Compare commits

..

4 Commits

Author SHA256 Message Date
97c96ed0fc checkpoint 2025-03-09 01:47:27 -08:00
207449ee26 add create_legislation_node endpiont 2025-03-08 22:57:53 -08:00
84156a1ce9 legislation cache working now too 2025-03-08 15:13:55 -08:00
be101beac8 cache working 2025-03-08 14:16:40 -08:00
3 changed files with 148 additions and 38 deletions

View File

@ -1,4 +1,3 @@
# app.py
from flask import Flask, jsonify, request
import os
import logging
@ -7,6 +6,7 @@ from dotenv import load_dotenv
from werkzeug.middleware.proxy_fix import ProxyFix
import importlib.util
# Load environment variables from .env file
load_dotenv()
app = Flask(__name__)
@ -40,7 +40,6 @@ def load_blueprints_from_directory(directory):
if filename.endswith('.py') and not filename.startswith('__'):
module_name = filename[:-3] # Remove .py extension
file_path = os.path.join(directory, filename)
spec = importlib.util.spec_from_file_location(module_name, file_path)
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module)
@ -51,5 +50,23 @@ def load_blueprints_from_directory(directory):
# Load blueprints
load_blueprints_from_directory('endpoints')
# Sitemap endpoint function
def sitemap():
# Get all registered routes
routes = []
for rule in app.url_map.iter_rules():
# Skip the sitemap route itself to avoid infinite recursion
if rule.endpoint != 'sitemap':
routes.append({
'rule': rule.rule,
'methods': list(rule.methods),
'endpoint': rule.endpoint
})
return jsonify(routes)
# Register the sitemap endpoint
app.add_url_rule('/sitemap', view_func=sitemap, methods=['GET'])
if __name__ == '__main__':
app.run(debug=True)

View File

@ -0,0 +1,58 @@
from flask import Blueprint, jsonify
import json
import os
import logging
from neo4j import GraphDatabase
from dotenv import load_dotenv
bp = Blueprint('create_legislation_node', __name__)
@bp.route('/create_legislation_node', methods=['GET'])
def create_legislation_nodes():
# Assuming the legislation cache is stored in a JSON file
legislation_cache_path = os.getenv("LEGISLATION_CACHE_PATH")
if not legislation_cache_path:
return jsonify({"error": "Legislation cache path is not set"}), 400
try:
with open(legislation_cache_path, 'r') as f:
legislation_data = json.load(f)
except FileNotFoundError:
return jsonify({"error": "Legislation cache file not found"}), 404
except json.JSONDecodeError:
return jsonify({"error": "Failed to decode JSON from the legislation cache"}), 500
# Ensure legislation_data is a list of dictionaries
if not isinstance(legislation_data, list):
return jsonify({"error": "Legislation data should be a list"}), 400
created_nodes = []
for item in legislation_data:
if not item.get("id"):
continue
# Prepare the properties for the node
properties = {k: v for k, v in item.items()}
# Create or merge a node in Neo4j with all properties
driver = get_driver()
with driver.session() as session:
query = "MERGE (l:Legislation {id: $id})"
for key in properties:
if key != 'id':
query += f" ON CREATE SET l.{key} = ${key}"
result = session.run(query, **properties)
# Log the creation or merging of the node
neo4j_logger.info(f"Created/Merged Legislation node with ID: {item.get('id')} and properties: {properties}")
driver.close()
created_nodes.append({"id": item.get("id"), "properties": properties})
return jsonify({"message": "Legislation nodes created/merged successfully", "nodes": created_nodes}), 201

