> ## Documentation Index
> Fetch the complete documentation index at: https://docs.wokelo.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Industry News Monitoring
> Fetch the latest news articles for any industry topic or sector, enriched with AI-generated summaries and geographic tags — returned synchronously with flexible date, geography, and publisher filtering.
## 1. Overview
The Industry News Monitoring API fetches the latest news articles for a given industry topic or sector, enriched with AI-generated summaries, geographic signals, and source metadata. Results are returned synchronously in the HTTP response — no job polling required.
This is a **synchronous GET API** — you pass a free-text topic and optional filters as URL parameters, and receive a paginated array of enriched news articles immediately.
Unlike the [Company News Monitoring API](/company-news-monitoring-doc), which fetches news anchored to a specific company, this API accepts any natural-language topic — a sector, a technology, a theme, a geopolitical event, or a cross-company trend. The breadth of coverage is defined by the `topic` string and optionally narrowed by `geo` and date range.
Each article in the response includes:
* **AI summary** — a concise, machine-generated synopsis of the article's key facts and implications
* **Geographic tags** — ISO 3166-1 alpha-3 country codes identifying which geographies are relevant to the article
* **Publisher and source metadata** — article URL, title, publication datetime, and source attribution
* **Article identifier** — a stable numeric `id` for deduplication across paginated requests
**Common use cases:**
* **Sector monitoring for investment research** — Track news on themes like "warehouse automation", "GLP-1 drugs", or "offshore wind" across a rolling 30-day window without being tied to a specific company
* **Geopolitical and macro intelligence** — Monitor topics like "US-China trade war", "European energy security", or "emerging market debt" filtered to specific regions using the `geo` parameter
* **LP and fund reporting** — Aggregate industry-level developments across portfolio sectors for quarterly reporting or LP briefings
* **Market entry and expansion research** — Filter a topic to a specific country or region (e.g., "electric vehicle charging" in `IND`) to surface market-specific activity
* **Thematic investment screening** — Use the `ai_summary` field to efficiently triage large volumes of sector news before reading full articles
* **Regulatory and policy tracking** — Monitor topics like "data privacy regulation", "carbon border adjustment", or "AI legislation" with geographic narrowing to track jurisdiction-specific developments
This API is synchronous. Results are returned directly in the HTTP response — no job submission or polling required. See [How Sync APIs work](/how-sync-apis-work).
***
## 2. Quick Start
**Step 1 — Make a simple request**
```bash cURL theme={"system"}
curl --location 'https://api.wokelo.ai/api/enterprise/industry/news/?topic=Trade%20war&limit=100' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json'
```
```python Python theme={"system"}
import requests
response = requests.get(
"https://api.wokelo.ai/api/enterprise/industry/news/",
headers={
"Authorization": "Bearer ",
"Content-Type": "application/json"
},
params={
"topic": "Trade war",
"limit": 100
}
)
data = response.json()
print(f"Retrieved {data['count']} of {data['total']} articles")
```
**Step 2 — Narrow by geography and date range**
```python theme={"system"}
response = requests.get(
"https://api.wokelo.ai/api/enterprise/industry/news/",
headers={"Authorization": "Bearer "},
params={
"topic": "Real Estate Development",
"geo": "ARE",
"start_date": "2026-04-01",
"end_date": "2026-04-30",
"limit": 100
}
)
articles = response.json()["data"]
```
**Step 3 — Work with the articles**
```python theme={"system"}
for article in articles:
geo_str = ", ".join(article.get("geo", []))
print(f"[{geo_str}] {article['title']}")
print(f" {article['published_date'][:10]}")
print(f" {article['ai_summary'][:150]}...")
print()
```
***
## 3. Authentication
All requests must include a **Bearer token** in the `Authorization` HTTP header. No other authentication method is supported.
```text theme={"system"}
Authorization: Bearer
```
API tokens are issued from your Wokelo account. Navigate to **Account Details → API Credentials** in the Wokelo dashboard to get your client id and client secret. Contact [support@wokelo.ai](mailto:support@wokelo.ai) if you do not yet have API access.
