diff --git a/.devcontainer/Dockerfile b/.devcontainer/Dockerfile
index 7ef8f731f..1401b3194 100644
--- a/.devcontainer/Dockerfile
+++ b/.devcontainer/Dockerfile
@@ -8,3 +8,9 @@ ENV PYTHONUNBUFFERED 1
 RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
     && apt-get -y install --no-install-recommends postgresql-client ruby-full
 
+COPY ./.devcontainer/post-create-command.sh /scripts/
+COPY ./requirements.txt requirements.txt
+COPY ./Gemfile Gemfile
+COPY ./Gemfile.lock Gemfile.lock
+RUN bash /scripts/post-create-command.sh
+
diff --git a/.devcontainer/README b/.devcontainer/README
index 3a1c348ce..5e9685b2c 100644
--- a/.devcontainer/README
+++ b/.devcontainer/README
@@ -2,4 +2,3 @@
 
 The dev container can be used to work on the project in a consistent environment independent of what machine you are working on.  When working in the dev container, you will have a postgres instance running.  You can access the postgres instance just by running psql.
 
-
diff --git a/.devcontainer/devcontainer.json b/.devcontainer/devcontainer.json
index c880fcea8..87eb3c386 100644
--- a/.devcontainer/devcontainer.json
+++ b/.devcontainer/devcontainer.json
@@ -4,7 +4,6 @@
     "service": "app",
     "workspaceFolder": "/workspace",
     "remoteUser": "vscode",
-    "postCreateCommand": "bash ./.devcontainer/post-create-command.sh",
     "postStartCommand": "git config --global --add safe.directory ${containerWorkspaceFolder}",
     "forwardPorts": [4567, 5432],
     "extensions": [
diff --git a/.devcontainer/docker-compose.yml b/.devcontainer/docker-compose.yml
index a90bde562..d84f95db6 100644
--- a/.devcontainer/docker-compose.yml
+++ b/.devcontainer/docker-compose.yml
@@ -26,12 +26,10 @@ services:
     network_mode: service:db
 
   db:
-    #image: postgres:latest
-    image: postgres:15.4
+    image: postgres:15.6-bullseye
     restart: unless-stopped
     volumes:
       - postgres-data:/var/lib/postgresql/data
-      #- ../pgdata:/var/lib/postgresql/data
     environment:
       POSTGRES_USER: app_user
       POSTGRES_DB: "disclosure-backend"
diff --git a/.devcontainer/enable-ssh-agent.ps1 b/.devcontainer/enable-ssh-agent.ps1
deleted file mode 100644
index 310d46384..000000000
--- a/.devcontainer/enable-ssh-agent.ps1
+++ /dev/null
@@ -1,5 +0,0 @@
-# To use git in the dev container, you have to enable ssh agent on Windows.  Try running the following in a PowerShell as Administrator.
-# Make sure you're running as an Administrator
-Set-Service ssh-agent -StartupType Automatic
-Start-Service ssh-agent
-Get-Service ssh-agent
diff --git a/.devcontainer/post-create-command.sh b/.devcontainer/post-create-command.sh
index a6636fdb4..50e3d85ac 100644
--- a/.devcontainer/post-create-command.sh
+++ b/.devcontainer/post-create-command.sh
@@ -1,8 +1,10 @@
 #!/bin/bash
 
