HTML

Text

Converter

import os, requests

API = "https://api.mixpeek.com"
H = {"Authorization": f"Bearer {os.environ['MIXPEEK_API_KEY']}",
     "X-Namespace": os.environ["NAMESPACE_ID"]}

# 1. a bucket, with a schema that declares the field you will send
bucket = requests.post(f"{API}/v1/buckets", headers=H, json={
    "bucket_name": "html-inputs",
    "bucket_schema": {"properties": {"html": {"type": "text"}}},
}).json()

# 2. land the file as an object. the URL goes in data, on the blob
requests.post(f"{API}/v1/buckets/{bucket['bucket_id']}/objects", headers=H, json={
    "key_prefix": "run-1",
    "blobs": [{"property": "html", "type": "text",
               "data": "https://example.com/page.html"}],
})

# 3. a collection over that bucket, running the extractor
collection = requests.post(f"{API}/v1/collections", headers=H, json={
    "collection_name": "html-to-text",
    "source": {"type": "bucket", "bucket_ids": [bucket["bucket_id"]]},
    "feature_extractor": {"feature_extractor_name": "web_scraper", "version": "v1"},
}).json()

# 4. run extraction over the bucket
requests.post(f"{API}/v1/buckets/{bucket['bucket_id']}/batches", headers=H, json={
    "collection_ids": [collection["collection_id"]],
    "auto_submit": True,
})

# 5. read the output
docs = requests.get(
    f"{API}/v1/collections/{collection['collection_id']}/documents", headers=H
).json()
print(docs)