File size: 11,097 Bytes
fdaad4e 3568f5f fdaad4e 3568f5f fdaad4e 3568f5f fdaad4e 3568f5f fdaad4e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 |
import streamlit as st
import pandas as pd
import requests
import json
import os
import xml.etree.ElementTree as ET
from typing import Dict, List
# Sample agency data
AGENCIES = {
"Department of Justice": {
"name": "Department of Justice",
"summary": {
"name": "Department of Justice",
"description": "The mission of the DOJ is to enforce the law...",
"abbreviation": "DOJ",
"website": "https://www.justice.gov"
},
"website": "https://www.justice.gov",
"emails": ["[email protected]"],
"address": {
"address_lines": ["950 Pennsylvania Avenue, NW"],
"street": "",
"city": "Washington",
"state": "DC",
"zip": "20530-0001"
},
"service_center": {"phone": ["202-514-2000"]},
"request_form": "https://www.justice.gov/oip/foia-request",
"request_time_stats": {
"2022": {"simple_median_days": 20, "complex_median_days": 45}
}
}
}
class Agency:
def __init__(self, data: Dict):
self.data = data
@property
def name(self) -> str:
return self.data.get("name", "")
@property
def summary(self) -> Dict:
return self.data.get("summary", {})
@property
def website(self) -> str:
return self.data.get("website", "")
@property
def emails(self) -> List[str]:
return self.data.get("emails", [])
@property
def address(self) -> Dict:
return self.data.get("address", {})
@property
def service_center(self) -> Dict:
return self.data.get("service_center", {})
@property
def request_form(self) -> str:
return self.data.get("request_form", "")
@property
def request_time_stats(self) -> Dict:
return self.data.get("request_time_stats", {})
def isFOIAonline(self) -> bool:
return "foiaonline" in self.request_form.lower()
def hasRequestForm(self) -> bool:
return bool(self.request_form)
def create_search_url_wikipedia(search_query):
base_url = "https://www.wikipedia.org/search-redirect.php?family=wikipedia&language=en&search="
return base_url + search_query.replace(' ', '+').replace('–', '%E2%80%93').replace('&', 'and')
def process_foia_xml_file(filename: str):
"""Process FOIA XML file and display results with emojis"""
try:
tree = ET.parse(filename)
root = tree.getroot()
# Namespace dictionary
ns = {
'iepd': 'http://leisp.usdoj.gov/niem/FoiaAnnualReport/exchange/1.03',
'foia': 'http://leisp.usdoj.gov/niem/FoiaAnnualReport/extension/1.03',
'nc': 'http://niem.gov/niem/niem-core/2.0',
'j': 'http://niem.gov/niem/domains/jxdm/4.1'
}
# Extract basic info
org = root.find(".//nc:Organization", ns)
org_name = org.find("nc:OrganizationName", ns).text if org is not None else "Unknown"
org_abbr = org.find("nc:OrganizationAbbreviationText", ns).text if org is not None else "N/A"
fiscal_year = root.find(".//foia:DocumentFiscalYearDate", ns).text if root.find(".//foia:DocumentFiscalYearDate", ns) is not None else "N/A"
st.subheader(f"📋 {org_name} ({org_abbr}) FOIA Report {fiscal_year}")
st.write(f"[Wikipedia - {org_name}]({create_search_url_wikipedia(org_name)})")
# Processing Statistics
proc_stats = root.find(".//foia:ProcessedRequestSection/foia:ProcessingStatistics", ns)
if proc_stats is not None:
st.write("📊 **Request Processing Statistics**")
st.write(f"- Pending at Start: {proc_stats.find('foia:ProcessingStatisticsPendingAtStartQuantity', ns).text} ⏳")
st.write(f"- Received: {proc_stats.find('foia:ProcessingStatisticsReceivedQuantity', ns).text} 📥")
st.write(f"- Processed: {proc_stats.find('foia:ProcessingStatisticsProcessedQuantity', ns).text} ✅")
st.write(f"- Pending at End: {proc_stats.find('foia:ProcessingStatisticsPendingAtEndQuantity', ns).text} ⏳")
# Request Dispositions
disp = root.find(".//foia:RequestDispositionSection/foia:RequestDisposition", ns)
if disp is not None:
st.write("📑 **Request Dispositions**")
st.write(f"- Full Grants: {disp.find('foia:RequestDispositionFullGrantQuantity', ns).text} ✅")
st.write(f"- Partial Grants: {disp.find('foia:RequestDispositionPartialGrantQuantity', ns).text} ➕")
st.write(f"- Full Denials: {disp.find('foia:RequestDispositionFullExemptionDenialQuantity', ns).text} ❌")
denial = disp.find('foia:NonExemptionDenial', ns)
if denial is not None:
st.write(f"- Non-Exemption Denial ({denial.find('foia:NonExemptionDenialReasonCode', ns).text}): {denial.find('foia:NonExemptionDenialQuantity', ns).text} 📭")
# Applied Exemptions
exemptions = root.findall(".//foia:RequestDispositionAppliedExemptionsSection/foia:ComponentAppliedExemptions/foia:AppliedExemption", ns)
if exemptions:
st.write("🚫 **Applied Exemptions**")
for ex in exemptions:
code = ex.find('foia:AppliedExemptionCode', ns).text
qty = ex.find('foia:AppliedExemptionQuantity', ns).text
st.write(f"- {code}: {qty} times")
# Response Times
resp_time = root.find(".//foia:ProcessedResponseTimeSection/foia:ProcessedResponseTime", ns)
if resp_time is not None:
st.write("⏰ **Response Times**")
simple = resp_time.find('foia:SimpleResponseTime', ns)
if simple is not None:
st.write(f"- Simple Requests:")
st.write(f" - Median: {simple.find('foia:ResponseTimeMedianDaysValue', ns).text} days ⏱️")
st.write(f" - Average: {simple.find('foia:ResponseTimeAverageDaysValue', ns).text} days 📈")
except ET.ParseError:
st.error(f"❌ Error parsing XML file: {filename}")
def list_xml_files():
xml_files = [f[:-4] for f in os.listdir('.') if f.endswith('.xml')]
if not xml_files:
st.markdown("No XML files found in the directory. 📂❓")
return []
return xml_files
def search_foia_content(query: str, agency: str = None) -> Dict:
results = {
"query": query,
"agency": agency,
"results": [
{"title": f"Sample FOIA Response 1 for {query}", "date": "2023-01-01"},
{"title": f"Sample FOIA Response 2 for {query}", "date": "2023-02-01"}
]
}
return results
def main():
st.title("Freedom of Information Act (FOIA) Explorer 🌍📊")
tab1, tab2 = st.tabs(["Agency Browser", "FOIA Datasets & XML Scanner"])
with tab1:
st.header("Agency Browser")
agency_names = sorted(list(AGENCIES.keys()))
selected_agency = st.selectbox("Select Agency", [""] + agency_names)
if selected_agency:
agency = Agency(AGENCIES[selected_agency])
st.subheader(f"{agency.name} Details")
st.write(f"Description: {agency.summary.get('description', 'N/A')}")
st.write(f"Abbreviation: {agency.summary.get('abbreviation', 'N/A')}")
if agency.website:
st.write(f"Website: [{agency.website}]({agency.website})")
st.subheader("Contact Information")
contact_info = [
"\n".join(agency.address.get("address_lines", [])),
agency.address.get("street", ""),
f"{agency.address.get('city', '')}, {agency.address.get('state', '')} {agency.address.get('zip', '')}",
agency.service_center.get("phone", [""])[0]
]
st.write("\n".join([line for line in contact_info if line]))
if agency.emails:
st.write(f"Email: [{agency.emails[0]}](mailto:{agency.emails[0]})")
if agency.hasRequestForm():
form_url = "https://foiaonline.regulations.gov/foia/action/public/request/createRequest" if agency.isFOIAonline() else agency.request_form
st.write(f"[Submit FOIA Request]({form_url})")
st.subheader("Median Processing Times")
if agency.request_time_stats:
for year, stats in agency.request_time_stats.items():
col1, col2 = st.columns(2)
with col1:
st.write(f"Year: {year}")
with col2:
for key, value in stats.items():
if "median" in key:
st.write(f"{key.replace('_median_days', '').title()}: {value} days")
st.subheader("Search FOIA Documents")
search_query = st.text_input("Enter search query")
if st.button("Search") and search_query:
with st.spinner("Searching..."):
results = search_foia_content(search_query, selected_agency)
st.write(f"Found {len(results['results'])} results for '{search_query}':")
for result in results["results"]:
st.write(f"- {result['title']} ({result['date']})")
with tab2:
st.header("FOIA Datasets & XML Scanner")
st.write("""
The Freedom of Information Act (FOIA) empowers individuals by granting access to previously unreleased information and documents controlled by the United States government. Championing transparency and accountability, FOIA serves as a foundation for democratic engagement and open government initiatives. 🎉✨
Below is a list of datasets available under FOIA, alongside guessed Wikipedia URLs for more information. 📚🔍
""")
st.markdown("""
- [FOIA.Gov](https://www.foia.gov/foia-dataset-download.html)
- [Data.Gov](https://catalog.data.gov/dataset?tags=foia)
""")
datasets = [
"Provider Taxonomy",
"Consumer Complaint Database",
"Medicare Provider Utilization and Payment Data",
"Global Terrorism Database",
"National Nutrient Database",
"Patent Grant Full Text Data",
"Toxic Release Inventory",
"Residential Energy Consumption Survey",
]
st.markdown("### FOIA Datasets and Wikipedia URLs")
for dataset in datasets:
st.markdown(f"- **{dataset}**: [Wikipedia]({create_search_url_wikipedia(dataset)})")
st.markdown("### Available FOIA XML Reports")
xml_files = list_xml_files()
for xml_file in xml_files:
col1, col2 = st.columns([3, 1])
with col1:
st.markdown(f"- [{xml_file}]({xml_file}.xml)")
with col2:
if st.button(f"📊 Process {xml_file}", key=f"process_{xml_file}"):
process_foia_xml_file(f"{xml_file}.xml")
if __name__ == "__main__":
main() |