+set -e
+
 pip install --upgrade pip
 #pip install 'urllib3[secure]'
 pip install -r requirements.txt
-pip install -r gdrive_requirements.txt
+#pip install -r download/requirements.txt
 sudo gem install pg bundler
 sudo bundle install
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 091c40daf..60c734a6b 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -1,25 +1,112 @@
-# This workflow will later be replaced with logic to "Generate Website Data"
-# The verify-gdrive.yml workflow file will be renamed to this one
-# We have to introduce this change in steps because GitHub gets confused until
-# we add the new workflow file to the master branch
 name: "Generate Website Data"
 on:
   workflow_dispatch:
+  push:
+env:
+  POSTGRES_USER: app_user
+  POSTGRES_DB: disclosure-backend
+  POSTGRES_PASSWORD: app_password
 jobs:
-  generate:
+  build:
     runs-on: ubuntu-latest
-    env:
-      REPO_OWNER: ${{ github.repository_owner}}
-      REPO_BRANCH: ${{ github.ref_name }}
-      SERVICE_ACCOUNT_KEY_JSON: ${{ secrets.SERVICE_ACCOUNT_KEY_JSON }}
-      GDRIVE_FOLDER: ${{ vars.GDRIVE_FOLDER }}
+    outputs:
+      devcontainer: ${{ steps.filter.outputs.devcontainer }}
+      noncontainer: ${{ steps.filter.outputs.noncontainer }}
     steps:
-    - uses: actions/checkout@v3
-    - run: pip install -r gdrive_requirements.txt
-    - run: python test_pull_from_gdrive.py
-    - name: Archive pulled files
-      uses: actions/upload-artifact@v3
+    - name: Login to GitHub Container Registry
+      uses: docker/login-action@v3
       with:
-        name: redacted-netfile-files
-        path: .local/downloads
+        registry: ghcr.io
+        username: ${{github.actor}}
+        password: ${{secrets.GITHUB_TOKEN}}
+    - uses: actions/checkout@v3
+    - name: Get changed files
+      id: changed-files
+      uses: tj-actions/changed-files@v40
+    - name: List all changed files
+      id: filter
+      run: |
+        echo ${{github.event_name}}
+        noncontainer=true
+        if docker pull ghcr.io/caciviclab/disclosure-backend-static/${{github.ref_name}}:latest; then
+          devcontainer=false
+        else
+          devcontainer=true
+        fi
+        for file in ${{ steps.changed-files.outputs.all_changed_files }}; do
+          echo "$file was changed"
+          if [[ ${{github.event_name}} = push ]]; then
+            if [[ $file = .devcontainer* ]]; then
+              devcontainer=true
+            elif [[ $file = *requirements.txt* ]]; then
+              devcontainer=true
+            elif [[ $file = Gemfile* ]]; then
+              devcontainer=true
+            fi
+          fi
+        done
+        
+        echo "devcontainer=$devcontainer" >> $GITHUB_OUTPUT
+        echo "noncontainer=$noncontainer" >> $GITHUB_OUTPUT
+    - name: Build dev container
+      if: steps.filter.outputs.devcontainer == 'true'
+      run: |
+        docker build --no-cache --tag ghcr.io/caciviclab/disclosure-backend-static/${{github.ref_name}}:latest -f ./.devcontainer/Dockerfile .
+        docker push ghcr.io/caciviclab/disclosure-backend-static/${{github.ref_name}}:latest
+    - name: Check code changes
+      if: steps.filter.outputs.noncontainer == 'true'
+      run: |
+        echo "TODO: run test to verify that code changes are good"
+  generate:
+    needs: build
+    if: needs.build.outputs.noncontainer == 'true'
+    runs-on: ubuntu-latest
+    container:
+      image: ghcr.io/caciviclab/disclosure-backend-static/${{github.ref_name}}:latest
+      credentials:
+        username: ${{ github.actor }}
+        password: ${{ secrets.github_token }}
+      env:
+        REPO_OWNER: ${{ github.repository_owner}}
+        REPO_BRANCH: ${{ github.ref_name }}
+        SERVICE_ACCOUNT_KEY_JSON: ${{ secrets.SERVICE_ACCOUNT_KEY_JSON }}
+        GDRIVE_FOLDER: ${{ vars.GDRIVE_FOLDER }}
+        PGHOST: postgres
+        PGDATABASE: ${{ env.POSTGRES_DB }}
+        PGUSER: ${{ env.POSTGRES_USER }}
+        PGPASSWORD: ${{ env.POSTGRES_PASSWORD }}
+    services:
+      postgres:
+        #image: postgres:9.6-bullseye
+        image: postgres:15.6-bullseye
+        env:
+          POSTGRES_USER: ${{ env.POSTGRES_USER }}
+          POSTGRES_DB: ${{ env.POSTGRES_DB }}
+          POSTGRES_PASSWORD: ${{ env.POSTGRES_PASSWORD }}
+    steps:
+    - uses: actions/checkout@v4
+    - name: Check setup
+      run: |
+        git -v
+        # This keeps git from thinking that the current dir is not a repo even though a .git dir exists
+        git config --global --add safe.directory "$GITHUB_WORKSPACE"
+        psql -l
+        echo "c1,c2" > test.csv
+        echo "a,b" >> test.csv
+        cat test.csv
+        csvsql -v --db postgresql:///disclosure-backend --insert test.csv
+        echo "List tables"
+        psql -c "SELECT * FROM pg_catalog.pg_tables WHERE schemaname != 'pg_catalog' AND schemaname != 'information_schema';"
 