Never expose your token in client-side code, browser requests, or public repositories. A missing or invalid token returns `401 Unauthorized`. A valid token without sufficient plan permissions returns `403 Forbidden`.
***
## 4. Request Reference
**Endpoint**
```text theme={"system"}
GET https://api.wokelo.ai/api/enterprise/industry/news/
```
All parameters are passed as URL query parameters.
| Parameter | Type | Required | Description |
| ------------- | ------- | ------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `topic` | string | **Required** | Free-text description of the industry, sector, or theme to monitor. The query engine matches articles by relevance to this string. Specific, descriptive topics yield tighter results than broad single-word queries. Examples: `"Warehouse Automation"`, `"GLP-1 obesity drugs"`, `"Real Estate Development"`, `"US-China trade tariffs"`. |
| `start_date` | string | Optional | Start of the date window for articles (`YYYY-MM-DD`). Inclusive. |
| `end_date` | string | Optional | End of the date window for articles (`YYYY-MM-DD`). Inclusive. |
| `limit` | integer | Optional | Maximum number of articles to return. Default `100`, max `1000`. |
| `offset` | integer | Optional | Number of articles to skip before returning results. Default `0`. Use with `limit` for pagination. |
| `blacklisted` | string | Optional | Comma-separated list of publisher domains to exclude. Include the full domain starting with `https://` (e.g. `"https://www.prnewswire.com/"`). |
| `geo` | string | Optional | Comma-separated list of ISO 3166-1 alpha-3 country codes to filter articles by geography (e.g. `"USA"`, `"GBR,DEU,FRA"`, `"ARE"`). Returns only articles tagged with at least one of the specified countries. |
**Full request example:**
```bash cURL theme={"system"}
curl --location 'https://api.wokelo.ai/api/enterprise/industry/news/?topic=Warehouse%20automation&start_date=2026-04-01&end_date=2026-04-30&geo=IND&limit=100&offset=0&blacklisted=https%3A%2F%2Fwww.prnewswire.com%2F' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json'
```
```python Python theme={"system"}
import requests
response = requests.get(
"https://api.wokelo.ai/api/enterprise/industry/news/",
headers={
"Authorization": "Bearer ",
"Content-Type": "application/json"
},
params={
"topic": "Warehouse automation",
"start_date": "2026-04-01",
"end_date": "2026-04-30",
"geo": "IND",
"limit": 100,
"offset": 0,
"blacklisted": "https://www.prnewswire.com/"
}
)
print(response.json())
```
***
## 5. Response
### Response structure
```json theme={"system"}
{
"status": "success",
"data": [ ...article objects... ],
"count": 14,
"total": 14,
"limit": 100,
"offset": 0
}
```
| Field | Type | Description |
| -------- | ------- | ------------------------------------------------------------------------------------------------------- |
| `status` | string | `"success"` when the request was processed successfully. |
| `data` | array | Array of enriched article objects. |
| `count` | integer | Number of articles returned in this response batch. |
| `total` | integer | Total number of matching articles available across all pages (before `limit` and `offset` are applied). |
| `limit` | integer | The `limit` value applied to this response. |
| `offset` | integer | The `offset` value applied to this response. |
### Article object fields
Each object in the `data` array contains the following fields:
**Article identity**
| Field | Type | Description |
| ---------------- | ------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- |
| `id` | integer | Stable numeric identifier for this article in Wokelo's index. Use for deduplication when paginating or comparing runs across different date windows. |
| `url` | string | Canonical URL of the original article. |
| `title` | string | Headline of the article as published. |
| `published_date` | string | Publication datetime in `YYYY-MM-DD HH:MM:SS` format (UTC). |
**AI enrichment**
| Field | Type | Description |
| ------------ | ------ | -------------------------------------------------------------------------------------------- |
| `ai_summary` | string | AI-generated 2–4 sentence summary of the article's key facts and implications for the topic. |
**Source and geography**
| Field | Type | Description |
| -------- | --------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `source` | string | Wokelo's internal signal source designation. Either `"Wokelo"` (directly indexed) or `"Google"` (sourced via search). |
| `geo` | string\[] | Array of ISO 3166-1 alpha-3 country codes identifying the geographies covered or referenced in the article (e.g. `["USA", "CHN"]`). Empty array when no country was detected. |
The Industry News Monitoring API returns a leaner article object than the Company News Monitoring API. Fields like `sentiment`, `primary_tag`, `secondary_tags`, `newsworthiness_impact`, `company_names`, `publisher`, `author`, and `scraped_text` are not included in industry news responses. Use `ai_summary` for content triage and `url` to fetch the full article when needed.
