克劳德网络爬虫：将可空的统计表转换为干净的JSON

pip install "anthropic==0.120.0" "openai==2.48.0" requests

export ANTHROPIC_API_KEY="sk-ant-your_key"
export SCRAPELESS_API_KEY="sk_your_scrapeless_key"

# fetch_teams.py — 通过 Scrapeless 获取球队统计页面
import os

import requests

resp = requests.post(
    "https://api.scrapeless.com/api/v2/unlocker/request",
    headers={
        "Content-Type": "application/json",
        "x-api-token": os.environ["SCRAPELESS_API_KEY"],
    },
    json={
        "actor": "unlocker.webunlocker",
        "input": {"url": "https://scrapethissite.com/pages/forms/", "method": "GET", "js_render": True},
    },
    timeout=120,
)
resp.raise_for_status()
html = resp.json().get("data", "")
print(f"获取 {len(html):,} 字符")
print("球队行：", html.count('<tr class="team">'))

with open("page.html", "w", encoding="utf-8") as f:
    f.write(html)

# extract_claude.py — 原生 Claude 提取（需要 ANTHROPIC_API_KEY）
import json

from anthropic import Anthropic

client = Anthropic()  # 从环境中读取 ANTHROPIC_API_KEY

page_html = open("page.html", encoding="utf-8").read()

response = client.messages.create(
    model="claude-haiku-4-5",
    max_tokens=6000,
    system="从此表中提取每个团队赛季行。ot_losses 在单元格为空时为 null。",
    messages=[{"role": "user", "content": page_html}],
    output_config={
        "format": {
            "type": "json_schema",
            "schema": {
                "type": "object",
                "properties": {
                    "teams": {
                        "type": "array",
                        "items": {
                            "type": "object",
                            "properties": {
                                "name": {"type": "string"},
                                "year": {"type": "integer"},
                                "wins": {"type": "integer"},
                                "losses": {"type": "integer"},
                                "ot_losses": {"type": ["integer", "null"]},
                                "win_pct": {"type": "number"},
                                "goals_for": {"type": "integer"},
                                "goals_against": {"type": "integer"},
                            },
                            "required": ["name", "year", "wins", "losses", "ot_losses", "win_pct", "goals_for", "goals_against"],
                            "additionalProperties": False,
                        },
                    }
                },
                "required": ["teams"],
                "additionalProperties": False,
            },
        }
    },
)

text = next(b.text for b in response.content if b.type == "text")
data = json.loads(text)
print(f"提取到 {len(data['teams'])} 支球队")

# extract_openrouter.py — 通过 OpenRouter 执行相同的提取
import json
import os

import requests
from openai import OpenAI

resp = requests.post(
    "https://api.scrapeless.com/api/v2/unlocker/request",
    headers={
        "Content-Type": "application/json",
        "x-api-token": os.environ["SCRAPELESS_API_KEY"],
    },
    json={
        "actor": "unlocker.webunlocker",
        "input": {"url": "https://scrapethissite.com/pages/forms/", "method": "GET", "js_render": True},
    },
    timeout=120,
)
resp.raise_for_status()
page_html = resp.json().get("data", "")

client = OpenAI(base_url="https://openrouter.ai/api/v1", api_key=os.environ["OPENROUTER_API_KEY"])

completion = client.chat.completions.create(
    model="anthropic/claude-haiku-4.5",
    temperature=0,
    max_tokens=6000,
    response_format={"type": "json_object"},
    messages=[
        {
            "role": "system",
            "content": '从此表中提取每个团队赛季行。仅回复 JSON: '
            '{"teams":[{"name":str,"year":int,"wins":int,"losses":int,"ot_losses":int|null,'
            '"win_pct":number,"goals_for":int,"goals_against":int}]}. '
            "ot_losses 在单元格为空时为 null。",
        },
        {"role": "user", "content": page_html},
    ],
)

raw = completion.choices[0].message.content.strip()
if raw.startswith("```"):
    raw = raw.split("```")[1]
    if raw.startswith("json"):
        raw = raw[4:]
data = json.loads(raw)
print(f"提取到 {len(data['teams'])} 支球队")
print(json.dumps(data["teams"][0], ensure_ascii=False))

提取到 25 支球队
{"name": "波士顿棕熊", "year": 1990, "wins": 44, "losses": 24, "ot_losses": null, "win_pct": 0.55, "goals_for": 299, "goals_against": 264}