </section>
+  <article class="opinion" data-type="majority">
+    <p id="b83-6" data-blocks='[["BL_83.6",3,[226,1320,752,926]],["BL_83.7",3,[226,1320,752,926]]]'>Case text 1Case text 2</p>
+    <aside data-label="1" class="footnote" id="footnote_1_1">
+      <a href="#ref_footnote_1_1">1</a>
+      <p id="b83-11" data-blocks='[["BL_83.16",3,[226,1320,752,926]]]'>Case text 3</p>
+    </aside>
+  </article>
+</section>
diff --git a/capstone/test_data/cap_static/unredacted/us/2/html/0002-01.html b/capstone/test_data/cap_static/unredacted/us/2/html/0002-01.html
new file mode 100644
index 000000000..edcdd9fac
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/2/html/0002-01.html
@@ -0,0 +1,12 @@
+<section class="casebody" data-case-id="00000004" data-firstpage="2" data-lastpage="6">
+  <section class="head-matter">
+    <h4 class="parties" id="b81-4" data-blocks='[["BL_81.3",3,[226,1320,752,926]]]'>Case text 0</h4>
+  </section>
+  <article class="opinion" data-type="majority">
+    <p id="b83-6" data-blocks='[["BL_83.6",3,[226,1320,752,926]],["BL_83.7",3,[226,1320,752,926]]]'>Case text 1Case text 2</p>
+    <aside data-label="1" class="footnote" id="footnote_1_1">
+      <a href="#ref_footnote_1_1">1</a>
+      <p id="b83-11" data-blocks='[["BL_83.16",3,[226,1320,752,926]]]'>Case text 3</p>
+    </aside>
+  </article>
+</section>
diff --git a/capstone/test_data/cap_static/unredacted/us/2/html/0002-02.html b/capstone/test_data/cap_static/unredacted/us/2/html/0002-02.html
new file mode 100644
index 000000000..accac1425
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/2/html/0002-02.html
@@ -0,0 +1,15 @@
+<section class="casebody" data-case-id="00000005" data-firstpage="2" data-lastpage="6">
+  <section class="head-matter">
+    <h4 class="parties" id="b1-1" data-blocks='[["BL_1.1",5,[25,11,300,490]]]'>Text 1</h4>
+  </section>
+  <article class="opinion" data-type="majority">
+    <p id="b1-2" data-blocks='[["BL_1.2",5,[4,32,100,100]],["BL_1.3",5,[225,11,430,290]]]'>Text 2Text 3not redacted</p>
+    <p class="image" id="b1-3" data-blocks='[["BL_1.4",5,[0,0,100,100]]]'>
+      <img src="data:image%20data" class="image" width="100" height="100">
+    </p>
+    <aside data-label="1" class="footnote" id="footnote_1_1">
+      <a href="#ref_footnote_1_1">1</a>
+      <p id="b1-4" data-blocks='[["BL_1.5",5,[190,312,330,490]]]'>Text 4</p>
+    </aside>
+  </article>
+</section>
diff --git a/capstone/test_data/cap_static/unredacted/us/ReporterMetadata.json b/capstone/test_data/cap_static/unredacted/us/ReporterMetadata.json
new file mode 100644
index 000000000..85516ff50
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/ReporterMetadata.json
@@ -0,0 +1,21 @@
+{
+  "id": 1,
+  "full_name": "United States Reports",
+  "short_name": "U.S.",
+  "start_year": 1900,
+  "end_year": 2000,
+  "jurisdictions": [
+    {
+      "id": 2,
+      "name": "Mass.",
+      "name_long": "Massachusetts"
+    },
+    {
+      "id": 1,
+      "name": "U.S.",
+      "name_long": "United States"
+    }
+  ],
+  "harvard_hollis_id": [],
+  "slug": "us"
+}
diff --git a/capstone/test_data/cap_static/unredacted/us/VolumesMetadata.json b/capstone/test_data/cap_static/unredacted/us/VolumesMetadata.json
new file mode 100644
index 000000000..1a24582d4
--- /dev/null
+++ b/capstone/test_data/cap_static/unredacted/us/VolumesMetadata.json
@@ -0,0 +1,58 @@
+[
+  {
+    "volume_number": "1",
+    "title": null,
+    "publisher": null,
+    "publication_year": null,
+    "start_year": null,
+    "end_year": null,
+    "series_volume_number": null,
+    "jurisdictions": [
+      {
+        "id": 2,
+        "name": "Mass.",
+        "name_long": "Massachusetts"
+      },
+      {
+        "id": 1,
+        "name": "U.S.",
+        "name_long": "United States"
+      }
+    ],
+    "id": "4909170303750",
+    "harvard_hollis_id": null,
+    "spine_start_year": null,
+    "spine_end_year": null,
+    "publication_city": null,
+    "second_part_of_id": null,
+    "nominative_reporter": null
+  },
+  {
+    "volume_number": "2",
+    "title": null,
+    "publisher": null,
+    "publication_year": null,
+    "start_year": null,
+    "end_year": null,
+    "series_volume_number": null,
+    "jurisdictions": [
+      {
+        "id": 2,
+        "name": "Mass.",
+        "name_long": "Massachusetts"
+      },
+      {
+        "id": 1,
+        "name": "U.S.",
+        "name_long": "United States"
+      }
+    ],
+    "id": "5012832128833",
+    "harvard_hollis_id": null,
+    "spine_start_year": null,
+    "spine_end_year": null,
+    "publication_city": null,
+    "second_part_of_id": null,
+    "nominative_reporter": null
+  }
+]
diff --git a/capstone/test_data/test_fixtures/fixtures.py b/capstone/test_data/test_fixtures/fixtures.py
index 9ee4a6954..7b7f37805 100644
--- a/capstone/test_data/test_fixtures/fixtures.py
+++ b/capstone/test_data/test_fixtures/fixtures.py
@@ -33,7 +33,7 @@
 ### Pytest setup ###
 