+        pip show sqlalchemy
+    - name: Create csv files
+      run: |
+        make clean
+        make download
+        make import
+        make process
+    - name: Summarize results
+      run: |
+        echo "List tables"
+        psql -c "SELECT * FROM pg_catalog.pg_tables WHERE schemaname != 'pg_catalog' AND schemaname != 'information_schema';"
+ 
diff --git a/.github/workflows/verify-gdrive.yml b/.github/workflows/verify-gdrive.yml
index 8cb029157..fcb748dac 100644
--- a/.github/workflows/verify-gdrive.yml
+++ b/.github/workflows/verify-gdrive.yml
@@ -4,6 +4,12 @@ on:
 jobs:
   check:
     runs-on: ubuntu-latest
+    container:
+      image: ghcr.io/caciviclab/disclosure-backend-static/${{github.ref_name}}:latest
+      credentials:
+        username: ${{ github.actor }}
+        password: ${{ secrets.github_token }}
+
     env:
       REPO_OWNER: ${{ github.repository_owner}}
       REPO_BRANCH: ${{ github.ref_name }}
@@ -11,8 +17,8 @@ jobs:
       GDRIVE_FOLDER: ${{ vars.GDRIVE_FOLDER }}
     steps:
     - uses: actions/checkout@v3
-    - run: pip install -r gdrive_requirements.txt
-    - run: python test_pull_from_gdrive.py
+    - name: Test pull from gdrive
+      run: python test_pull_from_gdrive.py
     - name: Archive pulled files
       uses: actions/upload-artifact@v3
       with:
diff --git a/Makefile b/Makefile
index bf7a9a39b..d3c749c08 100644
--- a/Makefile
+++ b/Makefile
@@ -10,7 +10,11 @@ clean-spreadsheets:
 	rm -rf downloads/csv/*.csv  downloads/csv/office_elections.csv  downloads/csv/measure_committees.csv downloads/csv/elections.csv
 
 clean:
-	rm -rf downloads/raw downloads/csv
+	rm -rf downloads/raw downloads/csv .local/downloads .local/csv
+	git --version
+	python --version
+	ruby --version
+	psql --version
 
 process: process.rb
 	# todo: remove RUBYOPT variable when activerecord fixes deprecation warnings
@@ -21,6 +25,9 @@ process: process.rb
 	bin/report-candidates
 	git --no-pager diff build/digests.json
 
+download-netfile-v2: 
+	python download/main.py
+
 download-spreadsheets: downloads/csv/candidates.csv downloads/csv/committees.csv \
 	downloads/csv/referendums.csv downloads/csv/name_to_number.csv \
 	downloads/csv/office_elections.csv downloads/csv/elections.csv
@@ -36,7 +43,8 @@ upload-cache:
 	tar czf - downloads/csv downloads/static downloads/cached-db \
 		| aws s3 cp - s3://odca-data-cache/$(shell date +%Y-%m-%d).tar.gz --acl public-read
 
-download: download-spreadsheets \
+download: download-netfile-v2 \
+	download-spreadsheets \
 	download-COAK-2014 download-COAK-2015 download-COAK-2016 \
 	download-COAK-2017 download-COAK-2018 \
 	download-COAK-2019 download-COAK-2020 \
@@ -110,9 +118,7 @@ do-import-spreadsheets:
 	csvsql --db postgresql:///$(DATABASE_NAME) --insert --no-create --no-inference downloads/csv/elections.csv
 	echo 'ALTER TABLE "elections" ADD COLUMN id SERIAL PRIMARY KEY;' | psql $(DATABASE_NAME)
 