### Notes on the `geo` field
The `geo` array reflects countries that are mentioned or relevant in the article — not necessarily where the article was published. A single article covering US-China trade policy may have `["USA", "CHN"]`. An article about a regional development project may have only one code.
* **Multi-country articles** — articles covering diplomatic events, bilateral trade deals, or multinational company activity commonly list three or more country codes
* **Empty geo** — some articles have an empty `geo` array when country detection was inconclusive; these are still returned unless you have filtered by `geo`
* **`geo` filter behaviour** — when you pass `geo=IND,SGP`, the API returns articles tagged with `IND` **or** `SGP`, not exclusively articles tagged with both
### Pagination notes
Industry topic queries can return very large result sets. For broad topics like "trade war" or "artificial intelligence" the `total` count can exceed several thousand. Always check `total` against `count` and paginate using `offset` until all records have been retrieved. The recommended approach is to stop when `count` returns `0` or `len(all_articles) >= total`.
***
## 6. Examples
### Monitoring a sector in a specific region
Fetch all real estate development news in the UAE for a specific month — useful for generating a sector brief or LP update.
```bash cURL theme={"system"}
curl --location 'https://api.wokelo.ai/api/enterprise/industry/news/?topic=Real%20Estate%20Development&geo=ARE&start_date=2026-04-01&end_date=2026-04-30&limit=100' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json'
```
```python Python theme={"system"}
import requests
HEADERS = {"Authorization": "Bearer "}
response = requests.get(
"https://api.wokelo.ai/api/enterprise/industry/news/",
headers=HEADERS,
params={
"topic": "Real Estate Development",
"geo": "ARE",
"start_date": "2026-04-01",
"end_date": "2026-04-30",
"limit": 100
}
)
data = response.json()
articles = data["data"]
print(f"Found {data['total']} articles on Real Estate Development in UAE\n")
for article in articles:
print(f"[{article['published_date'][:10]}] {article['title']}")
print(f" {article['ai_summary'][:200]}...")
print()
```
**Sample response (excerpt):**
```json theme={"system"}
{
"status": "success",
"data": [
{
"id": 10442144,
"ai_summary": "Nakheel has awarded contracts worth over Dh3.5 billion to construct 544 villas on Palm Jebel Ali, part of a major waterfront development in Dubai. Construction is set to start this quarter and aims for completion by late 2028, featuring smart and sustainable homes.",
"url": "https://gulfnews.com/business/property/nakheel-awards-dh35-billion-contracts-for-palm-jebel-ali-villas-1.500520259",
"title": "Nakheel Awards Dh3.5 Billion Contracts for 544 Palm Jebel Ali Villas in Major Dubai Waterfront Push",
"published_date": "2026-04-27 05:20:10",
"source": "Wokelo",
"geo": ["ARE"]
},
{
"id": 8786881,
"ai_summary": "Dubai's real estate market experienced a 23.4% increase in property sales value in Q1 2026, with off-plan projects being the primary driver of growth.",
"url": "https://www.constructionworld.in/latest-construction-news/real-estate-news/dubai-q1-property-sales-rise-23.4--in-value/89514",
"title": "Dubai Q1 Property Sales Rise 23.4% in Value",
"published_date": "2026-04-06 12:11:07",
"source": "Wokelo",
"geo": ["ARE"]
}
],
"count": 14,
"total": 14,
"limit": 100,
"offset": 0
}
```
### Multi-region sector sweep
Monitor a technology sector across several markets simultaneously by passing multiple `geo` codes. Useful for tracking a theme across different regulatory or market environments.