 def pytest_addoption(parser):
-    parser.addoption("--recreate_fastcase_files", action="store_true", default=False, help="Recreate files in test_data/fastcase rather than testing existing files")
+    parser.addoption("--recreate_files", action="store_true", default=False, help="Recreate files in test_data/ rather than testing existing files")
 
 
 ### Database setup ###
@@ -410,3 +410,101 @@ def urls(live_server):
 @pytest.fixture
 def map_data():
     management.call_command('loaddata', ('jurisdiction', 'reporter', 'snippet'), database='capdb')
+
+
+@pytest.fixture
+def redacted_case_factory(case_factory):
+    def factory(**kwargs):
+        # set up a redacted case
+        case = case_factory(volume__redacted=True, volume__pdf_file="redacted_volume.pdf", **kwargs)
+        structure = case.structure
+        page = structure.pages.first()
+        structure.opinions = [
+            # redacted paragraph
+            {
+                "type": "head",
+                "paragraphs": [
+                    {
+                        "class": "parties",
+                        "block_ids": ["BL_1.1"],
+                        "id": "b1-1",
+                        "redacted": True,
+                    }
+                ],
+            },
+            {
+                "type": "majority",
+                "paragraphs": [
+                    # redacted content blocks
+                    {
+                        "class": "p",
+                        "block_ids": ["BL_1.2", "BL_1.3"],
+                        "id": "b1-2",
+                    },
+                    # redacted image block
+                    {
+                        "class": "image",
+                        "block_ids": ["BL_1.4"],
+                        "id": "b1-3",
+                    },
+                ],
+                # redacted footnote
+                "footnotes": [
+                    {
+                        # redacted footnote paragraph
+                        "paragraphs": [
+                            {
+                                "class": "p",
+                                "block_ids": ["BL_1.5"],
+                                "id": "b1-4",
+                            }
+                        ],
+                        "label": "1",
+                        "id": "footnote_1_1",
+                        "redacted": True,
+                    }
+                ],
+            },
+        ]
+        structure.save()
+        page.blocks = [
+            {
+                "id": "BL_1.1",
+                "class": "p",
+                "tokens": ["Text 1"],
+                "rect": [25, 11, 300, 490],
+            },
+            {
+                "id": "BL_1.2",
+                "class": "p",
+                "tokens": ["Text 2"],
+                "redacted": True,
+                "rect": [4, 32, 100, 100],
+            },
+            {
+                "id": "BL_1.3",
+                "class": "p",
+                "tokens": [["redact"], "Text 3", ["/redact"], "not redacted"],
+                "rect": [225, 11, 430, 290],
+            },
+            {
+                "id": "BL_1.4",
+                "format": "image",
+                "redacted": True,
+                "class": "image",
+                "data": "image data",
+                "rect": [0, 0, 100, 100],
+            },
+            {
+                "id": "BL_1.5",
+                "class": "p",
+                "tokens": ["Text 4"],
+                "rect": [190, 312, 330, 490],
+            },
+        ]
+        page.encrypt()
+        page.save()
+        case.sync_case_body_cache()
+        case.refresh_from_db()
+        return case
+    return factory
diff --git a/capstone/test_data/test_fixtures/helpers.py b/capstone/test_data/test_fixtures/helpers.py
index d9d1327ff..0ef0448e9 100644
--- a/capstone/test_data/test_fixtures/helpers.py
+++ b/capstone/test_data/test_fixtures/helpers.py
@@ -1,5 +1,6 @@
 import difflib
 import hashlib
+import os
 from pathlib import Path
 
 from scripts.helpers import parse_xml, parse_html
@@ -114,3 +115,24 @@ def sort_nested_dict(d):
     if isinstance(d, (list, tuple)):
         return [sort_nested_dict(v) for v in d]
     return d
+
+
+def current_test_name():
+    return os.environ.get('PYTEST_CURRENT_TEST').split(':')[-1].split(' ')[0]
+
+
+def check_path(pytestconfig, new_contents, saved_path):
+    """
+    Either report a diff between new_contents and saved_path, or update saved_path to match new_contents, depending on pytest --recreate_files.
+    """
+    if isinstance(new_contents, Path):
+        new_contents = new_contents.read_text()
+    old_contents = saved_path.read_text() if saved_path.exists() else ''
+    if new_contents != old_contents:
+        if pytestconfig.getoption('recreate_files'):
+            saved_path.parent.mkdir(parents=True, exist_ok=True)
+            saved_path.write_text(new_contents)
+        elif old_contents:
+            assert new_contents == old_contents, f"File {saved_path} has changed. Run pytest -k {current_test_name()} --recreate_files to update."
+        else:
+            assert False, f"File {saved_path} does not exist. Run pytest -k {current_test_name()} --recreate_files to update."