-import-data: 496 497 A-Contributions B1-Loans B2-Loans C-Contributions \
-	D-Expenditure E-Expenditure F-Expenses F461P5-Expenditure F465P3-Expenditure \
-	F496P3-Contributions G-Expenditure H-Loans I-Contributions Summary
+import-data: import-old-data import-new-data
 	echo 'CREATE TABLE IF NOT EXISTS "calculations" (id SERIAL PRIMARY KEY, subject_id integer, subject_type varchar(30), name varchar(40), value jsonb);' | psql $(DATABASE_NAME)
 	./bin/remove_duplicate_transactions
 	./bin/make_view
@@ -124,9 +130,19 @@ recreatedb:
 reindex:
 	ruby search_index.rb
 
+import-new-data: elections_v2 committees_v2 a_contributions_v2
+	echo 'TODO: add new data to import'
+
+import-old-data: 496 497 A-Contributions B1-Loans B2-Loans C-Contributions \
+	D-Expenditure E-Expenditure F-Expenses F461P5-Expenditure F465P3-Expenditure \
+	F496P3-Contributions G-Expenditure H-Loans I-Contributions Summary
+
 496 497 A-Contributions B1-Loans B2-Loans C-Contributions D-Expenditure E-Expenditure F-Expenses F461P5-Expenditure F465P3-Expenditure F496P3-Contributions G-Expenditure H-Loans I-Contributions Summary:
 	DATABASE_NAME=$(DATABASE_NAME) ./bin/import-file $(CSV_PATH) $@
 
+elections_v2 committees_v2 a_contributions_v2:
+	DATABASE_NAME=$(DATABASE_NAME) ./bin/import-file $(CSV_PATH) $@ 0
+
 downloads/csv/candidates.csv:
 	mkdir -p downloads/csv downloads/raw
 	$(WGET) -O- \
diff --git a/bin/clean b/bin/clean
index e9ac2487d..dafae6847 100755
--- a/bin/clean
+++ b/bin/clean
@@ -18,4 +18,6 @@ cat <<-QUERY | psql ${database_name}
   DELETE FROM "$table_name"
   WHERE "Tran_Date" is NULL;
 QUERY
+else
+  echo
 fi
diff --git a/bin/import-file b/bin/import-file
index 635bfe786..843afe532 100755
--- a/bin/import-file
+++ b/bin/import-file
@@ -2,10 +2,12 @@
 # Contains logic to import files regardless of how many there are.
 # If there's no file, don't do anything with the database.
 # If the table already exists in the database, don't try to re-create it.
+# The fix_pending parameter defaults to 1 if not set.  Set it to 0
+# to skip the section that fixes the pending Filer_ID
 #
 # Usage:
-#   bin/import-file [csv_path] [table]
-#   bin/import-file downloads/csv A-Contributions
+#   bin/import-file [csv_path] [table] [fix_pending]
+#   bin/import-file downloads/csv A-Contributions 1
 set -euo pipefail
 
 if [ -z "${DATABASE_NAME:-""}" ]; then
@@ -14,12 +16,13 @@ if [ -z "${DATABASE_NAME:-""}" ]; then
 fi
 
 if [ $# -eq 0 ]; then
-  echo "Usage: bin/import-file [csv_path] [table]"
+  echo "Usage: bin/import-file [csv_path] [table] [fix_pending]"
   exit 1
 fi
 