```python theme={"system"}
import requests
HEADERS = {"Authorization": "Bearer "}
response = requests.get(
"https://api.wokelo.ai/api/enterprise/industry/news/",
headers=HEADERS,
params={
"topic": "Electric vehicle charging infrastructure",
"geo": "USA,GBR,DEU,FRA,IND",
"start_date": "2026-01-01",
"end_date": "2026-04-30",
"limit": 200
}
)
articles = response.json()["data"]
# Group by primary geography (first country code in the geo array)
from collections import defaultdict
by_geo = defaultdict(list)
for a in articles:
primary = a["geo"][0] if a.get("geo") else "Unknown"
by_geo[primary].append(a)
for country, items in sorted(by_geo.items(), key=lambda x: -len(x[1])):
print(f"\n{country}: {len(items)} articles")
for a in items[:2]:
print(f" [{a['published_date'][:10]}] {a['title']}")
```
### Rolling 30-day monitoring pipeline
Set up a recurring pull that always covers the most recent 30 days, suitable for a weekly digest or automated feed.
```python theme={"system"}
import requests
from datetime import datetime, timedelta
HEADERS = {"Authorization": "Bearer "}
def fetch_industry_news(topic, geo=None, days=30, blacklist=None):
end_date = datetime.today().strftime("%Y-%m-%d")
start_date = (datetime.today() - timedelta(days=days)).strftime("%Y-%m-%d")
params = {
"topic": topic,
"start_date": start_date,
"end_date": end_date,
"limit": 200
}
if geo:
params["geo"] = geo
if blacklist:
params["blacklisted"] = blacklist
response = requests.get(
"https://api.wokelo.ai/api/enterprise/industry/news/",
headers=HEADERS,
params=params
)
return response.json()
BLACKLIST = "https://www.prnewswire.com/, https://www.businesswire.com/"
topics = [
("Warehouse Automation", "USA,GBR,DEU"),
("GLP-1 obesity drugs", "USA"),
("Carbon border adjustment", "EU,GBR,DEU,FRA")
]
for topic, geo in topics:
result = fetch_industry_news(topic, geo=geo, days=30, blacklist=BLACKLIST)
print(f"\n{'='*60}")
print(f"Topic: {topic} | Region: {geo}")
print(f"Articles: {result['total']}")
for a in result["data"][:3]:
print(f" [{a['published_date'][:10]}] {a['title']}")
print(f" {a['ai_summary'][:150]}...")
```
### Paginating through large topic result sets
For broad topics, `total` can significantly exceed `limit`. Paginate using `offset` until all records are retrieved.
```python theme={"system"}
import requests
HEADERS = {"Authorization": "Bearer "}
PARAMS = {
"topic": "Artificial intelligence regulation",
"start_date": "2026-01-01",
"limit": 100,
"offset": 0
}
all_articles = []
while True:
response = requests.get(
"https://api.wokelo.ai/api/enterprise/industry/news/",
headers=HEADERS,
params=PARAMS
)
data = response.json()
batch = data.get("data", [])
all_articles.extend(batch)
fetched = len(all_articles)
total = data["total"]
print(f"Fetched {fetched} / {total} articles")
if fetched >= total or not batch:
break
PARAMS["offset"] += PARAMS["limit"]
# Deduplicate by article id
seen_ids = set()
unique = []
for a in all_articles:
if a["id"] not in seen_ids:
seen_ids.add(a["id"])
unique.append(a)
print(f"\nTotal unique articles: {len(unique)}")
```
### Comparing sector activity across geographies
Pull the same topic for multiple regions and compare article volume and recency — useful for understanding where in the world a theme is most actively developing.