View File

@ -1,13 +1,15 @@
# endpoints/get_sponsored.py
from flask import Blueprint, jsonify
from app import get_driver, neo4j_logger
import requests
import json
import os
import pandas as pd
# Assuming you have these functions and configurations in your app.py
from app import get_driver, neo4j_logger
bp = Blueprint('get_sponsored', __name__)
CACHE_FILE = 'cache.json'
CSV_FILE = 'legislation.csv'
def load_cache():
if os.path.exists(CACHE_FILE):
@ -22,11 +24,57 @@ def save_cache(cache_data):
json.dump(cache_data, f)
neo4j_logger.info(f"Saved data to cache file: {CACHE_FILE}")
def write_to_csv(legislation_data, csv_file):
# Flatten the nested dictionaries
flattened_legislation = []
for item in legislation_data:
flattened_item = {}
flatten_dict(item, "", flattened_item)
flattened_legislation.append(flattened_item)
df = pd.DataFrame(flattened_legislation)
if df.empty:
neo4j_logger.warning(f"No data to write to CSV file: {csv_file}")
print("DataFrame is empty. Debugging information:")
for item in flattened_legislation[:5]: # Print first 5 items
print(json.dumps(item, indent=4))
return
# Debugging statement to check DataFrame contents
print("DataFrame contents:")
print(df.head())
df.to_csv(csv_file, index=False)
neo4j_logger.info(f"Data written to CSV file: {csv_file}")
def flatten_dict(d, parent_key='', sep='_'):
items = []
for k, v in d.items():
new_key = f"{parent_key}{sep}{k}" if parent_key else k
if isinstance(v, dict):
# Debugging: Print the key and value when entering a nested dictionary
print(f"Entering nested dictionary with key: {new_key}")
items.extend(flatten_dict(v, new_key, sep=sep).items())
elif isinstance(v, list):
# Handle lists by converting them to strings or other appropriate representation
if v:
items.append((new_key, ', '.join(map(str, v))))
else:
# If the list is empty, add an empty string or a placeholder
items.append((new_key, ''))
elif v is not None:
# Debugging: Print the key and value when adding a non-dict, non-list item
print(f"Adding {new_key}: {v}")
items.append((new_key, v))
else:
# Handle None values appropriately (e.g., add an empty string or a placeholder)
items.append((new_key, ''))
return dict(items)
@bp.route('/get_sponsored')
def get_sponsored():
# Load bioguideIds and legislation from the same cache
cache = load_cache()
if 'bioguideIds' not in cache or len(cache['bioguideIds']) == 0:
return jsonify({"message": "No bioguideIds found in cache"}), 404
@ -35,11 +83,11 @@ def get_sponsored():
print(f"Initial bioguideIds count: {initial_bioguideIds_count}")
processed_legislation_count = 0
all_legislation_data = []
while 'bioguideIds' in cache and len(cache['bioguideIds']) > 0:
# Step 1: Retrieve a sponsor from the cache
current_bioguideId = cache['bioguideIds'].pop(0)
if current_bioguideId is None:
continue
@ -59,7 +107,6 @@ def get_sponsored():
# Step 2: Fetch sponsored legislation for the member
response = requests.get(congress_api_url, headers=headers)
print(f"Response Status Code: {response.status_code}")
print(f"Response Text: {response.text}")
@ -67,39 +114,27 @@ def get_sponsored():
neo4j_logger.error(f"Failed to fetch sponsored legislation for bioguideId {current_bioguideId}: Status Code {response.status_code}, Response: {response.text}")
continue
legislations = response.json().get('results', [])
response_data = response.json()
# Step 3: Store each piece of legislation in the cache along with the sponsor bioguideId
for legislation in legislations:
key = f"legislation_{legislation['id']}"
# Debugging statement to check the raw API response
print("Raw API Response:")
print(json.dumps(response_data, indent=4))
print(f"About to write to cache: {key} - {legislation}")
# Extract legislation data from the response
if 'sponsoredLegislation' in response_data and len(response_data['sponsoredLegislation']) > 0:
for result in response_data['sponsoredLegislation']:
all_legislation_data.append(result)
if key not in cache:
cache[key] = {
'bioguideId': current_bioguideId,
**legislation
}
processed_legislation_count += 1
# Debugging statement to check the number of legislation items collected
print(f"Number of legislation items collected: {len(all_legislation_data)}")
# Save the cache immediately after writing each entry
save_cache(cache)
if len(all_legislation_data) > 0:
# Print first few items to ensure data is structured correctly
for i, item in enumerate(all_legislation_data[:5]):
print(f"\nLegislation Item {i+1}:")
print(json.dumps(item, indent=4))
# Print the updated legislation cache for debugging
print(f"Updated legislation cache: {json.dumps(cache, indent=2)}")
# Write the extracted legislation data to a CSV file
write_to_csv(all_legislation_data, CSV_FILE)
# Step 4: Delete the sponsor from the bioguideIds list (already done by popping)
neo4j_logger.info(f"Processed sponsored legislation for bioguideId {current_bioguideId}")
# Print the number of items left in the bioguide cache
remaining_bioguideIds_count = len(cache['bioguideIds'])
print(f"Remaining bioguideIds count after processing {current_bioguideId}: {remaining_bioguideIds_count}")
# Save the cache again to ensure all changes are persisted
save_cache(cache)
# Print the total number of legislation items stored and overall items added to the cache
print(f"Total processed legislation count: {processed_legislation_count}")
print(f"Overall items in cache: {len(cache)}")
return jsonify({"message": "Sponsored legislation processed successfully", "processed_legislation_count": processed_legislation_count}), 200
return jsonify({"message": "Legislation data written to CSV successfully"}), 200