 csv_path=$1
 table_name=$2
+fix_pending=${3:-1}
 filename_glob=$csv_path'/*'${table_name}'.csv'
 table_exists=
 if psql disclosure-backend -c '\d "'${table_name}'"' >/dev/null 2>&1; then
@@ -34,9 +37,10 @@ if ls $filename_glob 2>/dev/null >/dev/null; then
     csvsql --db postgresql:///$DATABASE_NAME --tables $table_name --insert --no-inference --no-create
   echo -n '  Removing empty Tran_Date... '
   ./bin/clean "$DATABASE_NAME" "$table_name"
-  echo
-  echo -n '  Fixing pending Filer_IDs... '
-  ./bin/fix-pending "$DATABASE_NAME" "$table_name"
+  if [ "$fix_pending" = "1" ]; then
+    echo -n '  Fixing pending Filer_IDs... '
+    ./bin/fix-pending "$DATABASE_NAME" "$table_name"
+  fi
 else
   echo 'Found no files to import'
 fi
diff --git a/build/_data/stats.json b/build/_data/stats.json
index 4a04467b4..702469e97 100644
--- a/build/_data/stats.json
+++ b/build/_data/stats.json
@@ -1,3 +1,3 @@
 {
-  "date_processed": "2024-06-28 00:08:43 -0700"
+  "date_processed": "2024-07-02 00:08:35 -0700"
 }
diff --git a/build/schema.sql b/build/schema.sql
index 0e830b976..3345c740b 100644
--- a/build/schema.sql
+++ b/build/schema.sql
@@ -966,7 +966,7 @@ ALTER TABLE public."G-Expenditure" OWNER TO travis;
 
 CREATE TABLE public."H-Loans" (
     "Filer_ID" integer NOT NULL,
-    "Filer_NamL" character varying(47) NOT NULL,
+    "Filer_NamL" character varying(60) NOT NULL,
     "Report_Num" character varying(3) NOT NULL,
     "Committee_Type" character varying(3) NOT NULL,
     "Rpt_Date" date NOT NULL,
@@ -998,7 +998,7 @@ CREATE TABLE public."H-Loans" (
     "Loan_EMP" character varying(32),
     "Loan_OCC" character varying(32),
     "Loan_Self" boolean NOT NULL,
-    "Cmte_ID" integer NOT NULL,
+    "Cmte_ID" integer,
     "Tres_NamL" character varying(32),
     "Tres_NamF" character varying(32),
     "Tres_NamT" character varying(32),
diff --git a/dbschema/H-Loans.sql b/dbschema/H-Loans.sql
index 9627025cc..265b66d1a 100644
--- a/dbschema/H-Loans.sql
+++ b/dbschema/H-Loans.sql
@@ -1,6 +1,6 @@
 CREATE TABLE "H-Loans" (
 	"Filer_ID" INTEGER NOT NULL, 
-	"Filer_NamL" VARCHAR(47) NOT NULL, 
+	"Filer_NamL" VARCHAR(60) NOT NULL, 
 	"Report_Num" VARCHAR(3) NOT NULL, 
 	"Committee_Type" VARCHAR(3) NOT NULL, 
 	"Rpt_Date" DATE NOT NULL, 
@@ -32,7 +32,8 @@ CREATE TABLE "H-Loans" (
 	"Loan_EMP" VARCHAR(32), 
 	"Loan_OCC" VARCHAR(32), 
 	"Loan_Self" BOOLEAN NOT NULL, 
-	"Cmte_ID" INTEGER NOT NULL, 
+	--"Cmte_ID" INTEGER NOT NULL, 
+	"Cmte_ID" INTEGER, 
 	"Tres_NamL" VARCHAR(32), 
 	"Tres_NamF" VARCHAR(32), 
 	"Tres_NamT" VARCHAR(32), 
diff --git a/dbschema/a_contributions_v2.sql b/dbschema/a_contributions_v2.sql
new file mode 100644
index 000000000..e69de29bb
diff --git a/dbschema/committees_v2.sql b/dbschema/committees_v2.sql
new file mode 100644
index 000000000..273d9e569
--- /dev/null
+++ b/dbschema/committees_v2.sql
@@ -0,0 +1,15 @@
+CREATE TABLE committees_v2 (
+	filer_nid DECIMAL NOT NULL, 
+	"Ballot_Measure_Election" VARCHAR, 
+	"Filer_ID" VARCHAR, 
+	"Filer_NamL" VARCHAR NOT NULL, 
+	"_Status" VARCHAR NOT NULL, 
+	"_Committee_Type" VARCHAR NOT NULL, 
+	"Ballot_Measure" VARCHAR, 
+	"Support_Or_Oppose" VARCHAR, 
+	candidate_controlled_id BOOLEAN, 
+	"Start_Date" DATE, 
+	"End_Date" BOOLEAN, 
+	data_warning BOOLEAN, 
+	"Make_Active" BOOLEAN
+);
diff --git a/dbschema/elections_v2.sql b/dbschema/elections_v2.sql
new file mode 100644
index 000000000..1f4ab2fd6
--- /dev/null
+++ b/dbschema/elections_v2.sql
@@ -0,0 +1,6 @@
+CREATE TABLE elections_v2 (
+	location VARCHAR NOT NULL, 
+	date DATE NOT NULL, 
+	name VARCHAR NOT NULL, 
+	title VARCHAR NOT NULL
+);
diff --git a/download/main.py b/download/main.py
index 3658b2476..95730b21e 100644
--- a/download/main.py
+++ b/download/main.py
@@ -1,4 +1,7 @@
 """ main, to run everything """
+from collections import Counter
+from datetime import datetime
+import os
 import json
 from model.a_contributions import A_Contributions
 from model.committee import Committees
@@ -21,7 +24,12 @@ def unique_statuses(filers):
 