```python theme={"system"}
import requests
from datetime import datetime, timedelta
HEADERS = {"Authorization": "Bearer "}
REGIONS = {
"North America": "USA,CAN,MEX",
"Europe": "GBR,DEU,FRA,NLD,SWE",
"Asia-Pacific": "CHN,JPN,KOR,IND,AUS,SGP"
}
topic = "Generative AI investment"
start_date = (datetime.today() - timedelta(days=90)).strftime("%Y-%m-%d")
end_date = datetime.today().strftime("%Y-%m-%d")
print(f"Topic: {topic} | Last 90 days\n{'='*50}")
for region_name, geo in REGIONS.items():
response = requests.get(
"https://api.wokelo.ai/api/enterprise/industry/news/",
headers=HEADERS,
params={
"topic": topic,
"geo": geo,
"start_date": start_date,
"end_date": end_date,
"limit": 1 # We only need total count
}
)
total = response.json().get("total", 0)
print(f"{region_name:<20} {total:>5} articles")
```
### JavaScript / Node.js
```javascript theme={"system"}
const fetch = require("node-fetch");
async function getIndustryNews(topic, options = {}) {
const params = new URLSearchParams({
topic,
...(options.geo && { geo: options.geo }),
...(options.startDate && { start_date: options.startDate }),
...(options.endDate && { end_date: options.endDate }),
...(options.blacklisted && { blacklisted: options.blacklisted }),
limit: options.limit || 100,
offset: options.offset || 0
});
const response = await fetch(
`https://api.wokelo.ai/api/enterprise/industry/news/?${params}`,
{
method: "GET",
headers: {
"Authorization": `Bearer ${process.env.WOKELO_API_KEY}`,
"Content-Type": "application/json"
}
}
);
if (!response.ok) {
throw new Error(`API error: ${response.status} ${response.statusText}`);
}
return response.json();
}
// Example: monitor warehouse automation in India and Germany
getIndustryNews("Warehouse automation", {
geo: "IND,DEU",
startDate: "2026-01-01",
endDate: "2026-04-30"
}).then(data => {
console.log(`Found ${data.total} articles`);
data.data.forEach(a => {
console.log(`[${a.geo.join(", ")}] ${a.title}`);
});
});
```
***
## 7. Error Handling
The API uses standard HTTP status codes. All error responses include a JSON body with a `detail` or `message` field.
| Status | Meaning | Cause & Resolution |
| --------------------------- | ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `200 OK` | Success | Articles returned successfully. |
| `400 Bad Request` | Invalid parameters | A required parameter is missing or a value is invalid — e.g. missing `topic`, malformed `start_date`, or invalid ISO country code in `geo`. Check the `detail` field. |
| `401 Unauthorized` | Auth failed | The `Authorization` header is missing, malformed, or contains an invalid token. Verify your key in **Settings → API Keys**. |
| `403 Forbidden` | Insufficient access | Your plan does not include access to this endpoint. Contact [support@wokelo.ai](mailto:support@wokelo.ai) to review your plan. |
| `429 Too Many Requests` | Rate limit exceeded | Implement exponential back-off. The response includes a `Retry-After` header. |
| `500 Internal Server Error` | Server error | Retry after a brief delay. If the issue persists, contact [support@wokelo.ai](mailto:support@wokelo.ai). |
**Error response example:**
```json theme={"system"}
{
"status": "error",
"detail": "The 'topic' parameter is required."
