如何用 Python API 根据公司名称批量查找企业官网并补全缺失网址

1python3 -m venv .venv
2source .venv/bin/activate
3python -m pip install requests

1export DATABLIST_API_KEY="exampleuser-exampleaccount-EXAMPLE_TOKEN_NOT_VALID-2"

1import json
2import os
3import time
4import uuid
5
6import requests
7
8
9API_BASE_URL = "https://api.datablist.com/v1"
10
11
12def find_domains(companies, api_key):
13    headers = {
14        "Accept": "application/json",
15        "Content-Type": "application/json",
16        "X-API-Key": api_key,
17    }
18    inputs = [
19        {
20            "inputId": company["id"],
21            "data": {
22                "companyName": company["company_name"],
23                "targetCountry": company.get("country", ""),
24            },
25        }
26        for company in companies
27    ]
28    unique_id = f"python-domain-lookup-{uuid.uuid4().hex}"
29    payload = {
30        "enrichmentId": "company-name-to-domain",
31        "uniqueId": unique_id,
32        "settings": {
33            "workflow": "dataset_google",
34            "countryOverwrite": True,
35            "acceptNonRoot": True,
36        },
37        "inputs": inputs,
38    }
39
40    print(f"Task uniqueId: {unique_id}")
41    response = requests.post(
42        f"{API_BASE_URL}/enrichments/tasks",
43        headers=headers,
44        json=payload,
45    )
46    response.raise_for_status()
47    task_id = response.json()["@id"]
48
49    while True:
50        response = requests.get(
51            f"{API_BASE_URL}/enrichments/tasks/{task_id}",
52            headers=headers,
53        )
54        response.raise_for_status()
55        task = response.json()
56        if task["status"] in {"completed", "failed", "stopped"}:
57            break
58        time.sleep(3)
59
60    if task["status"] != "completed":
61        raise RuntimeError(
62            f"Task {task_id} ended with status {task['status']}: {task.get('error')}"
63        )
64
65    results = []
66    cursor = None
67    while True:
68        params = {"limit": 100}
69        if cursor is not None:
70            params["cursor"] = cursor
71
72        response = requests.get(
73            f"{API_BASE_URL}/enrichments/tasks/{task_id}/results",
74            headers=headers,
75            params=params,
76        )
77        response.raise_for_status()
78        page = response.json()
79        results.extend(page["results"])
80        cursor = page.get("nextCursor")
81        if cursor is None:
82            break
83
84    return results
85
86
87api_key = os.environ["DATABLIST_API_KEY"]
88companies = [
89    {
90        "id": "direct-microsoft-us",
91        "company_name": "Microsoft",
92        "country": "US",
93    }
94]
95
96lookup_results = find_domains(companies, api_key)
97for result in lookup_results:
98    print(json.dumps(result, indent=2))

1python find_company_websites.py

{
  "inputId": "direct-microsoft-us",
  "status": "success",
  "outputs": {
    "companyUrl": "https://microsoft.com",
    "companyDomain": "microsoft.com",
    "domainConfidence": "High"
  },
  "creditsUsed": "1",
  "error": null
}

1response = requests.post(
2    f"{API_BASE_URL}/enrichments/tasks",
3    headers=headers,
4    json=payload,
5)
6response.raise_for_status()
7task_id = response.json()["@id"]

1while True:
2    response = requests.get(
3        f"{API_BASE_URL}/enrichments/tasks/{task_id}",
4        headers=headers,
5    )
6    response.raise_for_status()
7    task = response.json()
8    if task["status"] in {"completed", "failed", "stopped"}:
9        break
10    time.sleep(3)

1results.extend(page["results"])
2cursor = page.get("nextCursor")
3if cursor is None:
4    break

1curl --get "https://api.datablist.com/v1/enrichments/tasks" \
2  --header "X-API-Key: $DATABLIST_API_KEY" \
3  --data-urlencode "enrichmentId=company-name-to-domain"

1records = [
2    {
3        "id": "crm-001",
4        "company_name": "Microsoft",
5        "country": "US",
6        "website": "https://www.microsoft.com",
7    },
8    {
9        "id": "crm-002",
10        "company_name": "boulangerie du palais lyon",
11        "country": "FR",
12        "website": "",
13    },
14    {
15        "id": "crm-003",
16        "company_name": "Mercury Engineering",
17        "country": "IE",
18        "website": None,
19    },
20    {
21        "id": "crm-004",
22        "company_name": "Mercury",
23        "country": "US",
24        "website": "   ",
25    },
26    {
27        "id": "crm-005",
28        "company_name": "Datablist",
29        "country": "FR",
30        "website": "https://www.datablist.com",
31    },
32    {
33        "id": "crm-006",
34        "company_name": "Mercury",
35        "country": "IE",
36        "website": None,
37    },
38]
39
40
41def website_is_missing(value):
42    return not isinstance(value, str) or not value.strip()
43
44
45records_to_lookup = [
46    record for record in records if website_is_missing(record.get("website"))
47]
48lookup_results = (
49    find_domains(records_to_lookup, api_key) if records_to_lookup else []
50)
51results_by_id = {result["inputId"]: result for result in lookup_results}
52
53for record in records:
54    if not website_is_missing(record.get("website")):
55        record["website_lookup"] = {"status": "not_requested"}
56        continue
57
58    result = results_by_id.get(record["id"])
59    if result is None:
60        record["website_lookup"] = {
61            "status": "missing_result",
62            "domain": None,
63            "confidence": None,
64            "credits": None,
65            "error": {
66                "code": "missing_result",
67                "message": "No result was returned for this inputId.",
68            },
69        }
70        continue
71
72    outputs = result.get("outputs") or {}
73    if result["status"] == "success" and outputs.get("companyUrl"):
74        record["website"] = outputs["companyUrl"]
75
76    record["website_lookup"] = {
77        "status": result["status"],
78        "domain": outputs.get("companyDomain"),
79        "confidence": outputs.get("domainConfidence"),
80        "credits": result.get("creditsUsed"),
81        "error": result.get("error"),
82    }
83
84print(json.dumps(records, indent=2))