Search then enrich

# search_then_enrich.py
# Topic -> top posts -> unique authors -> full profiles.
# Run with: INSIGHTSOCIAL_API_KEY=isk_live_... python search_then_enrich.py
import os
from concurrent.futures import ThreadPoolExecutor

import requests

KEY = os.environ["INSIGHTSOCIAL_API_KEY"]
BASE = "https://api.insightsocial.app/v1"
TOPIC = "home espresso setup"
KEYWORDS = ["espresso"]  # a post must mention one of these to count as on-topic
ACCOUNTS_PER_PLATFORM = 5

SEARCH = {"tiktok": "tiktok/search", "instagram": "instagram/search/reels"}
PROFILE = {"tiktok": "tiktok/profile", "instagram": "instagram/profile"}

def get(path, **params):
    res = requests.get(f"{BASE}/{path}", params=params,
                       headers={"x-api-key": KEY}, timeout=120)
    return res.json()

def on_topic(post):
    text = (post["content"]["text"] or "").lower()
    return any(k in text for k in KEYWORDS)

# Step 1: search both platforms.
with ThreadPoolExecutor(max_workers=2) as pool:
    found = dict(zip(SEARCH, pool.map(
        lambda p: get(SEARCH[p], query=TOPIC), SEARCH)))

# Step 2: unique authors of on-topic posts, in the order the search ranked them.
targets = []
for platform, body in found.items():
    if not body["success"]:
        print(f"{platform} search: {body['error']['type']}")
        continue
    handles = []
    for item in body["data"]["items"]:
        post = item["post"]
        handle = post["author"]["username"]
        if handle and handle not in handles and on_topic(post):
            handles.append(handle)
    targets += [(platform, h) for h in handles[:ACCOUNTS_PER_PLATFORM]]

# Step 3: enrich every author with a profile call.
def enrich(target):
    platform, handle = target
    return platform, handle, get(PROFILE[platform], handle=handle)

with ThreadPoolExecutor(max_workers=10) as pool:
    profiles = list(pool.map(enrich, targets))

rows = []
for platform, handle, body in profiles:
    if not body["success"]:
        continue
    author = body["data"]["author"]
    rows.append({
        "platform": platform,
        "handle": handle,
        "followers": author["followers"],
        "bio": (author["bio"] or "")[:60],
        "link": author["external_url"],
        "email": (author["ext"] or {}).get("public_email"),
    })

rows.sort(key=lambda r: r["followers"] or 0, reverse=True)
for r in rows:
    print(r)
spent = sum(b.get("credits_used", 0) for b in found.values()) + \
        sum(b.get("credits_used", 0) for _, _, b in profiles)
print(f"credits used: {spent}")