}
```
**Retry logic with exponential back-off:**
```python theme={"system"}
import time, requests
def fetch_industry_news_with_retry(params, api_key, max_retries=3):
headers = {
"Authorization": f"Bearer {api_key}",
"Content-Type": "application/json"
}
for attempt in range(max_retries):
try:
response = requests.get(
"https://api.wokelo.ai/api/enterprise/industry/news/",
headers=headers,
params=params,
timeout=30
)
if response.status_code == 429:
wait = 2 ** attempt # 1s, 2s, 4s
time.sleep(wait)
continue
response.raise_for_status()
return response.json()
except requests.exceptions.Timeout:
if attempt == max_retries - 1:
raise
time.sleep(1)
raise Exception(f"Failed after {max_retries} attempts")
```
***
## 8. Best Practices
**Write a specific, descriptive `topic` — this is the single highest-impact parameter**
The `topic` field drives the entire article retrieval. A vague topic like `"technology"` returns an enormous, noisy result set. A specific topic describing the exact theme, technology, or event produces a tight, actionable feed:
```python theme={"system"}
# ❌ Too broad — will return millions of tangentially related articles
params["topic"] = "technology"
# ✅ Specific — returns a focused, high-signal result set
params["topic"] = "Warehouse automation and robotics"
params["topic"] = "US-China semiconductor export controls"
params["topic"] = "Offshore wind farm development in the North Sea"
params["topic"] = "GLP-1 weight loss drug market competition"
```
**Use `geo` to narrow scope, not to replace topic specificity**
The `geo` filter restricts articles to those tagged with specific countries, but a vague topic with aggressive `geo` filtering can still return a noisy result set. Lead with a specific topic and use `geo` to reduce geographic noise:
```python theme={"system"}
# For India-specific EV charging — be specific in both dimensions
params = {
"topic": "Electric vehicle charging infrastructure investment",
"geo": "IND"
}
```
**Use ISO 3166-1 alpha-3 codes — not alpha-2**
The `geo` parameter requires 3-letter codes (`"USA"`, `"GBR"`, `"DEU"`) not the 2-letter equivalents (`"US"`, `"GB"`, `"DE"`). Passing alpha-2 codes will not filter correctly and may return unexpected results.
```python theme={"system"}
# ❌ Wrong format — 2-letter codes
params["geo"] = "US, GB"
# ✅ Correct format — 3-letter ISO codes
params["geo"] = "USA,GBR"
```
**Set a date window for every production run**
Without `start_date` and `end_date`, the query returns articles across the full Wokelo index, which for active topics can mean thousands of articles. Always bound queries to the window you intend to process — 30-day windows work well for regular monitoring runs, 7-day windows for weekly digests:
```python theme={"system"}
from datetime import datetime, timedelta
end_date = datetime.today().strftime("%Y-%m-%d")
start_date = (datetime.today() - timedelta(days=30)).strftime("%Y-%m-%d")
params["start_date"] = start_date
params["end_date"] = end_date
```
**Use article `id` for deduplication across runs**
The `id` field is a stable identifier for each article in Wokelo's index. When running the same topic query on an overlapping date range (e.g. daily refreshes), deduplicate by `id` to avoid processing the same article twice:
```python theme={"system"}
seen_ids = set()
new_articles = []
for a in articles:
if a["id"] not in seen_ids:
seen_ids.add(a["id"])
new_articles.append(a)
```
**Blacklist press release aggregators to improve signal quality**
Wire services and press release aggregators (`prnewswire.com`, `businesswire.com`, `globenewswire.com`) publish high volumes of company-issued releases that can dominate topic results. Blacklisting these domains surfaces editorial journalism and independent analysis:
```python theme={"system"}
params["blacklisted"] = (
"https://www.prnewswire.com/, "
"https://www.businesswire.com/, "
"https://www.globenewswire.com/"
)
```
**Use `ai_summary` for fast triage before fetching full articles**
The `ai_summary` field provides a reliable 2–4 sentence synopsis that is sufficient for most triage decisions. Read full articles via the `url` field only for items that pass your relevance threshold, rather than attempting to scrape all articles in a result set.
**Understand the difference from Company News Monitoring**
The Industry API response schema is intentionally leaner — it does not include `sentiment`, `primary_tag`, `secondary_tags`, `newsworthiness_impact`, `company_names`, `publisher`, `author`, or `scraped_text`. If you need these enrichment fields, or if your monitoring is anchored to specific companies, use the [Company News Monitoring API](/company-news-monitoring-doc) instead. The two APIs are complementary: industry monitoring for broad thematic coverage, company monitoring for entity-level depth.
***
## 9. Related APIs
Fetch company-specific news with richer enrichment — sentiment, event categories, company mentions, and full article text.
Retrieve a curated, cross-company newsfeed based on a topic, theme, or portfolio watchlist.
Generate a comprehensive AI research report on any industry — market size, competitive dynamics, key players, and outlook.
Run a structured, async AI research workflow on an industry topic and receive a formatted output report.
Discover and map all companies competing in a specific market or product category.
Company Search, Request Status, and other utilities used alongside monitoring workflows.