draft of hearings API

This commit is contained in:
James Turk 2025-01-10 17:05:25 -06:00
parent a4925b4a3e
commit 8f7c857c0c
2 changed files with 103 additions and 0 deletions

View File

@ -0,0 +1,40 @@
{
"hearing": {
"chamber": "House",
"citation": "H.Hrg.118",
"committees": [
{
"name": "House Public Lands Committee",
"systemCode": "hsii00",
"url": "https://api.congress.gov/v3/committee/house/hsii00?format=json"
}
],
"congress": 118,
"dates": [
{
"date": "2024-03-20"
}
],
"formats": [
{
"type": "Formatted Text",
"url": "https://congress.gov/118/chrg/CHRG-118hhrg55272/generated/CHRG-118hhrg55272.htm"
},
{
"type": "PDF",
"url": "https://congress.gov/118/chrg/CHRG-118hhrg55272/CHRG-118hhrg55272.pdf"
}
],
"jacketNumber": 55272,
"libraryOfCongressIdentifier": "LC73548",
"title": "H.R. 5015, H.R. 5499, H.R. 6085, H.R. 6209, H.R. 6547, AND H.R. 7006",
"updateDate": "2025-01-09T03:34:11Z"
},
"request": {
"chamber": "house",
"congress": "118",
"contentType": "application/json",
"format": "json",
"jacketNumber": "55272"
}
}

63
scrapple/hearings.py Normal file
View File

@ -0,0 +1,63 @@
import httpx
import json
import pathlib
from . import app
from flask import request
BASE_API_URL = "https://scrapple.fly.io/hearings/house/118/"
BASE_DIR = pathlib.Path("data/congress-hearing-118-house")
def _load_hearings():
all = {}
for hfile in BASE_DIR.glob("*.json"):
data = json.loads(hfile.read_text())
all[data["request"]["jacketNumber"]] = data
return all
ALL_HEARINGS = _load_hearings()
HEARING_IDS = list(ALL_HEARINGS.keys()) # semi-consistent ordering
def shortened(hearing):
"""return compact hearing form for list view"""
return {
"chamber": hearing["request"]["chamber"],
"congress": hearing["request"]["congress"],
"jacketNumber": hearing["request"]["jacketNumber"],
"updateDate": hearing["hearing"]["updateDate"],
"url": BASE_API_URL + hearing["request"]["jacketNumber"],
}
@app.route("/hearings")
def hearings_list():
offset = int(request.args.get("offset", 0))
limit = int(request.args.get("limit", 50))
format = request.args.get("format", "json")
if offset + limit > len(ALL_HEARINGS):
next_url = None
else:
next_url = str(
httpx.URL(BASE_API_URL).copy_with(
params={"offset": offset + limit, "limit": limit, "format": format}
)
)
hearing_ids = HEARING_IDS[offset : offset + limit]
hearings = [ALL_HEARINGS[h] for h in hearing_ids]
return {
"hearings": [shortened(h) for h in hearings],
"pagination": {"count": len(ALL_HEARINGS), "next": next_url},
"chamber": {
"chamber": "house",
"congress": "118",
"contentType": "application/json",
"format": "json",
},
}
@app.route("/hearings/<jacket_id>")
def hearings_detail(jacket_id):
return ALL_HEARINGS[jacket_id]