 def main():
     """ Do everyting """
-    # pull data from gdrive and put it in .local/downloads
+    data_dir_path = '.local/downloads'
+    csv_data_dir_path = '.local/csv'
+    os.makedirs(data_dir_path, exist_ok=True)
+    os.makedirs(csv_data_dir_path, exist_ok=True)
+
+    # pull data from gdrive and put it in .local/downloads/raw
     pull_data(subfolder='main', default_folder='OpenDisclosure')
 
     with open(f'{DATA_DIR_PATH}/elections.json', encoding='utf8') as f:
@@ -72,9 +80,9 @@ def main():
             'XRef_Match',
         ]).sample(n=20))
 
-    elections.df.write_csv(f'{OUTPUT_DIR}/elections.csv')
-    committees.df.write_csv(f'{OUTPUT_DIR}/committees.csv')
-    a_contributions.df.write_csv(f'{OUTPUT_DIR}/a_contributions.csv')
+    elections.df.write_csv(f'{csv_data_dir_path}/elections.csv')
+    committees.df.write_csv(f'{csv_data_dir_path}/committees.csv')
+    a_contributions.df.write_csv(f'{csv_data_dir_path}/a_contributions.csv')
 
 if __name__ == '__main__':
     main()
diff --git a/download/requirements.txt b/download/requirements.txt
deleted file mode 100644
index 453185900..000000000
--- a/download/requirements.txt
+++ /dev/null
@@ -1,6 +0,0 @@
-pandas~=2.0.3
-SQLAlchemy~=2.0.20
-psycopg2~=2.9.7
-gdrive-datastore==0.0.1.5
-pyarrow==14.0.1
-polars==0.19.12
diff --git a/gdrive_requirements.txt b/gdrive_requirements.txt
deleted file mode 100644
index fad47bef5..000000000
--- a/gdrive_requirements.txt
+++ /dev/null
@@ -1 +0,0 @@
-gdrive-datastore==0.0.1.5
diff --git a/requirements.txt b/requirements.txt
index 74c4a8ac2..e24fe46ff 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -4,18 +4,21 @@ Babel==2.9.1
 csvkit==1.4.0
 dbfread==2.0.7
 et-xmlfile==1.0.1
+gdrive-datastore==0.0.1.5
 isodate==0.5.4; python_version < '3.0' 
 isodate==0.6.1; python_version >= '3.0' 
 jdcal==1.3
 leather==0.3.3
-openpyxl==2.4.2
+openpyxl==3.1.5
+pandas~=2.0.3
 parsedatetime==2.1
 polars==0.20.1
 psycopg2-binary==2.7.4; python_version < '3.0'
-psycopg2-binary==2.8.6; python_version >= '3.0'
-python-dateutil==2.2
+psycopg2-binary==2.9.7; python_version >= '3.0'
+pyarrow==14.0.1
+python-dateutil==2.8.2
 pytimeparse==1.1.5
-pytz==2016.10
+pytz==2020.1
 regex==2016.12.27
 six==1.10.0
 SQLAlchemy~=2.0.23